.png){kind=icon}
返回
Learning to Track Multiple Targets
.png){kind=icon}
PRE
AI
DOI：10.1109/TNNLS.2014.2333751.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Monocular multiple-object tracking is a fundamental yet under-addressed computer vision problem. In this paper, we propose a novel learning framework for tracking multiple objects by detection. First, instead of heuristically defining a tracking algorithm, we learn that a discriminative structure prediction model from labeled video data captures the interdependence of multiple influence factors. Given the joint targets state from the last time step and the observation at the current frame, the joint targets state at the current time step can then be inferred by maximizing the joint probability score. Second, our detection results benefit from tracking cues. The traditional detection algorithms need a nonmaximal suppression postprocessing to select a subset from the total detection responses as the final output and a large number of selection mistakes are induced, especially under a congested circumstance. Our method integrates both detection and tracking cues. This integration helps to decrease the postprocessing mistake risk and to improve performance in tracking. Finally, we formulate the entire model training into a convex optimization problem and estimate its parameters using the cutting plane optimization. Experiments show that our method performs effectively in a large variety of scenarios, including pedestrian tracking in crowd scenes and vehicle tracking in congested traffic.
Keyword:
Cutting plane
discriminative model
interdependence
learning to track
multiple-object tracking
structure prediction
tracking-by-detection
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
8.9
论文数:
7.5K
被引数:
7.2W
机构
引用论文
PTX encapsulated by an XG–DOX conjugate for combination therapy against multi-drug resistance.png)
RSC Advances
RSC AdvancesIF0
PREAI
分享收藏分享收藏
查看更多内容