###
计算机系统应用英文版:2024,33(11):111-120
←前一篇   |   后一篇→
本文二维码信息
码上扫一扫!
基于注意力与量化感知的航拍红外目标检测
(1.南京信息工程大学 电子与信息工程学院, 南京 210044;2.无锡学院 电子信息工程学院, 无锡 214105)
Aerial Infrared Target Detection Based on Attention and Quantization Awareness
(1.School of Electronics and Information Engineering, Nanjing University of Information Science & Technology, Nanjing 210044, China;2.School of Electronic and Information Engineering, Wuxi University, Wuxi 214105, China)
摘要
图/表
参考文献
相似文献
本文已被:浏览 13次   下载 448
Received:April 28, 2024    Revised:June 28, 2024
中文摘要: 针对航拍场景下红外目标对比度低、识别精度差、检测难度大等问题, 提出一种基于注意力与量化感知的航拍红外目标检测算法. 首先, 利用DCNv2替代ELAN模块中的3×3卷积, 构建了DC-ELAN模块, 有效提升了模型捕捉局部和全局特征的能力, 进而强化了网络的特征表达能力; 其次, 通过巧妙地将SE注意力机制融入SPPCSPC模块和ELAN模块中, 设计出了SE-SPPCSPC模块和SE-ELAN模块, 有助于增强特征图的空间自注意力, 模型能够更好地关注目标区域; 此外, 引入QARepVGG模块, 提升模型的量化感知能力并增强其对量化误差的鲁棒性; 最后, 引入DyHead模块, 该模块可以根据输入图像的不同动态调整检测头, 提高模型对不同大小、形状目标的检测能力, 从而进一步提高红外目标检测的准确性和鲁棒性. 实验结果表明, 相较于原模型, 改进后的YOLOv7-tiny模型在计算量未增长的情况下, mAP@0.5值提升了3.4%, mAP@0.5:0.95值提升了4.8%, 显著提高了模型检测精度.
Abstract:Aiming at the problems of low contrast, poor recognition accuracy, and difficult detection of infrared targets in aerial scenes, this study proposes an aerial infrared target detection algorithm based on attention and quantization awareness. Firstly, the DC-ELAN module is constructed by using DCNv2 to replace the 3×3 convolution in the ELAN module, which effectively improves the ability of the model to capture local and global features, and then strengthens the feature representation ability of the network. Secondly, by cleverly integrating the SE attention mechanism into the SPPCSPC module and the ELAN module, the SE-SPPCSPC module and the SE-ELAN module are designed, which helps to enhance the spatial self-attention of the feature map, and the model can better focus on target areas. In addition, the QARepVGG module is introduced to improve the quantization awareness of the model and enhance its robustness to quantization errors. Finally, the DyHead module is introduced, which can dynamically adjust the detection head according to different input images, improve the detection ability of the model to targets of different sizes and shapes, and further improve the accuracy and robustness of infrared target detection. Experimental results show that compared with the original model, the improved YOLOv7-tiny model has 3.4% and 4.8% increases in mAP@0.5 and mAP@0.5:0.95 values without increasing the amount of calculation, which significantly improves model detection accuracy.
文章编号:     中图分类号:    文献标志码:
基金项目:国家自然科学基金青年项目(42205078); 苏高教会“高质量公共课教学改革研究”专项课题(2022JDKT138); 高校哲学社会科学研究一般项目(2022SJYB0979); 江苏职业教育研究立项课题一般项目(XHYBLX2023282); 无锡学院教改课题(XYJG2023002, XYJG2023023); 2023江苏省大学生创新创业训练计划(202313982007Z)
引用文本:
周进,裴晓芳.基于注意力与量化感知的航拍红外目标检测.计算机系统应用,2024,33(11):111-120
ZHOU Jin,PEI Xiao-Fang.Aerial Infrared Target Detection Based on Attention and Quantization Awareness.COMPUTER SYSTEMS APPLICATIONS,2024,33(11):111-120