Pattern recognition
Pattern recognition
复制标题
DOI：
10.4324/9780429028038-14
复制
发表时间：
2019-05
期刊：
影响因子：
--
通讯作者：
David B. Boles
中科院分区：
文献类型：
--
作者：
David B. Boles
在线多目标跟踪需要克服固有的检测器缺陷，例如，遗漏检测、错误警报和不准确的检测响应，以在不使用未来信息的情况下增长多个对象轨迹。在这个增长过程中存在各种干扰，如背景杂波，类似的目标和遮挡，这是一个很大的挑战。在这项工作中，我们提出了一种方法来学习一个分心感知的判别模型，可以处理连续错过和不准确的检测问题，由于遮挡或运动模糊。为了处理目标外观的变化，提出了一种关系注意学习机制，通过选择性地聚集历史状态中的特征，并从它们的外观拓扑关系中提取权重，来捕获不同的目标外观。基于该判别模型，设计了一个多级跟踪流水线，实现了弹道的自动初始化、传播和终止。广泛的实验分析和比较证明了其在广泛使用的具有挑战性的MOT16和MOT17基准测试中的最先进性能。为了便于多目标跟踪问题的进一步研究，本文公开了该算法的源代码。1
Online multi-object tracking needs to overcome the intrinsic detector deficiencies, e.g., missing detections, false alarms, and inaccurate detection responses, to grow multiple object trajectories without using future information. Various distractions exist during this growing process like background clutters, similar targets, and occlusions, which present a great challenge. We in this work propose a method for learning a distractor-aware discriminative model that can handle continuous missed and inaccurate detection problems due to the occlusion or the motion blur. To deal with target appearance variations, a relational attention learning mechanism is proposed to capture the distinctive target appearances by selectively aggregating features from history states with weights extracted from their appearance topological relationship. Based on the discrimination model, a multi-stage tracking pipeline is designed for automatic trajectory initialization,propagation, and termination. Extensive experimental analyses and comparisons demonstrate its state-of-the-art performance on widely used challenging MOT16 and MOT17 benchmarks. The source code of this work is released to facilitate further studies on the multi-object tracking problem. 1