首页|视频目标检测中位置注意力网络

视频目标检测中位置注意力网络

Position Attention Network in Video Object Detection

扫码查看
针对视频目标检测中,移动目标几何变化复杂使得边缘特征提取不足,导致边缘细节定位不准确问题,提出一种位置注意力网络(Position Attention Network,PA-Net).通过在尺寸适中的特征图上引入位置注意力网络,根据移动目标边缘与背景像素的显著差异给目标不同位置动态赋予水平和垂直方向的注意力权值,增强对目标边缘的关注程度.既捕获前景和背景之间的依赖关系,又保留目标的确切位置信息,进而加强目标边缘细节特征的提取能力,提高目标框定准确度.实验结果表明:PA-Net算法在Argoverse-HD数据集上的检测结果与基准视频目标检测网络StreamYOLO相比,平均检测精度在不同交并比下分别提高0.3%、1.6%和0.6%,在机器人和自动驾驶等领域具有一定应用前景.
Aiming at the problems that the complex geometry of moving targets makes edge fea-ture extraction insufficient and leads to inaccurate edge detail positioning,a position attention network(PA-Net)is proposed.By introducing a position attention network on a feature map of moderate size,according to the significant difference between the moving target edge and the background pixels,horizontal and vertical attention weights are dynamically assigned to different positions of the target,and the degree of attention to the target edge is enhanced.It not only captures the dependency between the foreground and the background,but also retains the exact position information of the target,thereby enhancing the ability to extract the details of the target edge and improving the accuracy of target framing.The experimental results show that compared with the benchmark video object detection network StreamYOLO,the detection results of the PA-Net algorithm on the Argoverse-HD dataset show an average improvement of 0.3%,1.6%,and 0.6%in detection accuracy under different intersection over union,respectively,which has certain application prospects in the fields of robotics and autonomous driving.

video object detectionobject locationposition attentionedge features

郭意凡、杨大伟、毛琳

展开 >

大连民族大学 机电工程学院,辽宁 大连 116650

视频目标检测 目标定位 位置注意力 边缘特征

国家自然科学基金项目辽宁省自然科学基金项目辽宁省自然科学基金项目辽宁省自然科学基金项目

6167308420170540192201805508662020-MZLH-24

2024

大连民族大学学报
大连民族学院

大连民族大学学报

CHSSCD
影响因子:0.266
ISSN:1009-315X
年,卷(期):2024.26(1)
  • 14