Heading machine onboard image stabilization method based on adaptive enhancement and improved Kalman filtering

The invention belongs to the field of digital image processing, and relates to a heading machine onboard image stabilization method based on adaptive enhancement and Kalman filtering. Comprising the following steps: S1, carrying out image adaptive enhancement on a jitter video acquired by an airborne camera of the heading machine; s2, extracting video frame feature points; s3, performing optical flow tracking on the feature points extracted from each frame of image; s4, acquiring a motion track of the camera through motion estimation; s5, track smoothing is carried out on the obtained motion track; and S6, motion compensation is carried out according to the relation between the camera motion trail before and after smoothing, and a stable video is generated. Video image stabilization is realized by adopting a digital image processing technology, the system cost is low, the portability is high, and the image stabilization requirement of underground coal mine airborne equipment can be met. 本发明属于数字图像处理领域，涉及一种基于自适