摘要
目标检测算法在视频监控领域有着较大的实用价值。针对当前在资源受限的视频监控系统中实现实时目标检测较为困难的情况,提出了一种基于YOLOv3-tiny改进的目标检测算法。该算法在YOLOv3-tiny架构的基础之上,通过添加特征重用来优化骨干网络结构,并提出全连接注意力混合模块来学习到更丰富的空间信息,更适合资源约束条件下的目标检测。实验数据表明,该算法相比于YOLOv3-tiny在模型体积降低39.2%,参数量降低39.8%,且在VOC数据集上提高了2.7%的mAP,在提高检测精度的同时显著降低了模型资源占用。
Object detection methods have great value in the application field of video surveillance.At present,it is difficult to realize real-time object detection in resource constrained video surveillance system.A object detection method based on improved YOLOv3-tiny is proposed.Based on the YOLOv3-tiny architecture,the algorithm optimizes the backbone network by adding feature reuse,and a fully-connected attention mix module is proposed to enable the network to learn more abundant spatial information,which is more suitable for object detection under resource constraints.The experimental data shows that compared with YOLOv3-tiny,the algorithm reduces the model volume by 39.2%,the amount of parameters by 39.8%,and improves the mAP of 2.7%on the VOC data set,which significantly reduces the occupation of model resources while improving the detection accuracy.
作者
王均成
贺超
赵志源
邹建纹
Wang Juncheng;He Chao;Zhao Zhiyuan;Zou Jianwen(School of Communication and Information Engineering,Chongqing University of Posts and Telecommunications,Chongqing 400065,China;Advanced Network and Intelligent Connection Technology Key Laboratory of Chongqing Education Commission of China,Chongqing 400065,China;Chongqing Key Laboratory of Ubiquitous Sensing and Networking,Chongqing 400065,China)
出处
《电子技术应用》
2022年第7期30-33,39,共5页
Application of Electronic Technique
