参考文献:

MOTChallenge 2015: Towards a Benchmark for Multi-Target Tracking
Laura Leal-Taix ´e, Anton Milan, Ian Reid, Stefan Roth, and Konrad Schindler

1、DP_NMS:Network flow tracing

  where each node represents a detection and each edge represents a transition between two detections. Special source and sink nodes allow spawning and absorbing trajectories.

2、CEM:Continuous energy minimization

  The target state X is represented by continuous x; y coordinates in all frames. The energy E(X) is made up of several components, including a data term to keep the solution close to the observed data (detections), a dynamic model to smooth the trajectories, an exclusion term to avoid collisions, a persistence term to reduce track fragmentations, and a regularizer. The resulting energy is highly non-convex and is minimized in an alternating fashion using conjugate gradient descent and deterministic jump moves.

3、SMOT:Similar moving objects

The Similar Multi-Object Tracking (SMOT) approach [15] specifically targets situations where target appearance is ambiguous and rather concentrates on using the motion as a primary cue for data association. Tracklets with similar motion are linked to longer trajectories using the generalized linear assignment (GLA) formulation. The motion similarity and the underlying dynamics of a tracklet are modeled as the order of a linear regressor
approximating that tracklet

4、TBD: Tracking-by-detection

This two-stage tracking-by-detection (TBD) approach [21], [56] is part of a larger traffic scene understanding framework and employs a rather simple data association technique. The first stage links overlapping detections with similar appearance in successive frames into trackletsThe second stage aims to bridge occlusions of up to 20 frames. Both stages employ the Hungarian algorithm to optimally solve the matching problem. Note that we did not re-train this baseline but rather used the original implementation and parameters provided.

5、SFM: Social forces for tracking

Most tracking systems work with the assumption that the motion model for each target is independent, but in reality, a pedestrian follows a series of social rules, i.e. is subject to social forces according to other moving targets around him/her. These have been defined in what is called the social force model (SFM) [23], [26] and have recently been applied to multiple people tracking. For the 3D benchmark we include two baselines that include a few hand-designed force terms, such as collision avoidance or group attraction. The first method (KALMANSFM) [40] includes those in an online predictive Kalman filter approach while the second (LPSFM) [30] includes the social forces in a Linear Programming framework as described in Sec. 4.2. For the 2D benchmark, we include a recent algorithm (MOTICON) [29], which learns an image-based motion context that encodes the pedestrian’s reaction to the environment, i.e., other moving objects. The motion context, created from low-level image features, leads to a much richer representation of the physical interactions between targets compared to hand-specified social force models. This allows for a more accurate prediction of the future position of each pedestrian in image space, information that is then included in a Linear Programming framework for multi-target tracking.

6、TC ODAL: Tracklet confidence

Robust Online Multi-Object Tracking based on Tracklet Confidence and Online Discriminative Appearance Learning, or TC ODAL [8], is the only online method among the baselines. It proceeds in two stages. First, close detections are linked to form a set of short, reliable tracklets. This so-called local association allows one to progressively aggregate confident tracklets. In case of occlusions or missed detections, the tracklet confidence value is decreased and a global association is employed to bridge longer occlusion gaps. Both association techniques are formulated as bipartite matching and tackled with the Hungarian algorithm. Another prominent component of TC ODAL is online appearance learning. To that end, positive samples are collected from tracklets with high confidence and incremental linear discriminant analysis (ILDA) is employed to update the appearance model in an online fashion.

多目标跟踪baseline methods的更多相关文章

  1. Learning to Promote Saliency Detectors

    Learning to Promote Saliency Detectors 原本放在了思否上, 但是公式支持不好, csdn广告太多, 在博客园/掘金上发一下 https://github.com/ ...

  2. 【软件分析与挖掘】ELBlocker: Predicting blocking bugs with ensemble imbalance learning

    摘要: 提出一种方法——ELBlocker,用于自动检测出Blocking Bugs(prevent other bugs from being fixed). 难度在于这些Blocking Bugs仅 ...

  3. 近年Recsys论文

    2015年~2017年SIGIR,SIGKDD,ICML三大会议的Recsys论文: [转载请注明出处:https://www.cnblogs.com/shenxiaolin/p/8321722.ht ...

  4. CIKM 2013 Paper Modeling interaction features for debate side clustering

    中文简单介绍:本文对怎样对网上论坛讨论中用户交互关系进行统计建模分析进行了研究. 论文出处:CIKM'13. 英文摘要: Online discussion forums are popular so ...

  5. Deep-learning augmented RNA-seq analysis of transcript splicing | 用深度学习预测可变剪切

    可变剪切的预测已经很流行了,目前主要有两个流派: 用DNA序列以及variant来预测可变剪切:GeneSplicer.MaxEntScan.dbscSNV.S-CAP.MMSplice.clinVa ...

  6. 论文翻译——Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank

    Abstract Semantic word spaces have been very useful but cannot express the meaning of longer phrases ...

  7. 个性探测综述阅读笔记——Recent trends in deep learning based personality detection

    目录 abstract 1. introduction 1.1 个性衡量方法 1.2 应用前景 1.3 伦理道德 2. Related works 3. Baseline methods 3.1 文本 ...

  8. 论文解读(DeepWalk)《DeepWalk: Online Learning of Social Representations》

    一.基本信息 论文题目:<DeepWalk: Online Learning of Social Representations>发表时间:  KDD 2014论文作者:  Bryan P ...

  9. 论文解读(DFCN)《Deep Fusion Clustering Network》

    Paper information Titile:Deep Fusion Clustering Network Authors:Wenxuan Tu, Sihang Zhou, Xinwang Liu ...

随机推荐

  1. 一次org.springframework.jdbc.BadSqlGrammarException ### Error querying database Cause: com.mysql.jdbc.exceptions.jdbc4.MySQLSyntaxErrorException问题排查过程

    先说结论: 因为在表设计中有一个商品描述字段被设置为desc,但desc是mysql中的关键字,如select id,name,desc,price from product;这条sql语句在查询时的 ...

  2. 【运维技术】CentOS7上从零开始安装阿里RocketMQ版本:release-4.0.1【亲测哈哈】

    CentOS7上从零开始安装阿里RocketMQ版本:release-4.0.1[亲测哈哈] 安装git # 更新包 $ yum update # 安装git $ yum install git # ...

  3. Python笔记 #16# Pandas: Operations

    10 Minutes to pandas #Stats # shift 这玩意儿有啥用??? s = pd.Series([1,5,np.nan], index=dates).shift(0) # s ...

  4. JAVA volatile 解析

    volatile这个关键字可能很多朋友都听说过,或许也都用过.在Java 5之前,它是一个备受争议的关键字,因为在程序中使用它往往会导致出人意料的结果.在Java 5之后,volatile关键字才得以 ...

  5. Hash课堂测试补写

    Hash课堂测试补写 测试要求: 利用除留余数法为下列关键字集合的存储设计hash函数,并画出分别用开放寻址法和拉链法解决冲突得到的空间存储状态(散列因子取0.75) 关键字集合:85,75,57,6 ...

  6. QT+VS中ui不能声明为指针?

    问题描述:QtCreator里的UI全是默认为指针类型,调用的时候[ui->]但是使用VS+Qt来,发来默认的是变量类型,使用的时候[ui.] 统一:为了统一我把后者声明改为前者 问题:在mai ...

  7. git am PATCH_FILE_NAME自动打patch失败后的操作方法

    1.找到打入patch不成功的patch 从打入patch的失败信息可以找到 2.根据patch的index重新打入 patch,将可以合并的内容合并,冲突的部分单独生成文件 比如出问题patch的i ...

  8. (探讨贴)POJ 1463 树形DP解法的不正确性

    POJ1463是一个典型的树状DP题. 通常解法如下代码所示: using namespace std; ; ]; int pre[maxn]; int childcnt[maxn]; int n; ...

  9. POJ 2112 Optimal Milking(二分+最大流)

    http://poj.org/problem?id=2112 题意: 现在有K台挤奶器和C头奶牛,奶牛和挤奶器之间有距离,每台挤奶器每天最多为M头奶挤奶,现在要安排路程,使得C头奶牛所走的路程中的最大 ...

  10. [原][译][osgearth]样式表style中参数总结(OE官方文档翻译)

    几何Geometry 高度Altitude 挤压Extrusion 图标Icon 模型Model 渲染Render 皮肤Skin 文本Text 覆盖Coverage 提示: 在SDK中,样式表的命名空 ...