X264-视频压缩编码VCL

在前面的过程中，我们得到了编码图像，编码器开始H264视频编码VCL。首先初始化有关参数，包括帧类型的获取、创建多参考帧的列表、初始化码流控制、初始化写码流结构和写SPS、PPS头结构信息。

1.初始化相关参数

若为IDR帧，则意味着一个新图像片的开始。在H264中为了防止编码错误扩散，规定当前片不以本片以外的其他帧为参考，因而编码器遇到IDR帧则需要重置参考帧区域。同时，将SEI、SPS、PPS分别单独写入NAL单元。这三个参数集集合了编解码的核心参数，直接关系解码端能否正常解码。

若不是IDR帧，依据帧类型设定当前NAL单元的类型和图像片的类型。接着进行一系列初始化参数的操作，包括建立关于参考帧的list0和list1，初始化码流控制得到量化步长、参考帧等相关信息，初始化写比特流环境变量等。

在函数x264_lookahead_put_frame（）中，将fenc放入lookanead.next.list[]队列，再调用函数x264_lookahead_get_frame（）判断帧的类型。

x264_lookahead_get_frame（）：

//通过lookahead分析帧类型
void x264_lookahead_get_frames( x264_t *h )
{
    if( h->param.i_sync_lookahead )
    {   /* We have a lookahead thread, so get frames from there */
        x264_pthread_mutex_lock( &h->lookahead->ofbuf.mutex );
        while( !h->lookahead->ofbuf.i_size && h->lookahead->b_thread_active )
            x264_pthread_cond_wait( &h->lookahead->ofbuf.cv_fill, &h->lookahead->ofbuf.mutex );
        x264_lookahead_encoder_shift( h );
        x264_pthread_mutex_unlock( &h->lookahead->ofbuf.mutex );
    }
    else
    {   /* We are not running a lookahead thread, so perform all the slicetype decide on the fly */
    	//currect[]必须为空，next不能为空？
        if( h->frames.current[0] || !h->lookahead->next.i_size )
            return;
        //分析lookahead->next->list帧的类型
        x264_stack_align( x264_slicetype_decide, h );
        //更新lookahead->last_nonb
        x264_lookahead_update_last_nonb( h, h->lookahead->next.list[0] );
        int shift_frames = h->lookahead->next.list[0]->i_bframes + 1;
        //lookahead->next.list移动到lookahead->ofbuf.list
        x264_lookahead_shift( &h->lookahead->ofbuf, &h->lookahead->next, shift_frames );

        /* For MB-tree and VBV lookahead, we have to perform propagation analysis on I-frames too. */
        if( h->lookahead->b_analyse_keyframe && IS_X264_TYPE_I( h->lookahead->last_nonb->i_type ) )
            x264_stack_align( x264_slicetype_analyse, h, shift_frames );

        //lookahead->ofbuf.list帧移动到frames->current
        x264_lookahead_encoder_shift( h );
    }
}

函数 x264_lookahead_get_frame（）里调用了x264_slicetype_decide（）函数来判断帧的类型：

//确定帧的类型（I、B、P）
void x264_slicetype_decide( x264_t *h )
{
    x264_frame_t *frames[X264_BFRAME_MAX+2];
    x264_frame_t *frm;
    int bframes;
    int brefs;

    if( !h->lookahead->next.i_size )
        return;

    int lookahead_size = h->lookahead->next.i_size;

    //遍历next队列
    for( int i = 0; i < h->lookahead->next.i_size; i++ )
    {
        if( h->param.b_vfr_input )
        {
            if( lookahead_size-- > 1 )
                h->lookahead->next.list[i]->i_duration = 2 * (h->lookahead->next.list[i+1]->i_pts - h->lookahead->next.list[i]->i_pts);
            else
                h->lookahead->next.list[i]->i_duration = h->i_prev_duration;
        }
        else
            h->lookahead->next.list[i]->i_duration = delta_tfi_divisor[h->lookahead->next.list[i]->i_pic_struct];
        h->i_prev_duration = h->lookahead->next.list[i]->i_duration;
        h->lookahead->next.list[i]->f_duration = (double)h->lookahead->next.list[i]->i_duration
                                               * h->sps->vui.i_num_units_in_tick
                                               / h->sps->vui.i_time_scale;

        if( h->lookahead->next.list[i]->i_frame > h->i_disp_fields_last_frame && lookahead_size > 0 )
        {
            h->lookahead->next.list[i]->i_field_cnt = h->i_disp_fields;
            h->i_disp_fields += h->lookahead->next.list[i]->i_duration;
            h->i_disp_fields_last_frame = h->lookahead->next.list[i]->i_frame;
        }
        else if( lookahead_size == 0 )
        {
            h->lookahead->next.list[i]->i_field_cnt = h->i_disp_fields;
            h->lookahead->next.list[i]->i_duration = h->i_prev_duration;
        }
    }

    if( h->param.rc.b_stat_read )
    {
    	//b_stat_read在2pass模式的第2遍才不为0

        /* Use the frame types from the first pass */
        for( int i = 0; i < h->lookahead->next.i_size; i++ )
            h->lookahead->next.list[i]->i_type =
                x264_ratecontrol_slice_type( h, h->lookahead->next.list[i]->i_frame );
    }
    else if( (h->param.i_bframe && h->param.i_bframe_adaptive)
             || h->param.i_scenecut_threshold
             || h->param.rc.b_mb_tree
             || (h->param.rc.i_vbv_buffer_size && h->param.rc.i_lookahead) )
        x264_slicetype_analyse( h, 0 );//分析帧的类型（I、B、P）
    //===========================================================================

    for( bframes = 0, brefs = 0;; bframes++ )
    {
    	//从next队列取出1个
        frm = h->lookahead->next.list[bframes];
        //BREF的处理
        if( frm->i_type == X264_TYPE_BREF && h->param.i_bframe_pyramid < X264_B_PYRAMID_NORMAL &&
            brefs == h->param.i_bframe_pyramid )
        {
        	//BREF改成B
            frm->i_type = X264_TYPE_B;
            x264_log( h, X264_LOG_WARNING, "B-ref at frame %d incompatible with B-pyramid %s \n",
                      frm->i_frame, x264_b_pyramid_names[h->param.i_bframe_pyramid] );
        }
        /* pyramid with multiple B-refs needs a big enough dpb that the preceding P-frame stays available.
           smaller dpb could be supported by smart enough use of mmco, but it's easier just to forbid it. */
        else if( frm->i_type == X264_TYPE_BREF && h->param.i_bframe_pyramid == X264_B_PYRAMID_NORMAL &&
            brefs && h->param.i_frame_reference <= (brefs+3) )
        {
            frm->i_type = X264_TYPE_B;
            x264_log( h, X264_LOG_WARNING, "B-ref at frame %d incompatible with B-pyramid %s and %d reference frames\n",
                      frm->i_frame, x264_b_pyramid_names[h->param.i_bframe_pyramid], h->param.i_frame_reference );
        }
        //Keyframe处理
        if( frm->i_type == X264_TYPE_KEYFRAME )
            frm->i_type = h->param.b_open_gop ? X264_TYPE_I : X264_TYPE_IDR;

        /* Limit GOP size */
        if( (!h->param.b_intra_refresh || frm->i_frame == 0) && frm->i_frame - h->lookahead->i_last_keyframe >= h->param.i_keyint_max )
        {
            if( frm->i_type == X264_TYPE_AUTO || frm->i_type == X264_TYPE_I )
                frm->i_type = h->param.b_open_gop && h->lookahead->i_last_keyframe >= 0 ? X264_TYPE_I : X264_TYPE_IDR;
            int warn = frm->i_type != X264_TYPE_IDR;
            if( warn && h->param.b_open_gop )
                warn &= frm->i_type != X264_TYPE_I;
            if( warn )
            {
                x264_log( h, X264_LOG_WARNING, "specified frame type (%d) at %d is not compatible with keyframe interval\n", frm->i_type, frm->i_frame );
                frm->i_type = h->param.b_open_gop && h->lookahead->i_last_keyframe >= 0 ? X264_TYPE_I : X264_TYPE_IDR;
            }
        }
        if( frm->i_type == X264_TYPE_I && frm->i_frame - h->lookahead->i_last_keyframe >= h->param.i_keyint_min )
        {
            if( h->param.b_open_gop )
            {
                h->lookahead->i_last_keyframe = frm->i_frame; // Use display order
                if( h->param.b_bluray_compat )
                    h->lookahead->i_last_keyframe -= bframes; // Use bluray order
                frm->b_keyframe = 1;
            }
            else
                frm->i_type = X264_TYPE_IDR;
        }
        if( frm->i_type == X264_TYPE_IDR )
        {
            /* Close GOP */
        	//设置当前帧为“上一个关键帧”
            h->lookahead->i_last_keyframe = frm->i_frame;
            frm->b_keyframe = 1;
            if( bframes > 0 )
            {
                bframes--;
                h->lookahead->next.list[bframes]->i_type = X264_TYPE_P;
            }
        }

        if( bframes == h->param.i_bframe ||
            !h->lookahead->next.list[bframes+1] )
        {
            if( IS_X264_TYPE_B( frm->i_type ) )
                x264_log( h, X264_LOG_WARNING, "specified frame type is not compatible with max B-frames\n" );
            if( frm->i_type == X264_TYPE_AUTO
                || IS_X264_TYPE_B( frm->i_type ) )
                frm->i_type = X264_TYPE_P;
        }

        if( frm->i_type == X264_TYPE_BREF )
            brefs++;

        if( frm->i_type == X264_TYPE_AUTO )
            frm->i_type = X264_TYPE_B;

        else if( !IS_X264_TYPE_B( frm->i_type ) ) break;
    }

    if( bframes )
        h->lookahead->next.list[bframes-1]->b_last_minigop_bframe = 1;
    h->lookahead->next.list[bframes]->i_bframes = bframes;

    /* insert a bref into the sequence */
    if( h->param.i_bframe_pyramid && bframes > 1 && !brefs )
    {
        h->lookahead->next.list[bframes/2]->i_type = X264_TYPE_BREF;
        brefs++;
    }

    /* calculate the frame costs ahead of time for x264_rc_analyse_slice while we still have lowres */
    if( h->param.rc.i_rc_method != X264_RC_CQP )
    {
        x264_mb_analysis_t a;
        int p0, p1, b;
        p1 = b = bframes + 1;

        x264_lowres_context_init( h, &a );

        frames[0] = h->lookahead->last_nonb;
        memcpy( &frames[1], h->lookahead->next.list, (bframes+1) * sizeof(x264_frame_t*) );
        if( IS_X264_TYPE_I( h->lookahead->next.list[bframes]->i_type ) )
            p0 = bframes + 1;
        else // P
            p0 = 0;

        x264_slicetype_frame_cost( h, &a, frames, p0, p1, b, 0 );

        if( (p0 != p1 || bframes) && h->param.rc.i_vbv_buffer_size )
        {
            /* We need the intra costs for row SATDs. */
            x264_slicetype_frame_cost( h, &a, frames, b, b, b, 0 );

            /* We need B-frame costs for row SATDs. */
            p0 = 0;
            for( b = 1; b <= bframes; b++ )
            {
                if( frames[b]->i_type == X264_TYPE_B )
                    for( p1 = b; frames[p1]->i_type == X264_TYPE_B; )
                        p1++;
                else
                    p1 = bframes + 1;
                x264_slicetype_frame_cost( h, &a, frames, p0, p1, b, 0 );
                if( frames[b]->i_type == X264_TYPE_BREF )
                    p0 = b;
            }
        }
    }

    /* Analyse for weighted P frames */
    if( !h->param.rc.b_stat_read && h->lookahead->next.list[bframes]->i_type == X264_TYPE_P
        && h->param.analyse.i_weighted_pred >= X264_WEIGHTP_SIMPLE )
    {
        x264_emms();
        x264_weights_analyse( h, h->lookahead->next.list[bframes], h->lookahead->last_nonb, 0 );
    }

    /* shift sequence to coded order.
       use a small temporary list to avoid shifting the entire next buffer around */
    int i_coded = h->lookahead->next.list[0]->i_frame;
    if( bframes )
    {
        int idx_list[] = { brefs+1, 1 };
        for( int i = 0; i < bframes; i++ )
        {
            int idx = idx_list[h->lookahead->next.list[i]->i_type == X264_TYPE_BREF]++;
            frames[idx] = h->lookahead->next.list[i];
            frames[idx]->i_reordered_pts = h->lookahead->next.list[idx]->i_pts;
        }
        frames[0] = h->lookahead->next.list[bframes];
        frames[0]->i_reordered_pts = h->lookahead->next.list[0]->i_pts;
        memcpy( h->lookahead->next.list, frames, (bframes+1) * sizeof(x264_frame_t*) );
    }

    for( int i = 0; i <= bframes; i++ )
    {
        h->lookahead->next.list[i]->i_coded = i_coded++;
        if( i )
        {
            x264_calculate_durations( h, h->lookahead->next.list[i], h->lookahead->next.list[i-1], &h->i_cpb_delay, &h->i_coded_fields );
            h->lookahead->next.list[0]->f_planned_cpb_duration[i-1] = (double)h->lookahead->next.list[i]->i_cpb_duration *
                                                                      h->sps->vui.i_num_units_in_tick / h->sps->vui.i_time_scale;
        }
        else
            x264_calculate_durations( h, h->lookahead->next.list[i], NULL, &h->i_cpb_delay, &h->i_coded_fields );
    }
}

在这个函数里又调用了另一个重要函数：x264_slicetype_analyse（），用来分析帧的类型。

//分析帧的类型（I、B、P）
void x264_slicetype_analyse( x264_t *h, int intra_minigop )
{
    x264_mb_analysis_t a;
    x264_frame_t *frames[X264_LOOKAHEAD_MAX+3] = { NULL, };
    int num_frames, orig_num_frames, keyint_limit, framecnt;
    int i_mb_count = NUM_MBS;
    int cost1p0, cost2p0, cost1b1, cost2p1;
    // 确定最大的搜索长度
    // 在我的调试当中， h->lookahead->next.i_size = 4
    int i_max_search = X264_MIN( h->lookahead->next.i_size, X264_LOOKAHEAD_MAX );
    int vbv_lookahead = h->param.rc.i_vbv_buffer_size && h->param.rc.i_lookahead;
    /* For determinism we should limit the search to the number of frames lookahead has for sure
     * in h->lookahead->next.list buffer, except at the end of stream.
     * For normal calls with (intra_minigop == 0) that is h->lookahead->i_slicetype_length + 1 frames.
     * And for I-frame calls (intra_minigop != 0) we already removed intra_minigop frames from there. */
    if( h->param.b_deterministic )
        i_max_search = X264_MIN( i_max_search, h->lookahead->i_slicetype_length + 1 - intra_minigop );
    int keyframe = !!intra_minigop;

    assert( h->frames.b_have_lowres );

    if( !h->lookahead->last_nonb )
        return;
    //frames[0]指向上一次的非B帧
    frames[0] = h->lookahead->last_nonb;
    //frames[] 依次指向 lookahead->next链表中的帧
    for( framecnt = 0; framecnt < i_max_search && h->lookahead->next.list[framecnt]->i_type == X264_TYPE_AUTO; framecnt++ )
        frames[framecnt+1] = h->lookahead->next.list[framecnt];

    x264_lowres_context_init( h, &a );

    if( !framecnt )
    {
        if( h->param.rc.b_mb_tree )
            x264_macroblock_tree( h, &a, frames, 0, keyframe );
        return;
    }

    keyint_limit = h->param.i_keyint_max - frames[0]->i_frame + h->lookahead->i_last_keyframe - 1;
    orig_num_frames = num_frames = h->param.b_intra_refresh ? framecnt : X264_MIN( framecnt, keyint_limit );

    /* This is important psy-wise: if we have a non-scenecut keyframe,
     * there will be significant visual artifacts if the frames just before
     * go down in quality due to being referenced less, despite it being
     * more RD-optimal. */
    if( (h->param.analyse.b_psy && h->param.rc.b_mb_tree) || vbv_lookahead )
        num_frames = framecnt;
    else if( h->param.b_open_gop && num_frames < framecnt )
        num_frames++;
    else if( num_frames == 0 )
    {
        frames[1]->i_type = X264_TYPE_I;
        return;
    }

    int num_bframes = 0;
    int num_analysed_frames = num_frames;
    int reset_start;
    //通过scenecut()函数判断是否有场景切换，从而确定I帧
    if( h->param.i_scenecut_threshold && scenecut( h, &a, frames, 0, 1, 1, orig_num_frames, i_max_search ) )
    {
        frames[1]->i_type = X264_TYPE_I;
        return;
    }

#if HAVE_OPENCL
    x264_opencl_slicetype_prep( h, frames, num_frames, a.i_lambda );
#endif
    //允许有B帧的时候
    if( h->param.i_bframe )
    {
        if( h->param.i_bframe_adaptive == X264_B_ADAPT_TRELLIS )
        {
            if( num_frames > 1 )
            {
                char best_paths[X264_BFRAME_MAX+1][X264_LOOKAHEAD_MAX+1] = {"","P"};
                int best_path_index = num_frames % (X264_BFRAME_MAX+1);

                /* Perform the frametype analysis. */
                for( int j = 2; j <= num_frames; j++ )
                    x264_slicetype_path( h, &a, frames, j, best_paths );

                num_bframes = strspn( best_paths[best_path_index], "B" );
                /* Load the results of the analysis into the frame types. */
                for( int j = 1; j < num_frames; j++ )
                    frames[j]->i_type = best_paths[best_path_index][j-1] == 'B' ? X264_TYPE_B : X264_TYPE_P;
            }
            frames[num_frames]->i_type = X264_TYPE_P;
        }
        else if( h->param.i_bframe_adaptive == X264_B_ADAPT_FAST )
        {
            for( int i = 0; i <= num_frames-2; )
            {
            	//i+2作为Ｐ帧编码的代价
                //注：i+2始终为P帧
            	cost2p1 = x264_slicetype_frame_cost( h, &a, frames, i+0, i+2, i+2, 1 );
                if( frames[i+2]->i_intra_mbs[2] > i_mb_count / 2 )
                {
                    frames[i+1]->i_type = X264_TYPE_P;
                    frames[i+2]->i_type = X264_TYPE_P;
                    i += 2;
                    continue;
                }

#if HAVE_OPENCL
                if( h->param.b_opencl )
                {
                    int b_work_done = 0;
                    b_work_done |= x264_opencl_precalculate_frame_cost(h, frames, a.i_lambda, i+0, i+2, i+1 );
                    b_work_done |= x264_opencl_precalculate_frame_cost(h, frames, a.i_lambda, i+0, i+1, i+1 );
                    b_work_done |= x264_opencl_precalculate_frame_cost(h, frames, a.i_lambda, i+1, i+2, i+2 );
                    if( b_work_done )
                        x264_opencl_flush( h );
                }
#endif
                //计算代价
                //x264_slicetype_frame_cost(,,,p0,p1,b,)
                //p0 b p1
                //p1!=b为B帧，否则为P帧

                // i + 1 作为B帧编码的代价
                cost1b1 = x264_slicetype_frame_cost( h, &a, frames, i+0, i+2, i+1, 0 );
                // i + 1 作为P帧编码的代价
                cost1p0 = x264_slicetype_frame_cost( h, &a, frames, i+0, i+1, i+1, 0 );
                // i + 2 作为P帧编码的代价
                cost2p0 = x264_slicetype_frame_cost( h, &a, frames, i+1, i+2, i+2, 0 );
                //如果i+1作为P帧编码的代价　+ i+2作为P帧编码的代价
                //小于 i+1作为B帧编码的代价   + i+2作为P帧编码的代价
                if( cost1p0 + cost2p0 < cost1b1 + cost2p1 )
                {
                    //那么i+1将作为P帧编码
                    //然后直接continue
                    frames[i+1]->i_type = X264_TYPE_P;
                    i += 1;
                    continue;
                }

                // arbitrary and untuned
                #define INTER_THRESH 300
                #define P_SENS_BIAS (50 - h->param.i_bframe_bias)

                // i+1 将作为B帧编码
                frames[i+1]->i_type = X264_TYPE_B;

                int j;
                for( j = i+2; j <= X264_MIN( i+h->param.i_bframe, num_frames-1 ); j++ )
                {
                    int pthresh = X264_MAX(INTER_THRESH - P_SENS_BIAS * (j-i-1), INTER_THRESH/10);
                    // 预测j+1作为P帧编码代价
                    int pcost = x264_slicetype_frame_cost( h, &a, frames, i+0, j+1, j+1, 1 );
                    // 如果pcost 满足下述条件， 则确定了一个P帧，跳出循环
                    if( pcost > pthresh*i_mb_count || frames[j+1]->i_intra_mbs[j-i+1] > i_mb_count/3 )
                        break;
                    // 否则就是B帧
                    frames[j]->i_type = X264_TYPE_B;
                }
                // 将j帧确定为P帧
                frames[j]->i_type = X264_TYPE_P;
                i = j;
            }
            // 最后一帧确定为P帧
            frames[num_frames]->i_type = X264_TYPE_P;
            num_bframes = 0;
            // 确定有多少个B帧
            while( num_bframes < num_frames && frames[num_bframes+1]->i_type == X264_TYPE_B )
                num_bframes++;
        }
        else
        {
        	// 确定多少B帧
            num_bframes = X264_MIN(num_frames-1, h->param.i_bframe);
            // 每num_bframes + 1一个P帧， 其余皆为B帧
            for( int j = 1; j < num_frames; j++ )
                frames[j]->i_type = (j%(num_bframes+1)) ? X264_TYPE_B : X264_TYPE_P;
            // 最后一帧为P帧
            frames[num_frames]->i_type = X264_TYPE_P;
        }

        /* Check scenecut on the first minigop. */
        // 如果B帧中， 有帧有场景切换， 则改变其为P帧
        for( int j = 1; j < num_bframes+1; j++ )
            if( h->param.i_scenecut_threshold && scenecut( h, &a, frames, j, j+1, 0, orig_num_frames, i_max_search ) )
            {
                frames[j]->i_type = X264_TYPE_P;
                num_analysed_frames = j;
                break;
            }

        reset_start = keyframe ? 1 : X264_MIN( num_bframes+2, num_analysed_frames+1 );
    }
    else
    {
    	//h->param.i_bframe为 0
    	//则所有的帧皆为P帧
        for( int j = 1; j <= num_frames; j++ )
            frames[j]->i_type = X264_TYPE_P;
        reset_start = !keyframe + 1;
        num_bframes = 0;
    }

    /* Perform the actual macroblock tree analysis.
     * Don't go farther than the maximum keyframe interval; this helps in short GOPs. */
    if( h->param.rc.b_mb_tree )
        x264_macroblock_tree( h, &a, frames, X264_MIN(num_frames, h->param.i_keyint_max), keyframe );

    /* Enforce keyframe limit. */
    if( !h->param.b_intra_refresh )
        for( int i = keyint_limit+1; i <= num_frames; i += h->param.i_keyint_max )
        {
        	//迫使为I帧
            frames[i]->i_type = X264_TYPE_I;
            reset_start = X264_MIN( reset_start, i+1 );
            if( h->param.b_open_gop && h->param.b_bluray_compat )
                while( IS_X264_TYPE_B( frames[i-1]->i_type ) )
                    i--;
        }

    if( vbv_lookahead )
        x264_vbv_lookahead( h, &a, frames, num_frames, keyframe );

    /* Restore frametypes for all frames that haven't actually been decided yet. */
    for( int j = reset_start; j <= num_frames; j++ )
        frames[j]->i_type = X264_TYPE_AUTO;

#if HAVE_OPENCL
    x264_opencl_slicetype_end( h );
#endif
}

获取了帧的类型后，调用函数x264_slice_init（）创建Slice Header。

//创建Slice Header
static inline void x264_slice_init( x264_t *h, int i_nal_type, int i_global_qp )
{
    /* ------------------------ Create slice header  ----------------------- */
    if( i_nal_type == NAL_SLICE_IDR )
    {
    	//I帧

    	//对x264_slice_header_t进行赋值
        x264_slice_header_init( h, &h->sh, h->sps, h->pps, h->i_idr_pic_id, h->i_frame_num, i_global_qp );

        /* alternate id */
        if( h->param.i_avcintra_class )
        {
            switch( h->i_idr_pic_id )
            {
                case 5:
                    h->i_idr_pic_id = 3;
                    break;
                case 3:
                    h->i_idr_pic_id = 4;
                    break;
                case 4:
                default:
                    h->i_idr_pic_id = 5;
                    break;
            }
        }
        else
            h->i_idr_pic_id ^= 1;
    }
    else
    {
    	//非IDR帧
        x264_slice_header_init( h, &h->sh, h->sps, h->pps, -1, h->i_frame_num, i_global_qp );
        //参考帧列表
        h->sh.i_num_ref_idx_l0_active = h->i_ref[0] <= 0 ? 1 : h->i_ref[0];
        h->sh.i_num_ref_idx_l1_active = h->i_ref[1] <= 0 ? 1 : h->i_ref[1];
        if( h->sh.i_num_ref_idx_l0_active != h->pps->i_num_ref_idx_l0_default_active ||
            (h->sh.i_type == SLICE_TYPE_B && h->sh.i_num_ref_idx_l1_active != h->pps->i_num_ref_idx_l1_default_active) )
        {
            h->sh.b_num_ref_idx_override = 1;
        }
    }

    if( h->fenc->i_type == X264_TYPE_BREF && h->param.b_bluray_compat && h->sh.i_mmco_command_count )
    {
        h->b_sh_backup = 1;
        h->sh_backup = h->sh;
    }

    h->fdec->i_frame_num = h->sh.i_frame_num;

    if( h->sps->i_poc_type == 0 )
    {
        h->sh.i_poc = h->fdec->i_poc;
        if( PARAM_INTERLACED )
        {
            h->sh.i_delta_poc_bottom = h->param.b_tff ? 1 : -1;
            h->sh.i_poc += h->sh.i_delta_poc_bottom == -1;
        }
        else
            h->sh.i_delta_poc_bottom = 0;
        h->fdec->i_delta_poc[0] = h->sh.i_delta_poc_bottom == -1;
        h->fdec->i_delta_poc[1] = h->sh.i_delta_poc_bottom ==  1;
    }
    else
    {
        /* Nothing to do ? */
    }
    //主要对mb结构体赋初值
    x264_macroblock_slice_init( h );
}

做好一切准备后，接下来就是对视频图像的实际编码了。

2.编码

编码的主要函数是x264_slices_write（）：

//真正的编码——编码1个图像帧
//注意“slice”后面有一个“s”
//它其中又调用了一个x264_slice_write()
//这一点要区分开
static void *x264_slices_write( x264_t *h )
{
    int i_slice_num = 0;
    int last_thread_mb = h->sh.i_last_mb;

    /* init stats */
    memset( &h->stat.frame, 0, sizeof(h->stat.frame) );
    h->mb.b_reencode_mb = 0;
    //循环每一个slice（一幅图像可以由多个Slice构成）
    while( h->sh.i_first_mb + SLICE_MBAFF*h->mb.i_mb_stride <= last_thread_mb )
    {
        h->sh.i_last_mb = last_thread_mb;
        if( !i_slice_num || !x264_frame_new_slice( h, h->fdec ) )
        {
            if( h->param.i_slice_max_mbs )
            {
                if( SLICE_MBAFF )
                {
                    // convert first to mbaff form, add slice-max-mbs, then convert back to normal form
                    int last_mbaff = 2*(h->sh.i_first_mb % h->mb.i_mb_width)
                        + h->mb.i_mb_width*(h->sh.i_first_mb / h->mb.i_mb_width)
                        + h->param.i_slice_max_mbs - 1;
                    int last_x = (last_mbaff % (2*h->mb.i_mb_width))/2;
                    int last_y = (last_mbaff / (2*h->mb.i_mb_width))*2 + 1;
                    h->sh.i_last_mb = last_x + h->mb.i_mb_stride*last_y;
                }
                else
                {
                    h->sh.i_last_mb = h->sh.i_first_mb + h->param.i_slice_max_mbs - 1;
                    if( h->sh.i_last_mb < last_thread_mb && last_thread_mb - h->sh.i_last_mb < h->param.i_slice_min_mbs )
                        h->sh.i_last_mb = last_thread_mb - h->param.i_slice_min_mbs;
                }
                i_slice_num++;
            }
            else if( h->param.i_slice_count && !h->param.b_sliced_threads )
            {
                int height = h->mb.i_mb_height >> PARAM_INTERLACED;
                int width = h->mb.i_mb_width << PARAM_INTERLACED;
                i_slice_num++;
                h->sh.i_last_mb = (height * i_slice_num + h->param.i_slice_count/2) / h->param.i_slice_count * width - 1;
            }
        }
        h->sh.i_last_mb = X264_MIN( h->sh.i_last_mb, last_thread_mb );
        //真正的编码——编码1个Slice
        //x264_stack_align()应该是平台优化过程中内存对齐的工作
        //实际上就是调用x264_slice_write()
        if( x264_stack_align( x264_slice_write, h ) )
            goto fail;
        //注意这里对i_first_mb进行了赋值
        h->sh.i_first_mb = h->sh.i_last_mb + 1;
        // if i_first_mb is not the last mb in a row then go to the next mb in MBAFF order
        if( SLICE_MBAFF && h->sh.i_first_mb % h->mb.i_mb_width )
            h->sh.i_first_mb -= h->mb.i_mb_stride;
    }

    return (void *)0;

fail:
    /* Tell other threads we're done, so they wouldn't wait for it */
    if( h->param.b_sliced_threads )
        x264_threadslice_cond_broadcast( h, 2 );
    return (void *)-1;
}

其内部调用了函数x264_slice_write（），x264_slices_write（）的单位是帧，而x264_slice_write（）的单位是Slice，这两个是不一样的，一帧可以有多个Slice，一帧也可以只有一个Slice。

x264_slice_write（）：

static intptr_t x264_slice_write( x264_t *h )
{
    int i_skip;
    //宏块的序号，以及序号对应的x，y坐标
    int mb_xy, i_mb_x, i_mb_y;
    /* NALUs other than the first use a 3-byte startcode.
     * Add one extra byte for the rbsp, and one more for the final CABAC putbyte.
     * Then add an extra 5 bytes just in case, to account for random NAL escapes and
     * other inaccuracies. */
    int overhead_guess = (NALU_OVERHEAD - (h->param.b_annexb && h->out.i_nal)) + 1 + h->param.b_cabac + 5;
    int slice_max_size = h->param.i_slice_max_size > 0 ? (h->param.i_slice_max_size-overhead_guess)*8 : 0;
    int back_up_bitstream_cavlc = !h->param.b_cabac && h->sps->i_profile_idc < PROFILE_HIGH;
    int back_up_bitstream = slice_max_size || back_up_bitstream_cavlc;
    int starting_bits = bs_pos(&h->out.bs);
    int b_deblock = h->sh.i_disable_deblocking_filter_idc != 1;
    int b_hpel = h->fdec->b_kept_as_ref;
    int orig_last_mb = h->sh.i_last_mb;
    int thread_last_mb = h->i_threadslice_end * h->mb.i_mb_width - 1;
    uint8_t *last_emu_check;
#define BS_BAK_SLICE_MAX_SIZE 0
#define BS_BAK_CAVLC_OVERFLOW 1
#define BS_BAK_SLICE_MIN_MBS  2
#define BS_BAK_ROW_VBV        3
    x264_bs_bak_t bs_bak[4];
    b_deblock &= b_hpel || h->param.b_full_recon || h->param.psz_dump_yuv;
    bs_realign( &h->out.bs );

    /* Slice */
    //开始输出一个NAL
    //后面对应着x264_nal_end()
    x264_nal_start( h, h->i_nal_type, h->i_nal_ref_idc );
    h->out.nal[h->out.i_nal].i_first_mb = h->sh.i_first_mb;

    /* Slice header */

    //存储宏块像素的缓存fdec_buf和fenc_buf的初始化
    //宏块编码缓存p_fenc[0]，p_fenc[1]，p_fenc[2]
    //宏块重建缓存p_fdec[0]，p_fdec[1]，p_fdec[2]
    //[0]存Y，[1]存U，[2]存V
    x264_macroblock_thread_init( h );

    /* Set the QP equal to the first QP in the slice for more accurate CABAC initialization. */
    h->mb.i_mb_xy = h->sh.i_first_mb;
    h->sh.i_qp = x264_ratecontrol_mb_qp( h );
    h->sh.i_qp = SPEC_QP( h->sh.i_qp );
    h->sh.i_qp_delta = h->sh.i_qp - h->pps->i_pic_init_qp;
    //输出 slice header
    x264_slice_header_write( &h->out.bs, &h->sh, h->i_nal_ref_idc );
    //如果使用CABAC，需要初始化
    if( h->param.b_cabac )
    {
        /* alignment needed */
        bs_align_1( &h->out.bs );

        /* init cabac */
        x264_cabac_context_init( h, &h->cabac, h->sh.i_type, x264_clip3( h->sh.i_qp-QP_BD_OFFSET, 0, 51 ), h->sh.i_cabac_init_idc );
        x264_cabac_encode_init ( &h->cabac, h->out.bs.p, h->out.bs.p_end );
        last_emu_check = h->cabac.p;
    }
    else
        last_emu_check = h->out.bs.p;
    h->mb.i_last_qp = h->sh.i_qp;
    h->mb.i_last_dqp = 0;
    h->mb.field_decoding_flag = 0;
    //宏块位置-纵坐标（初始值）
    i_mb_y = h->sh.i_first_mb / h->mb.i_mb_width;
    //宏块位置-横坐标（初始值）
    i_mb_x = h->sh.i_first_mb % h->mb.i_mb_width;
    i_skip = 0;

    //一个大循环
    //对一个slice中每个宏块进行编码
    while( 1 )
    {
    	//宏块序号。由i_mb_x和i_mb_y计算而来。
        mb_xy = i_mb_x + i_mb_y * h->mb.i_mb_width;
        int mb_spos = bs_pos(&h->out.bs) + x264_cabac_pos(&h->cabac);
        //一行的开始
        if( i_mb_x == 0 )
        {
            if( x264_bitstream_check_buffer( h ) )
                return -1;
            if( !(i_mb_y & SLICE_MBAFF) && h->param.rc.i_vbv_buffer_size )
                x264_bitstream_backup( h, &bs_bak[BS_BAK_ROW_VBV], i_skip, 1 );
            //去块效应滤波、半像素插值、SSIM/PSNR计算等
            //一次处理一行宏块
            if( !h->mb.b_reencode_mb )
                x264_fdec_filter_row( h, i_mb_y, 0 );
        }

        if( back_up_bitstream )
        {
            if( back_up_bitstream_cavlc )
                x264_bitstream_backup( h, &bs_bak[BS_BAK_CAVLC_OVERFLOW], i_skip, 0 );
            if( slice_max_size && !(i_mb_y & SLICE_MBAFF) )
            {
                x264_bitstream_backup( h, &bs_bak[BS_BAK_SLICE_MAX_SIZE], i_skip, 0 );
                if( (thread_last_mb+1-mb_xy) == h->param.i_slice_min_mbs )
                    x264_bitstream_backup( h, &bs_bak[BS_BAK_SLICE_MIN_MBS], i_skip, 0 );
            }
        }

        if( PARAM_INTERLACED )
        {
            if( h->mb.b_adaptive_mbaff )
            {
                if( !(i_mb_y&1) )
                {
                    /* FIXME: VSAD is fast but fairly poor at choosing the best interlace type. */
                    h->mb.b_interlaced = x264_field_vsad( h, i_mb_x, i_mb_y );
                    memcpy( &h->zigzagf, MB_INTERLACED ? &h->zigzagf_interlaced : &h->zigzagf_progressive, sizeof(h->zigzagf) );
                    if( !MB_INTERLACED && (i_mb_y+2) == h->mb.i_mb_height )
                        x264_expand_border_mbpair( h, i_mb_x, i_mb_y );
                }
            }
            h->mb.field[mb_xy] = MB_INTERLACED;
        }

        /* load cache */
        //将要编码的宏块的周围的宏块的值读进来
        //主要是上面、左边块的值
        if( SLICE_MBAFF )
            x264_macroblock_cache_load_interlaced( h, i_mb_x, i_mb_y );
        else
            x264_macroblock_cache_load_progressive( h, i_mb_x, i_mb_y );
        //分析-帧内预测模式选择、帧间运动估计等
        x264_macroblock_analyse( h );

        /* encode this macroblock -> be careful it can change the mb type to P_SKIP if needed */
reencode:
		//编码-残差DCT变换、量化
        x264_macroblock_encode( h );
        //输出CABAC
        if( h->param.b_cabac )
        {
            if( mb_xy > h->sh.i_first_mb && !(SLICE_MBAFF && (i_mb_y&1)) )
                x264_cabac_encode_terminal( &h->cabac );

            if( IS_SKIP( h->mb.i_type ) )
                x264_cabac_mb_skip( h, 1 );
            else
            {
                if( h->sh.i_type != SLICE_TYPE_I )
                    x264_cabac_mb_skip( h, 0 );
                //输出
                x264_macroblock_write_cabac( h, &h->cabac );
            }
        }
        else
        {
        	//输出CAVLC
            if( IS_SKIP( h->mb.i_type ) )
                i_skip++;
            else
            {
                if( h->sh.i_type != SLICE_TYPE_I )
                {
                    bs_write_ue( &h->out.bs, i_skip );  /* skip run */
                    i_skip = 0;
                }
                //输出
                x264_macroblock_write_cavlc( h );
                /* If there was a CAVLC level code overflow, try again at a higher QP. */
                if( h->mb.b_overflow )
                {
                    h->mb.i_chroma_qp = h->chroma_qp_table[++h->mb.i_qp];
                    h->mb.i_skip_intra = 0;
                    h->mb.b_skip_mc = 0;
                    h->mb.b_overflow = 0;
                    x264_bitstream_restore( h, &bs_bak[BS_BAK_CAVLC_OVERFLOW], &i_skip, 0 );
                    goto reencode;
                }
            }
        }

        int total_bits = bs_pos(&h->out.bs) + x264_cabac_pos(&h->cabac);
        int mb_size = total_bits - mb_spos;

        if( slice_max_size && (!SLICE_MBAFF || (i_mb_y&1)) )
        {
            /* Count the skip run, just in case. */
            if( !h->param.b_cabac )
                total_bits += bs_size_ue_big( i_skip );
            /* Check for escape bytes. */
            uint8_t *end = h->param.b_cabac ? h->cabac.p : h->out.bs.p;
            for( ; last_emu_check < end - 2; last_emu_check++ )
                if( last_emu_check[0] == 0 && last_emu_check[1] == 0 && last_emu_check[2] <= 3 )
                {
                    slice_max_size -= 8;
                    last_emu_check++;
                }
            /* We'll just re-encode this last macroblock if we go over the max slice size. */
            if( total_bits - starting_bits > slice_max_size && !h->mb.b_reencode_mb )
            {
                if( !x264_frame_new_slice( h, h->fdec ) )
                {
                    /* Handle the most obnoxious slice-min-mbs edge case: we need to end the slice
                     * because it's gone over the maximum size, but doing so would violate slice-min-mbs.
                     * If possible, roll back to the last checkpoint and try again.
                     * We could try raising QP, but that would break in the case where a slice spans multiple
                     * rows, which the re-encoding infrastructure can't currently handle. */
                    if( mb_xy <= thread_last_mb && (thread_last_mb+1-mb_xy) < h->param.i_slice_min_mbs )
                    {
                        if( thread_last_mb-h->param.i_slice_min_mbs < h->sh.i_first_mb+h->param.i_slice_min_mbs )
                        {
                            x264_log( h, X264_LOG_WARNING, "slice-max-size violated (frame %d, cause: slice-min-mbs)\n", h->i_frame );
                            slice_max_size = 0;
                            goto cont;
                        }
                        x264_bitstream_restore( h, &bs_bak[BS_BAK_SLICE_MIN_MBS], &i_skip, 0 );
                        h->mb.b_reencode_mb = 1;
                        h->sh.i_last_mb = thread_last_mb-h->param.i_slice_min_mbs;
                        break;
                    }
                    if( mb_xy-SLICE_MBAFF*h->mb.i_mb_stride != h->sh.i_first_mb )
                    {
                        x264_bitstream_restore( h, &bs_bak[BS_BAK_SLICE_MAX_SIZE], &i_skip, 0 );
                        h->mb.b_reencode_mb = 1;
                        if( SLICE_MBAFF )
                        {
                            // set to bottom of previous mbpair
                            if( i_mb_x )
                                h->sh.i_last_mb = mb_xy-1+h->mb.i_mb_stride*(!(i_mb_y&1));
                            else
                                h->sh.i_last_mb = (i_mb_y-2+!(i_mb_y&1))*h->mb.i_mb_stride + h->mb.i_mb_width - 1;
                        }
                        else
                            h->sh.i_last_mb = mb_xy-1;
                        break;
                    }
                    else
                        h->sh.i_last_mb = mb_xy;
                }
                else
                    slice_max_size = 0;
            }
        }
cont:
        h->mb.b_reencode_mb = 0;

        /* save cache */
        //保存当前宏块的的值，用于以后的宏块的编码
        //包括Intra4x4宏块帧内预测模式，DCT非零系数，运动矢量，参考帧序号等等
        x264_macroblock_cache_save( h );
        //码率控制
        if( x264_ratecontrol_mb( h, mb_size ) < 0 )
        {
            x264_bitstream_restore( h, &bs_bak[BS_BAK_ROW_VBV], &i_skip, 1 );
            h->mb.b_reencode_mb = 1;
            i_mb_x = 0;
            i_mb_y = i_mb_y - SLICE_MBAFF;
            h->mb.i_mb_prev_xy = i_mb_y * h->mb.i_mb_stride - 1;
            h->sh.i_last_mb = orig_last_mb;
            continue;
        }

        /* accumulate mb stats */
        //后面很大一段代码都是对stat结构体中的统计信息进行赋值================================
        h->stat.frame.i_mb_count[h->mb.i_type]++;

        int b_intra = IS_INTRA( h->mb.i_type );
        int b_skip = IS_SKIP( h->mb.i_type );
        if( h->param.i_log_level >= X264_LOG_INFO || h->param.rc.b_stat_write )
        {
            if( !b_intra && !b_skip && !IS_DIRECT( h->mb.i_type ) )
            {
                if( h->mb.i_partition != D_8x8 )
                        h->stat.frame.i_mb_partition[h->mb.i_partition] += 4;
                    else
                        for( int i = 0; i < 4; i++ )
                            h->stat.frame.i_mb_partition[h->mb.i_sub_partition[i]] ++;
                if( h->param.i_frame_reference > 1 )
                    for( int i_list = 0; i_list <= (h->sh.i_type == SLICE_TYPE_B); i_list++ )
                        for( int i = 0; i < 4; i++ )
                        {
                            int i_ref = h->mb.cache.ref[i_list][ x264_scan8[4*i] ];
                            if( i_ref >= 0 )
                                h->stat.frame.i_mb_count_ref[i_list][i_ref] ++;
                        }
            }
        }

        if( h->param.i_log_level >= X264_LOG_INFO )
        {
            if( h->mb.i_cbp_luma | h->mb.i_cbp_chroma )
            {
                if( CHROMA444 )
                {
                    for( int i = 0; i < 4; i++ )
                        if( h->mb.i_cbp_luma & (1 << i) )
                            for( int p = 0; p < 3; p++ )
                            {
                                int s8 = i*4+p*16;
                                int nnz8x8 = M16( &h->mb.cache.non_zero_count[x264_scan8[s8]+0] )
                                           | M16( &h->mb.cache.non_zero_count[x264_scan8[s8]+8] );
                                h->stat.frame.i_mb_cbp[!b_intra + p*2] += !!nnz8x8;
                            }
                }
                else
                {
                    int cbpsum = (h->mb.i_cbp_luma&1) + ((h->mb.i_cbp_luma>>1)&1)
                               + ((h->mb.i_cbp_luma>>2)&1) + (h->mb.i_cbp_luma>>3);
                    h->stat.frame.i_mb_cbp[!b_intra + 0] += cbpsum;
                    h->stat.frame.i_mb_cbp[!b_intra + 2] += !!h->mb.i_cbp_chroma;
                    h->stat.frame.i_mb_cbp[!b_intra + 4] += h->mb.i_cbp_chroma >> 1;
                }
            }
            if( h->mb.i_cbp_luma && !b_intra )
            {
                h->stat.frame.i_mb_count_8x8dct[0] ++;
                h->stat.frame.i_mb_count_8x8dct[1] += h->mb.b_transform_8x8;
            }
            if( b_intra && h->mb.i_type != I_PCM )
            {
                if( h->mb.i_type == I_16x16 )
                    h->stat.frame.i_mb_pred_mode[0][h->mb.i_intra16x16_pred_mode]++;
                else if( h->mb.i_type == I_8x8 )
                    for( int i = 0; i < 16; i += 4 )
                        h->stat.frame.i_mb_pred_mode[1][h->mb.cache.intra4x4_pred_mode[x264_scan8[i]]]++;
                else //if( h->mb.i_type == I_4x4 )
                    for( int i = 0; i < 16; i++ )
                        h->stat.frame.i_mb_pred_mode[2][h->mb.cache.intra4x4_pred_mode[x264_scan8[i]]]++;
                h->stat.frame.i_mb_pred_mode[3][x264_mb_chroma_pred_mode_fix[h->mb.i_chroma_pred_mode]]++;
            }
            h->stat.frame.i_mb_field[b_intra?0:b_skip?2:1] += MB_INTERLACED;
        }
        //===========================================================

        /* calculate deblock strength values (actual deblocking is done per-row along with hpel) */
        //计算去块效应滤波器强度Bs
        //这里没有滤波
        if( b_deblock )
            x264_macroblock_deblock_strength( h );

        //如果处理完最后一个宏块，就跳出大循环
        if( mb_xy == h->sh.i_last_mb )
            break;

        if( SLICE_MBAFF )
        {
            i_mb_x += i_mb_y & 1;
            i_mb_y ^= i_mb_x < h->mb.i_mb_width;
        }
        else
            i_mb_x++;//宏块序号x加1
        //处理完一行宏块
        if( i_mb_x == h->mb.i_mb_width )
        {
        	//该处理下一行了
            i_mb_y++;//宏块序号y加1
            i_mb_x = 0;//宏块序号x设置为0
        }
    }
    if( h->sh.i_last_mb < h->sh.i_first_mb )
        return 0;

    h->out.nal[h->out.i_nal].i_last_mb = h->sh.i_last_mb;

    //熵编码的收尾工作
    if( h->param.b_cabac )
    {
        x264_cabac_encode_flush( h, &h->cabac );
        h->out.bs.p = h->cabac.p;
    }
    else
    {
        if( i_skip > 0 )
            bs_write_ue( &h->out.bs, i_skip );  /* last skip run */
        /* rbsp_slice_trailing_bits */
        bs_rbsp_trailing( &h->out.bs );
        bs_flush( &h->out.bs );
    }
    //结束输出一个NAL
    //前面对应着x264_nal_start()
    if( x264_nal_end( h ) )
        return -1;
    //多线程并行处理？
    if( h->sh.i_last_mb == (h->i_threadslice_end * h->mb.i_mb_width - 1) )
    {
        h->stat.frame.i_misc_bits = bs_pos( &h->out.bs )
                                  + (h->out.i_nal*NALU_OVERHEAD * 8)
                                  - h->stat.frame.i_tex_bits
                                  - h->stat.frame.i_mv_bits;
        x264_fdec_filter_row( h, h->i_threadslice_end, 0 );

        if( h->param.b_sliced_threads )
        {
            /* Tell the main thread we're done. */
            x264_threadslice_cond_broadcast( h, 1 );
            /* Do hpel now */
            for( int mb_y = h->i_threadslice_start; mb_y <= h->i_threadslice_end; mb_y++ )
                x264_fdec_filter_row( h, mb_y, 1 );
            x264_threadslice_cond_broadcast( h, 2 );
            /* Do the first row of hpel, now that the previous slice is done */
            if( h->i_thread_idx > 0 )
            {
                x264_threadslice_cond_wait( h->thread[h->i_thread_idx-1], 2 );
                x264_fdec_filter_row( h, h->i_threadslice_start + (1 << SLICE_MBAFF), 2 );
            }
        }

        /* Free mb info after the last thread's done using it */
        if( h->fdec->mb_info_free && (!h->param.b_sliced_threads || h->i_thread_idx == (h->param.i_threads-1)) )
        {
            h->fdec->mb_info_free( h->fdec->mb_info );
            h->fdec->mb_info = NULL;
            h->fdec->mb_info_free = NULL;
        }
    }

    return 0;
}

x264_slice_write（）函数的具体流程：

首先，调用x264_nal_start（）开始输出一个NALU；

接着，x264_macroblock_thread_init（）函数初始化宏块重建像素缓存fdec_buf[]和编码像素缓存fenc_buf[]。

接着调用x264_slice_header_write（）输出Slice Header。

进入一个循环，该循环每执行一次编码一个宏块。

（a）调用x264_fdec_filter_row（）执行滤波模块；

（b）调用x264_macroblock_cache_load_progressive（）将要编码的宏块的周围宏块的信息读进来。

（c）调用x264_macroblock_analyse（）执行分析模块。

（d）调用x264_macroblock_encode（）执行宏块编码信息。

（e）调用x264_macroblock_write_cabac（）/x264_macroblock_write_cavlc（）执行熵编码模块。

（f）调用x264_macroblock_cache_save（）保存当前宏块的信息。

（g）调用x264_ratecontrol_mb（）执行码率控制。

（h）准备处理下一个宏块。

最后调用x264_nal_end（）结束输出一个NALU。