计算机工程与应用 ›› 2022, Vol. 58 ›› Issue (18): 188-194.DOI: 10.3778/j.issn.1002-8331.2101-0222

• 模式识别与人工智能 • 上一篇    下一篇

面向多目标跟踪系统的专用循环目标检测器

牛嘉丰,石蕴玉,刘翔,贺桢,戴佩哲   

  1. 上海工程技术大学 电子电气工程学院,上海 201600
  • 出版日期:2022-09-15 发布日期:2022-09-15

Dedicated Cyclic Detector for Multiple Object Tracking

NIU Jiafeng, SHI Yunyu, LIU Xiang, HE Zhen, DAI Peizhe   

  1. School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai 201620, China
  • Online:2022-09-15 Published:2022-09-15

摘要: 多目标跟踪技术在视频分析、信号处理等领域有着广泛的应用。在现代多目标跟踪系统通常遵循的“按检测跟踪”模式中,目标检测器的性能决定了多目标跟踪任务的跟踪精度和速度。为提高多目标跟踪系统跟踪性能,提出了面向多目标跟踪系统的专用循环目标检测器,它利用视频帧序列间高度相似性的特点,依据先前帧的目标位置信息和当前帧相对于先前帧的变化得分图来选取候选框,解决了传统二阶段目标检测器中使用候选框推荐网络带来的参数量和计算量大的问题,同时融合了目标外观特征提取分支,进一步减少了多目标跟踪系统整体运行时间。实验表明,专用循环目标检测器及其他最先进的检测器分别应用于多目标跟踪系统,采用专用循环目标检测器时能够在保证多目标跟踪系统跟踪精度的情况下提升跟踪速度。

关键词: 多目标跟踪, 目标检测, 目标外观特征

Abstract: Multiple object tracking technology has been widely applied in video analysis, signal processing and other fields. The object detector’s performance determines the tracking accuracy and speed, in the “tracking by detection” mode that modern multiple object tracking systems usually follow. A dedicated cyclic detector is proposed to improve the tracking performance, which uses the characteristics of high similarity between video frames. The candidate frame is selected by considering object position information in the previous frame, and variation score map of current frame relative to the previous frame, which solves the problem of large parameters and calculations caused by region proposal network in traditional two-stage target detector. At the same time, dedicated cyclic detector integrating the object appearance feature extraction branch can further reduce the overall running time of multiple object tracking system. Dedicated cyclic detector and other state-of-the-art detectors are respectively applied to multiple object tracking system. Experimental results prove that dedicated cyclic detector can improve the tracking speed while ensuring the tracking accuracy.

Key words: multiple object tracking, object detection, appearance feature