激光与光电子学进展, 2020, 57 (22): 221507, 网络出版: 2020-11-12
目标跟踪中基于光流映射的模板更新算法 下载: 888次
Template-Updating Algorithm Based on Optical Flow Mapping in Object Tracking
机器视觉 目标跟踪 孪生网络 光流映射 模板更新 machine vision object tracking siamese network optical flow mapping template update
摘要
基于深层孪生网络的目标跟踪算法普遍缺乏目标模板在线更新方法,从而在某些复杂应用场景中适应能力较差。针对这一问题,提出一种基于光流映射的目标模板在线更新算法,该算法能够在保证实时性的前提下有效提高对复杂场景的适应能力。首先在跟踪过程中计算模板帧之间的光流信息;其次由光流映射和残差计算获取目标的运动变化信息。除此以外,还提出一种基于奇异值分解的由初始帧生成的修正项以修正目标位置偏差的方法。在OTB100和VOT2016数据集上对所提算法进行测试评估,结果显示,所提算法可以较好地优化新生成的目标模板,增强算法的鲁棒性,且与现有的跟踪算法相比,所提算法结果更佳。
Abstract
The tracking algorithm based on deep-level siamese network generally lacks the capability to update the target template online; hence, it exhibits poor adaptability in some complex application environments. Aiming to resolve this problem, a target template online-updating algorithm based on optical flow mapping is proposed herein. On the premise of ensuring real-time operation, the proposed algorithm can efficiently improve its adaptability in complex circumstances. First, the optical-flow information between the template frames is calculated in the tracking process. Then, the information of motion change is generated via optical flow mapping and residual calculation. Furthermore, based on singular value decomposition, a method that creates a correction term via the initial frame, which modifies the target-position deviation, is proposed herein. Finally, the proposed algorithm is tested on OTB100 and VOT2016 datasets. The results show that the proposed algorithm can optimize the new target template to enhance the robustness and can achieve the best results compared with existing tracking algorithms.
张静, 郝志晖, 刘婧. 目标跟踪中基于光流映射的模板更新算法[J]. 激光与光电子学进展, 2020, 57(22): 221507. Jing Zhang, Zhihui Hao, Jing Liu. Template-Updating Algorithm Based on Optical Flow Mapping in Object Tracking[J]. Laser & Optoelectronics Progress, 2020, 57(22): 221507.