混合采样下多级特征聚合的视频目标检测算法

Video object detection algorithm based on multi-level feature aggregation under mixed sampler

针对现有基于深度学习的视频目标检测算法无法同时满足精度和效率要求的问题,在单阶段检测器YOLOX-S的基础上,提出基于混合加权采样和多级特征聚合注意力的视频目标检测算法.混合加权参考帧采样(MWRS)策略采用加权随机采样操作和局部连续采样操作,充分利用有效的全局信息与帧间局部信息.多级特征聚合注意力模块(MFAA)基于自注意力机制,对YOLOX-S提取的分类特征进行细化,使得网络从不同层次的特征中学到更加丰富的特征信息.实验结果表明,所提算法在ImageNet VID数据集上的检测精度均值AP50达到77.8%,平均检测速度为11.5 ms/帧,在检测图片上的目标分类和定位效果明显优于YOLOX-S,表明所提算法达到了较高的精度,具有较快的检测速度.

A video object detection algorithm which was built upon the YOLOX-S single-stage detector based on mixed weighted reference-frame sampler and multi-level feature aggregation attention was proposed aiming at the problems of existing deep learning-based video object detection algorithms failing to simultaneously meet accuracy and efficiency requirements.Mixed weighted reference-frame sampler(MWRS)included weighted random sampling and local consecutive sampling to fully utilize effective global information and inter-frame local information.Multilevel feature aggregation attention(MFAA)module refined the classification features extracted by YOLOX-S based on self-attention mechanism,encouraging the network to learn richer feature information from multi-level features.The experimental results demonstrated that the proposed algorithm achieved an average precision AP50 of 77.8%on the ImageNet VID dataset with an average detection speed of 11.5 milliseconds per frame.The object classification and location performance are significantly better than that of YOLOX-S,indicating that the proposed algorithm achieves higher accuracy and faster detection speed.