融合注意力机制的Cascade R-CNN田间害虫检测方法

Field pest detection method based on improved Cascade R-CNN by incorporating attention mechanism

为解决测报灯采集图像中害虫依赖人工识别及统计结果可靠性低和准确性差的问题,本研究提出一种改进型Cascade R-CNN田间害虫检测算法。该算法以Cascade R-CNN为基础框架,采用ResNeSt-50作为主干网络,融合了跨通道注意力机制;使用统一目标检测头(unifying object detection heads with attentions,DyHead),并融合尺度感知、空间位置感知和任务感知。此外,采用简单复制-粘贴(simple copy-paste,SCP)方法进行了数据增强。研究共采集到20类害虫总计1 500张图像,制作了符合MS COCO格式(microsoft common objects in context 2017,MS COCO 2017)的测报灯田间害虫数据集。结果显示,本研究提出的方法的F1分数(F1-score)达到了86.2%。当交并比(intersection over union,IoU)为0.5时,其F1-分数与经典Cascade R-CNN、Faster R-CNN和YOLOv4相比,分别提升了2.8、5.8和8.2个百分点。表明该方法满足测报灯害虫检测任务对判别能力和实时性的要求,实现了害虫的高精度自动识别与计数,可直接应用于田间害虫检测。

In order to address the challenges of manual identification of pests in images collected by light traps,as well as the low reliability and poor accuracy of statistical results,this study proposes an improved Cascade R-CNN algorithm for field pest detection.The algorithm is based on the Cascade R-CNN framework and uses ResNeSt-50 as the backbone network,incorporating cross-channel attention mechanisms to obtain feature maps more conducive to pest detection.A unifying object detection head with attentions(DyHead) is used,incorporating scale awareness,spatial position awareness,and task awareness to improve the performance of the detection head.Additionally,the simple copy-paste(SCP) method is employed for data augmentation to enhance the model's detection capabilities in complex scenarios.A total of 1 500 images of 20 pest categories were collected,and a monitoring lamp field pest dataset compliant with the microsoft common objects in context(MS COCO 2017) format was created.The results show that the F1-score of the proposed method reaches 86.2%.When the intersection over union(IoU) is set to 0.5,the F1-score increases by 2.8,5.8,and 8.2 percentages compared to the classic Cascade R-CNN,Faster RCNN,and YOLOv4,respectively.The results shows that the proposed method meets the requirements of discriminative ability and real-time performance for monitoring lamp pest detection tasks,achieving highprecision automatic identification and counting of pests,and can be directly applied to field pest detection.