Automatic classification of insulator by combining k-nearest neighbor algorithm with multi-type feature for the Internet of Things

New algorithms and architectures in the context of 5G shall be explored to ensure the efficiency, robustness, and consistency in variable application environments which concern different issues, such as the smart grid, water supply, gas monitoring, etc. In power line monitoring, we can get lots of images through a wide range of sensors and can ensure the safe operation of the smart grid by analyzing images. Feature extraction is critical to identify insulators in the aerial image. Existing approaches have primarily addressed this problem by using a single type of feature such as color feature, texture feature, or shape feature. However, a single type of feature usually leads to poor classification rates and missed detection in identifying insulators. Aiming to fully describe the characteristics of insulator and enhance the robustness of insulator against the complex background in aerial images, we combine three types of feature including color feature, texture feature, and shape feature towards a multi-type feature. Then, the multi-type feature is integrated with k-nearest neighbor classifier for automatic classifying insulators. Our experiment with 4500 aerial images demonstrates that the recognition rate is 99% by using this multi-type feature. Comparing to a single type of feature, our method yielded a better classification performance.