The wire rope is widely used in mechanical and electrical special equipment, such as rope way, elevator, and hoisting machinery. Wire rope usually bear alternating loads during operation. Wire breakage, corrosion, and other defects may occur during long-term operation, which may cause serious accidents of machine damage and human death. The traditional method for detecting burrs on wire ropes is manual visual inspection, which has the problems of missed detection, false detection and so on. Therefore, a no-contact detection method of wire rope burrs based on vision is proposed. Firstly, the clear local continuous frame image of the wire rope is collected, and the region of interest (ROI) of the wire rope in the continuous frame image is subjected to morphological processing and adaptive enhancement to highlight the image of the wire rope in the image. Then, subpixel edge detection is performed on the images within the ROI to distinguish the target area and background area of the wire rope. Finally, the length and quantity of burrs on the wire rope in the ROI background area are detected. This method helps to overcome the difficulties of on-site detection and missed detection in traditional detection methods, reduces the impact of the technical level of operators on the detection results, shortens detection time, and improves efficiency.