摘要
红外检测作为远程搜索和监视的重要手段,在诸多领域发挥着重要作用。为了提高复杂背景下红外小目标的检测精度,提出了一种基于RT-DETR改进YOLOv8模型的Trans-YOLO算法。首先,为了避免YOLOv8模型中非极大值抑制(NMS)错误抑制真实目标,利用RT-DETR中的Decoder&Head替换其Head部;然后,为了应对红外小目标信号弱、尺寸小等特点,设计了一个RGCSPELAN模块,使检测网络能够对输入特征进行更细粒度的处理;最后,为了缩小深浅层特征语义差距,设计了CAFMFusion(CAFM-based fusion)机制作为新的特征融合策略,促进不同特征信息在网络中流动,从而增强模型对不同尺寸目标的检测能力。实验结果表明,所提Trans-YOLO模型在两个复杂场景的公开数据集上交并比阈值为0.5时的平均精度均值分别达到了86.1%和99.5%,比原YOLOv8模型分别提高了7.7百分点和3.0百分点。此外,该模型在两个数据集上的处理速度分别达到了371.9 frame/s和369.4 frame/s,在准确性和速度之间实现了有效平衡。
Infrared detection serves as a crucial tool for remote search and surveillance,and it plays a significant role in many applications.To enhance the infrared detection accuracy of small targets in complex backgrounds,a Trans-YOLO detection framework based on an improved YOLOv8 model with RT-DETR is proposed.First,to avoid the issue of nonmaximum suppression(NMS)in YOLOv8 erroneously suppressing true targets,the Head component of YOLOv8 is replaced with the Decoder&Head from RT-DETR.Furthermore,to address the challenges of weak signal strength and small size of infrared small targets,an RGCSPELAN module is designed to enable the detection network to perform more fine-grained processing of the input features.Finally,to reduce the semantic disparity between deep and shallow features,a new feature fusion strategy,called CAFM-based fusion(CAFMFusion)mechanism,is designed to facilitate the flow of different types of feature information within the network,thereby enhancing the model’s ability to detect targets of varying sizes.Experimental results show that the proposed Trans-YOLO model achieves 86.1%and 99.5%mean average precision at IoU=0.5(intersection over union)on two public datasets with complex scenarios,representing improvements of 7.7 percentage points and 3.0 percentage points over the original YOLOv8 model,respectively.Additionally,the model achieves the processing speed of 371.9 frame/s and 369.4 frame/s on the two datasets,respectively,effectively balancing accuracy and speed.
作者
刘囝囡
刘淑娴
哈妮克孜·伊拉洪
艾斯卡尔·艾木都拉
Liu Jiannan;Liu Shuxian;Hankiz Yilahun;Askar Hamdulla(Department of Computer Science and Technology,Xinjiang University,Urumqi 830046,Xinjiang,China)
出处
《激光与光电子学进展》
北大核心
2025年第10期370-381,共12页
Laser & Optoelectronics Progress
作者简介
通信作者:艾斯卡尔·艾木都拉,askar@xju.edu.cn。
