High-Temperature Zone Localization Image Processing Algorithm for Pantograph Infrared Image

The infrared temperature of the pantograph is one of the important technical parameters in the train operation and it is important to monitor the infrared of the train in time to ensure the safety of the train. This paper proposes a high-temperature region localization image processing algorithm for pantograph infrared image. Smoothing the image Gaussian filtering should be performing on the image data collected in the field at first; After performing grayscale processing on the filtered image, image morphology is enhanced according to image pixel grayscale differences; The k-means algorithm is used to cluster the regions with higher temperatures to locate the target detection regions. Compared with manual observation, the system detection consistency is better than manual observation, and the calculation formula can meet the requirements of measurement accuracy and real time. Comparing with the effect photos in different values, the best parameters are obtained, which can help for further research.