基于AC-YOLO的路面落叶检测方法

Detection method of fallen leaves on road based on AC-YOLO

随着城市绿化程度的不断提高,落叶清理任务变得更加复杂繁重.针对落叶形状多变、大小不一、背景复杂、分布不均的特点,提出一种融合Attention-Context(AC)网络和YOLOv3的落叶检测算法(AC-YOLO),解决现有模型对落叶漏检、误检的问题,实现快速、准确地识别检测路面落叶.针对小目标落叶易发生漏检的问题,提出AC网络结构,将不同层次的特征映射融合作为小目标的上下文信息,同时引入自注意力机制来抑制复杂背景和底层噪声带来的影响,提升小目标落叶检测能力;其次,采用Mish激活函数替换Leaky ReLU以提升模型的泛化能力,提高落叶检测准确度;最后,考虑到落叶堆叠情况对清理机器人的工作效率有影响,提出非极大值融合算法(non-maximum fusion,NMF)来融合密集落叶预测框,从而通过更少的导航点解决密集落叶的检测问题,同时提升落叶检测清理的效率.实验结果表明,基于AC-YOLO的检测算法对落叶检测的覆盖率(cover)达到95%,检测速度达到53帧/s,可以完成实际应用环境中的落叶检测任务,实现对落叶的高效率、智能化清理.

With the continuous improvement of urban greening,it is more complex and heavy to clean the fallen leaves.According to the characteristics of variable shape,complex background and uneven distribution of fallen leaves,we propose a fallen leaf detection algorithm,which integrates an attention context(AC)network and YOLOv3,named AC-YOLO,to detect fallen leaves on the road quickly and accurately.To solve the problem that small leaves are difficult to detect,we propose the AC network.We use different feature levels as the context information of small leaves and attention mechanism to suppress the influence of complex background and bottom noise,so as to improve the ability of small leaves detection.In addition,we use the Mish activation function to replace Leaky ReLU to enhance the generalization ability of the model and improve the accuracy of leaf detection.Finally,considering that the stacking of fallen leaves has an impact on the work efficiency of the cleaning robot,we propose the non-maximum fusion to fuse the dense fallen leaves detection boxes,which promotes the detection of dense fallen leaves and improves the work efficiency by reducing goal nodes.Experiment results show that the cover of leaf detection based on the AC-YOLO algorithm is 95%and the detection speed is 53 frames per second,which can complete the leaf detection task in the practical application and realize the efficient and intelligent leaves cleaning.