计算机工程与应用2024，Vol.60Issue(17)：233-242,10.DOI:10.3778/j.issn.1002-8331.2305-0412
多尺度特征融合的双模态目标检测方法
Multiscale Feature Fusion Approach for Dual-Modal Object Detection
摘要
Abstract
Object detection based on visible images is difficult to adapt to complex lighting conditions such as low light,no light,strong light,etc.,while object detection based on infrared images is greatly affected by background noise.Infra-red objects lack color information and have weak texture features,which pose a greater challenge.To address these prob-lems,a dual-modal object detection approach that can effectively fuse the features of visible and infrared dual-modal images is proposed.A multiscale feature attention module is proposed,which can extract the multiscale features of the input IR and RGB images separately.Meanwhile,channel attention and spatial pixel attention is introduced to focus the multiscale feature information of dual-modal images from both channel and pixel dimensions.Finally,a dual-modal feature fusion module is proposed to adaptively fuse the feature information of dual-modal images.On the large-scale dual-modal image dataset DroneVehicle,compared with the benchmark algorithm YOLOv5s using visible or infrared single-modal image detection,the proposed algorithm improves the detection accuracy by 13.42 and 2.27 percentage points,and the detec-tion speed reaches 164 frame/s,with ultra-real-time end-to-end detection capability.The proposed algorithm effectively improves the robustness and accuracy of object detection in complex scenes,which has good application prospects.关键词
目标检测/多尺度特征融合/双模态/注意力机制Key words
object detection/multiscale features fusion/dual-modal image/attention mechanism分类
信息技术与安全科学引用本文复制引用
张睿,李允臣,王家宝,陈瑶,王梓祺,李阳..多尺度特征融合的双模态目标检测方法[J].计算机工程与应用,2024,60(17):233-242,10.基金项目
江苏省自然科学基金(BK20200581). （BK20200581）
