Abstract: Aiming at the problem of edge extraction and vibration detection of steel wire rope image in coal mine hoisting system, the edge extraction algorithm and vibration detection method of steel wire rope are improved. Firstly, the gray-scale image of the steel wire rope in the suspended rope section is collected by the camera, and the region of interest (ROI) is set. Then, the ROI is binarized by the Matlab image processing program, combined with Sobel algorithm and the rational use of mathematical morphology theory. Then the camera calibration is used to obtain the internal and external parameters of the camera. The world coordinate system and camera coordinate system are reasonably set. Coordinate conversion and matrix operation are carried out to directly obtain the world coordinates of the string rope. Finally, the real-time detection of the string rope vibration displacement is realized by nesting Labview and Matlab programs. The experimental verification shows that the improved method can quickly and accurately realize the edge extraction of wire rope and non-contact vibration detection of wire rope, and has better research significance and application value.