Steel is a widely used material in industry and construction. The tensile and compressive strengths of steel are relatively high compared to other materials. On the other hand, low corrosion resistance is the main weakness of steel, which can encourage steel deterioration and fatal accidents for the user. Furthermore, regular visual inspection by a human should be performed to prevent catastrophic incidents. However, human visual inspection increases the risk of work accidents and reduces work effectiveness. Therefore, a drone with a camera is one solution to increase efficiency, increase security levels, and minimize difficulties or risks during corrosion detection. In this research, the drone was used to capture corroded video of a construction structure. The convolutional neural network (CNN) method was used to detect the location of the corroded images. This study was conducted on Surabaya's Petekan bridge using the Mobilenet V1 SSD pre-training model. In this study, the distance between a drone and the detected object varied between 1 and 2 m. Next, the drone speed was varied into 0.6 m/s, 0.9 m/s, and 1.3 m/s. As a result, CNN could detect corrosion on the surface of steel materials. The best accuracy was 84.66% with a minimum total loss value of 1.673 by applying 200 images, 200000 epochs, batch size at 4, learning rate at 0.