基于计算机视觉的电信运营商智能巡检机器人技术研究

本文构建了面向电信运营商机房配电设备的智能巡检机器人及视觉检测系统，具有环境感知、行为控制、导航规划与动态决策等功能，通过传感器感知环境信息和自身的速度、位置、姿态等信息，处理感知信息并作出正确的决策和行为控制。设计和实施了一种基于RPN+SVM级联网络的运营商机房配电设备异常检测方法，对深度学习模型Faster-RCNN进行改进，在RPN网络后级联二分类网络SVM来识别消除背景区域的干扰，引入Faster-RCNN、SSD算法进行比较，证明了本方法在检测精度、检测速率和训练时长方面效果更优。

Research on Intelligent Inspection Robot based on Computer Vision Technology in Telecommunication operators

The intelligent inspection robot with environmental sensing and autonomous navigation is a special robot, which is mostly used for equipment defect detection in industrial areas such as the power distribution room. An intelligent patrol car system for abnormal detection of distribution equipment is constructed in this paper, which has the functions of environment perception, behavior control, navigation planning and dynamic decision-making. Through the perception of environmental information and its own speed, position, posture and other information by sensors, the patrol car processes the sensing information and makes correct decision and behavior control. A defect?detection method on power distribution equipment based on an improved cascaded network is presented, which fully embodies the advantages of deep-learning on feature extraction, region proposal, small object recognition. Faster-RCNN is improved by adding support vector machine after Region Proposal Network to improve classification accuracy on the foreground and background images. Only the foreground features including target are sent to the subsequent network for training to make?this?method?take good balance between accuracy and training efficiency. Faster-RCNN, SSD algorithms are introduced for comparison, it is proved that the detection accuracy, detection rate and training time of this method are better in the identification for copper bar in power distribution room.