首页|基于可变形卷积和注意力机制的视频目标检测算法

基于可变形卷积和注意力机制的视频目标检测算法

扫码查看
视频帧中目标模糊、遮挡和形变是影响视频目标检测精度的重要原因,针对此类问题,提出一种DG-YOLOv8n算法.首先,基于可变形卷积对骨干网络中的C2f模块进行了重新设计,以增强骨干网络对于目标变化的处理能力;其次,在颈部网络引入GAM全局注意机制,放大全局交互表示来提高算法的性能;最后,在ImageNet VID数据集上的实验结果表明,改进的DG-YOLOv8n算法的平均精度为84.5%,较原YOLOv8n算法提高了6.1个百分点,验证了改进算法的有效性.
Video object detection algorithm based on deformable convolution and attention mechanism
The blurring,occlusion,and deformation of targets in video frames are important factors affecting the accuracy of video object detection.To address these issues,a DG-YOLOv8n algorithm is proposed.Firstly,the C2f module in the backbone net-work was redesigned based on deformable convolution to enhance its ability to handle target changes.Secondly,the GAM global at-tention mechanism is introduced into the neck network to amplify the global interactive representation and improve the performance of the algorithm.Finally,the experimental results on the ImageNet VID dataset showed that the improved DG-YOLOv8n algorithm had an average precision of 84.5%,which was 6.1 percentage point higher than the original YOLOv8n algorithm,verifying the effec-tiveness of the improved algorithm.

object detectionvideo object detectiondeformable convolutionglobal attention mechanismfeature aggregationYOLOv8

魏一帆、郭本华、粟长权、钱淑渠

展开 >

贵州财经大学信息学院,贵阳 550025

安顺学院数学与计算机科学学院,安顺 561000

目标检测 视频目标检测 可变形卷积 GAM全局注意机制 YOLOv8

2024

现代计算机
中大控股

现代计算机

影响因子:0.292
ISSN:1007-1423
年,卷(期):2024.30(21)