Image segmentation method and device for moving target under mine and monitoring system

The invention provides an image segmentation method and device for a moving target in a mine and a monitoring system, and the method comprises the steps: obtaining a mine video image which is a video image of each construction part monitored by a monitoring device in an underground mining process; and carrying out image segmentation on the video image by adopting an improved FCM algorithm to obtain a plurality of sub-images, the improved FCM algorithm being an improved algorithm which takes a prior probability of Markov as a constraint term and adds the prior probability to a target function in a standard FCM algorithm. According to the method, the prior probability based on the Markov random process serves as a constraint item to be added into a target function of the FCM algorithm, so that the improved FCM algorithm comprises the distance from a pixel point to a clustering center in a standard FCM algorithm and also comprises neighborhood information of the pixel, noise points and interference points in an