基于改进DeepLabv3+的光伏电站道路识别方法  

Road Recognition Method of Photovoltaic Plant Based on Improved DeepLabv3+

作　　者：李翠明[1] 王华[1] 徐龙儿 王龙 LI Cuiming;WANG Hua;XU Longer;WANG Long(School of Mechanical and Electrical Engineering,Lanzhou University of Technology,Lanzhou 730050,China)

机构地区：[1]兰州理工大学机电工程学院,兰州730050

出　　处：《上海交通大学学报》2024年第5期776-782,I0010,共8页Journal of Shanghai Jiaotong University

基　　金：甘肃省自然科学基金(18JR3RA139);国家自然科学基金(51765031)资助项目。

摘　　要：针对移动清洁机器人在光伏电站作业时需要精确快速识别道路的问题,提出一种改进的DeepLabv3+目标识别模型对光伏电站道路进行识别.首先,将原DeepLabv3+模型的主干网络替换为优化的MobileNetv2网络以降低模型复杂度;其次,采用异感受野融合和空洞深度可分离卷积结合的策略改进空洞空间金字塔池化(ASPP)结构,提高ASPP的信息利用率和模型训练效率;最后,引入注意力机制,提升模型识别精度.结果表明,改进后模型的平均像素准确率为98.06%,平均交并比为95.92%,相比于DeepLabv3+基础模型分别提高了1.79个百分点、2.44个百分点,且高于SegNet、UNet模型.同时,改进后的模型参数量小,实时性好,能够更好地实现光伏电站移动清洁机器人的道路识别.Aiming at the problem that mobile cleaning robot needs to identify road accurately and quickly when it operates in photovoltaic plants,a target recognition model of improved DeepLabv3+to identify the roads within photovoltaic plants is proposed.First,the backbone network of the original DeepLabv3+model is replaced with an optimized MobileNetv2 network to reduce complexity.Then,the strategy that combines diverse receptive field fusion with depth separable convolution is employed,which enhances the atrous spatial pyramid pooling(ASPP)structure and improves the information utilization of ASPP and the training efficiency of model.Finally,the attention mechanism is introduced to improve the segmentation accuracy of the model.The results show that the average pixel accuracy of the improved model is 98.06%,and the average intersection over union is 95.92%,which are 1.79 percentage points and 2.44 percentage points higher than those of the DeepLabv3+basic model,and SegNet and UNet models.Furthermore,the improved model has fewer parameters and a good real-time performance,which can better realize the road recognition of mobile cleaning robot of photovoltaic plants.

关 键 词：光伏电站 道路识别 DeepLabv3+模型 注意力机制 MobileNetv2 

分 类 号：TP242.6[自动化与计算机技术—检测技术与自动化装置]