In recent years, the importance of railway transport increases with the development of fast trains. Maintenance of this train should be performed at an early stage for safety and reliability. Because pantograph-catenary system is used to transmit the energy to the train in most of the electric trains, the early detection of the problems occurred in these systems are very important. In this study, an FPGA (Field Programmable Gate Arrays) based new fault detection method is proposed by using normal and thermal images. The method takes the images of pantograph-catenary system by a camera attached to the FPGA Kit and saves them to SDRAM and RAM blocks. Thresholding method is applied to image matrix read from SDRAM and occurred arcs are detected. On the other hand, the pantograph overhead bar is detected by applying sobel edge detection to the image read from RAM block. Arcs occurred in contact point is detected in real time by combining two methods. The proposed method is verified in a real experimental setup.