Wang Ping, Li Chuanxue, Yang Qiang, Fu Lin, Yu Fan, Min Lixiao, Guo Dequan, Li Xinming
School of Network & Communication Engineering, Chengdu Technological University, Chengdu 610031, China.
School of Automation, Chengdu University of Information Technology, Chengdu 610225, China.
J Imaging. 2022 Sep 21;8(10):257. doi: 10.3390/jimaging8100257.
Compared with traditional manual inspection, inspection robots can not only meet the all-weather, real-time, and accurate inspection needs of substation inspection, they also reduce the work intensity of operation and maintenance personnel and decrease the probability of safety accidents. For the urgent demand of substation inspection robot intelligence enhancement, an environment understanding algorithm is proposed in this paper, which is an improved DeepLab V3+ neural network. The improved neural network replaces the original dilate rate combination in the ASPP (atrous spatial pyramid pooling) module with a new dilate rate combination with better segmentation accuracy of object edges and adds a CBAM (convolutional block attention module) in the two up-samplings, respectively. In order to be transplanted to the embedded platform with limited computing resources, the improved neural network is compressed. Multiple sets of comparative experiments on the standard dataset PASCAL VOC 2012 and the substation dataset have been made. Experimental results show that, compared with the DeepLab V3+, the improved DeepLab V3+ has a mean intersection-over-union (mIoU) of eight categories of 57.65% on the substation dataset, with an improvement of 6.39%, and the model size of 13.9 M, with a decrease of 147.1 M.
与传统人工巡检相比，巡检机器人不仅能够满足变电站巡检全天候、实时、准确的巡检需求，还能降低运维人员的工作强度，减少安全事故发生概率。针对变电站巡检机器人智能化增强的迫切需求，本文提出一种环境理解算法，即改进的DeepLab V3+神经网络。改进后的神经网络将空洞空间金字塔池化（ASPP）模块中原来的扩张率组合替换为具有更好目标边缘分割精度的新扩张率组合，并在两次上采样中分别添加了卷积块注意力模块（CBAM）。为了移植到计算资源有限的嵌入式平台，对改进后的神经网络进行了压缩。在标准数据集PASCAL VOC 2012和变电站数据集上进行了多组对比实验。实验结果表明，与DeepLab V3+相比，改进后的DeepLab V3+在变电站数据集上八类的平均交并比（mIoU）为57.65%，提高了6.39%，模型大小为13.9M，减少了147.1M。
