计算机工程与应用 ›› 2024, Vol. 60 ›› Issue (5): 183-190.DOI: 10.3778/j.issn.1002-8331.2305-0401

• 图形图像处理 • 上一篇    下一篇

基于上下文信息与特征细化的无人机小目标检测算法

彭晏飞,赵涛,陈炎康,袁晓龙   

  1. 辽宁工程技术大学 电子与信息工程学院,辽宁 葫芦岛 125105
  • 出版日期:2024-03-01 发布日期:2024-03-01

UAV Small Object Detection Algorithm Based on Context Information and Feature Refinement

PENG Yanfei, ZHAO Tao, CHEN Yankang, YUAN Xiaolong   

  1. College of Electronics and Information Engineering, Liaoning Technical University, Huludao, Liaoning 125105, China
  • Online:2024-03-01 Published:2024-03-01

摘要: 无人机航拍图像中的目标检测是近年来研究的热点,针对无人机视角下目标小而密集、背景复杂导致检测精度低的问题,提出一种基于上下文信息与特征细化的无人机小目标检测算法。通过上下文特征增强模块,利用多尺度扩张卷积捕获与周围区域像素点的潜在关系,为网络补充上下文信息,并根据不同尺度的特征层自适应生成各层级特征图的输出权重,动态优化特征图表达能力;由于不同特征图细粒度不同,使用特征细化模块来抑制特征融合中冲突信息的干扰,防止小目标特征淹没在冲突信息中;设计了一种带权重的损失函数,加快模型收敛速度,进一步提高小目标检测精度。在VisDrone2021数据集进行大量实验表明,改进后的模型较基准模型mAP50提高8.4个百分点,mAP50:95提高5.9个百分点,FPS为42,有效提高了无人机航拍图像中小目标的检测精度。

关键词: 无人机, 小目标检测, 上下文信息, 特征细化, 损失函数

Abstract: Object detection in UAV aerial images is a research hotspot in recent years, aiming at the problem of low detection accuracy caused by small and dense objects and complex background from the perspective of UAV, a UAV small object detection algorithm based on context information and feature refinement is proposed. Firstly, through the context feature enhancement module, the multi-scale dilated convolution is used to capture the potential relationship with the pixels in the surrounding area, which complements the context information of the network. According to the feature layers of different scales, the output weights of each level of feature maps are adaptively generated, and the expression ability of the feature map is dynamically optimized. Secondly, due to different fineness of different feature maps, the feature refinement module is used to suppress the interference of conflict information in feature fusion to prevent the small object features from drowning in conflict information. Finally, a weighted loss function is designed to accelerate the convergence speed of the model and further improve the accuracy of small object detection. Extensive experiments on the VisDrone2021 dataset show that the improved model improves 8.4 percentage points over the benchmark model mAP50, 5.9 percentage points over mAP50:95, and the FPS is 42, which effectively improves the detection accuracy of small objects in UAV aerial images.

Key words: unmanned aerial vehicle (UAV), small object detection, context information, feature refinement, loss function