Research On Power Vision Terminal Target Detection System Based On Deep Learning

External damage to power facilities caused by crane,excavator and other construction operations increases year by year,which will seriously threaten the safe operation of power system.It is an important measure to ensure the safe and reliable operation of power system to implement intelligent monitoring and early warning of power external breakdown through video and other non-contact observation means.The video data of power mainly comes from the fixed monitoring of helicopters,uavs and transformation poles and towers,which is characterized by large amount of data,complex scenes and serious environmental interference.The traditional target detection method usually selects the candidate area first,and then makes judgment based on the characteristics of human construction.The detection speed is slow and the accuracy is low,which makes it impossible to monitor the video data in real time,so as to make timely and accurate early warning and intervention for external damage.The target detection method based on deep learning optimizes or even eliminates the selection of candidate regions,which greatly speeds up the detection speed.By learning a lot of target samples through the deep neural network,the characteristics of high robustness are gradually fitted to make the target judgment more accurate.There are three key problems in introducing the target detection method based on deep learning into the power video detection:Firstly,the target detection method based on deep learning has a large amount of calculation and many parameters.In order to realize in-place operation on terminals with limited computing and storage capacity,it is necessary to find a practical method to simplify the network and reduce the amount of operational data in the detection process,which is the key to realize in-place operation and terminal operation of deep neural network.Secondly,for specific application scenarios,the effect of different target detection algorithms varies greatly,and there is a strong particularity of power video.Finding an effective target detection method is the key to improve the detection speed and accuracy.Finally,with the continuous development of deep learning,the structure of deep neural network changes with each passing day,and each has its own characteristics,which network structure is used as the feature extraction layer of target detection algorithm is the focus of research.This paper introduces a power vision terminal target detection system based on deep learning.And the target detection method based on deep learning is applied to the power video target detection.Firstly,the detection results of different detection methods were compared,and then the influence of feature extraction with different depth neural networks on the detection results in the power application scenarios was explored.Finally,neural network compression algorithm based on compression,quantization and Huffman coding is adopted to compress the network,and the compressed network is transplanted to the power vision terminal.The experiment selected three typical target detection algorithms such as DPM,SSD(Single Shot MultiBox Detector)and r-cnn for comparison.The influence of setting different superparameters on the detection results in the training process was investigated.Three typical network structures,ZFNet,VGGNet and ResNet,are selected as the feature extraction layer of SSD algorithm.From the aspects of training process,detection performance and generalization ability,the performance of different network structures in detection of external break-proof targets of power is compared.The results show that the SSD target detection method based on deep learning has high detection accuracy and good real-time performance,and it can meet the requirements of detection of external break-proof targets in power facilities.SSD algorithm with VGGNet as the feature extraction layer has better detection effect and is more suitable for external power detection scenarios.The compressed quantized network can be correctly operated in the power visual terminals,and it can still maintain high detection accuracy under the condition of small precision loss and successfully complete the power video target detection task.