融合多阶语义增强的JDE多目标跟踪算法  

JDE multi⁃object tracking algorithm integrating multi⁃level semantic enhancement

作　　者：王俊 王鹏[2] 李晓艳[1] 王梁 孙梦宇 郜辉[1] WANG Jun;WANG Peng;LI Xiaoyan;WANG Liang;SUN Mengyu;GAO Hui(School of Electronics and Information Engineering,Xi′an Technological University,Xi′an 710021,China;Development Planning Service,Xi′an Technological University,Xi′an 710021,China;Shaanxi Academy of Aerospace Technology Application Co.,Ltd,Xi′an 710100,China)

机构地区：[1]西安工业大学电子信息工程学院,陕西西安710021 [2]西安工业大学发展规划处,陕西西安710021 [3]陕西航天技术应用研究院有限公司,陕西西安710100

出　　处：《西北工业大学学报》2022年第4期944-952,共9页Journal of Northwestern Polytechnical University

基　　金：国家自然科学基金(62171360);陕西省科技厅重点研发计划(2022GY⁃110);西安工业大学校长基金面上培育项目(XGPY200217)资助。

摘　　要：为了解决联合检测和嵌入(JDE)算法中目标遮挡以及ID信息与位置信息提取不足造成的目标ID切换问题,提出了融合多阶语义增强的JDE多目标跟踪方法。采用SPA特征空间金字塔注意力模块扩大感受野,获得更丰富的语义信息,提高模型对不同尺度目标的检测精度;通过FCN网络使检测头和ID Embedding任务协同学习以缓解两者的过度竞争并增强原始语义信息,有效减少ID切换次数;利用PCCs⁃Ma运动度量加强卡尔曼滤波的预测和观察之间的联系,提高运动特征相似度判别的可靠性。为了验证算法的有效性,设计了相同实验环境下JDE算法和所提算法的对比实验。实验结果表明,所提算法模型检测平均精度提高了3.94%。在MOT16数据集上,MOTA和IDF1指标均提高了6.9%,改进后的算法ID切换次数明显减少,取得了良好的跟踪效果。In order to solve the problem of target ID switching caused by target occlusion and insufficient ID infor⁃mation and location information extraction in JDE(joint detection and embedding)algorithm,an improved multi⁃target tracking algorithm based on JDE is proposed in this paper.Firstly,the SPA feature space pyramid attention module is used to expand the receptive field and obtain more abundant semantic information to improve the detection accuracy of the model for different scale targets.Secondly,the FCN network makes the header and ID Embedding task collaborative learning to alleviate the excessive competition and enhance the original semantic infor⁃mation,effectively reducing the number of ID switching.Finally,PCCs⁃Ma motion measurement can strengthen the connection between Kalman filtering prediction and observation,and improve the reliability of similarity discrimina⁃tion of motion characteristics.In order to verify the effectiveness of the algorithm,the JDE algorithm and the pro⁃posed algorithm are compared in the same experimental environment.The experimental results show that the average accuracy of model detection is improved by 3.94%.On the MOT16 dataset,the MOTA and IDF1 indexes are increased by 6.9%,and the number of ID switching of the improved algorithm is significantly reduced,and good tracking results are achieved.

关 键 词：多目标跟踪 JDE算法 语义信息 SPA 感受野 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]