激光与光电子学进展, 2020, 57 (24): 241008, 网络出版: 2020-11-19
一种基于改进SiameseRPN的全景视频目标跟踪算法 下载: 1023次
Algorithm for Panoramic Video Tracking Based on Improved SiameseRPN
图像处理 目标跟踪 深度学习 全景视频 MobileNetV3 SiameseRPN image processing target tracking deep learning panoramic video MobileNetV3 SiameseRPN
摘要
在全景视频目标跟踪过程中,由于光照条件变化复杂和目标相对镜头运动时尺度变化剧烈,目标跟踪算法存在精度低和适用性差等问题。为了解决这个问题,提出了一种基于改进SiameseRPN的全景视频目标跟踪算法。首先采用MobileNetV3中的网络结构提取深度特征,使算法对全景视频序列中出现的场景缺陷有更好的适应性,并利用Squeeze and Excite模块增加网络对特征选择的敏感度。提出并构建了一种基于双线性插值的特征融合模块,运用双线性插值的方法使输出的后三层深度特征具有相同尺度,并融合这三层特征以用于网络预测。最后利用分类分支预测出当前序列中的正负样本,利用回归分支预测当前输出目标的位置信息和尺度信息,最终输出目标的位置信息。实验结果表明:所提算法可以有效地解决全景数据中的局部图像质量欠佳和尺度变化的问题,在保持实时跟踪性能的同时,具有较高的跟踪精度,对目标跟踪中出现的小目标、目标遮挡及多目标交叉运动等情况表现出良好的适应性,具有良好的视觉效果和较高的跟踪得分。
Abstract
The target tracking algorithm is suffering from low accuracy and poor applicability due to the complex lighting conditions and severe changes in scale caused by the relative lens movement during panoramic video target tracking. To address this issue, we propose an algorithm for panoramic target tracking based on the improved SiameseRPN. First, the network structure of MobileNetV3 is used to extract the deep features to make the algorithm have a better adaptability to the scene defects appearing in panoramic video sequences, and the Squeeze and Excite module is used to increase the sensitivity of the network to feature selection. Then, we propose and construct a feature fusion module based on bilinear interpolation, which is used to make the output depth features of the last three layers have the same scale, and these three layers of features are fused for network prediction. Finally, we use a classification sequence to predict the positive and negative samples in the current sequence, and adopt a regression branch to predict the position information and scale information of current output targets. Thus the target position information is outputted. The experimental results show that the proposed algorithm has better tracking accuracy and it can effectively deal with the problems of poor local image quality and scale changes in panoramic data, while maintaining the real-time tracking performance. It shows a good adaptability to small targets, target occlusion, and multi-target cross movements in target tracking, and has good visual effects and high tracking scores.
王殿伟, 方浩宇, 刘颖, 姜静, 任新成, 许志杰, 覃泳睿. 一种基于改进SiameseRPN的全景视频目标跟踪算法[J]. 激光与光电子学进展, 2020, 57(24): 241008. Dianwei Wang, Haoyu Fang, Ying Liu, Jing Jiang, Xincheng Ren, Zhijie Xu, Yongrui Qin. Algorithm for Panoramic Video Tracking Based on Improved SiameseRPN[J]. Laser & Optoelectronics Progress, 2020, 57(24): 241008.