On-site Threatening Object Recognition Method for Power Equipment Based on Statistical Learning

In order to improve the capacity of the remote early warning against the threatening status of the transmission lines,remote video monitoring is usually necessary for the overhead transmission lines in the open air.An intelligent video monitoring system can vastly save the manpower resource by automatically recognizing the threatening object and making decisions.This paper uses the statistical learning method based on Haar feature and Adaboost method to train the classifier,capable of recognizing the threatening objects such as construction trucks.The simulation results show that the proposed method has higher recognition rate and stability.