基于分组特征提取的轻量型多源目标检测  

Lightweight Multisource Object Detection Based on Group Feature Extraction

作　　者：万军 周凯 何文磊 WAN Jun;ZHOU Kai;HE Wenlei(Sanmenxia College of Social Administration,Sanmengxia 472000,China;Electronic Information College,Xi'an Polytechnic University,Xi'an 710048,China;Chengdu Institute of Computer Application,Chinese Academy of Sciences,Chengdu 610041,China)

机构地区：[1]三门峡社会管理职业学院,河南三门峡472000 [2]西安工程大学电子信息学院,陕西西安710048 [3]中国科学院成都计算机应用研究所,四川成都610041

出　　处：《红外技术》2025年第3期307-315,共9页Infrared Technology

基　　金：国家自然科学基金(62072362)。

摘　　要：为兼顾多源目标检测网络的精度与效率,将分组卷积作用于目标多模态特征中,并配合注意力多尺度结构以及改进的目标框筛选策略,设计了一种轻量级的红外与可见光目标检测模型。模型先以多种特征降维策略对输入图像进行采样,降低噪声及冗余信息的影响;其次,根据特征通道所属模态进行分组,并利用深度可分离卷积分别对红外特征、可见光特征以及融合特征进行提取,提升多源特征提取结构的多样性以及高效性;然后,针对各维度多模态特征,引入改进的注意力机制来增强关键特征,再结合邻域多尺度融合结构保障网络的尺度不变性;最后,利用优化后的非极大值抑制算法来综合各尺度目标预测结果,精确检测出各个目标。通过在KAIST、FLIR、RGBT公开数据集上的测试结果表明,所提模型有效提升了目标检测性能,并且相对于同类型多源目标检测方法,该模型也体现出较高的鲁棒性和泛化性,可以更好地实现目标检测。To balance the accuracy and efficiency of multisource object detection networks,a lightweight infrared and visible light object detection model with a multiscale attention structure and an improved object-box filtering strategy was designed by applying group convolution to multimodal object features.First,multiple feature dimensionality reduction strategies were adopted to sample the input image and reduce the impact of noise and redundant information.Subsequently,feature grouping was performed based on the mode of the feature channel,and deep separable convolution was used to extract infrared,visible,and fused features,to enhance the diversity and efficiency of extracted multisource feature structures.Then,an improved attention mechanism was utilized to enhance key multimodal features in various dimensions,combining them with a neighborhood multiscale fusion structure to ensure scale invariance of the network.Finally,the optimized non-maximum suppression algorithm was used to synthesize the prediction results of objects at various scales for accurate detection of each object.Experimental results based on the KAIST,FLIR,and RGBT public thermal datasets show that the proposed model effectively improves object detection performance compared with the same type of multisource object detection methods.

关 键 词：多源目标检测 分组特征提取 注意力多尺度 非极大值抑制 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]