Abstract: In coal mine, the dust concentration is high and the illumination is low. The image acquisition quality and characteristic extraction effect are greatly affected by dust concentration. However, the camera parameters and image processing parameters cannot be adjusted adaptively according to the change of dust concentration. Therefore, it is easy to cause problems such as unstable point-line characteristic extraction and image frame loss. In order to solve the above problems, the position and posture measurement system for boom-type roadheader based on machine vision is improved. The mine-used explosion-proof industrial camera is used to collect the laser point-line images under different dust concentrations. The relationship model between the image gray value and the dust concentration level is established through the transmittance. The optimal camera parameters and image processing parameters under different dust concentration levels are obtained through experiments. A parameter adaptive adjustment algorithm is proposed, and the parameter values are adjusted adaptively according to the dust concentration levels. Therefore, the image collection quality and the stability and precision of the point-line characteristic extraction are improved. Moreover, the precision of position and posture measurement system for roadheader based on machine vision is improved. The experimental result show that the average measurement errors in X, Y and Z directions of the improved vision detection system for boom-type roadheader are 28.26 mm, 30.58 mm and 22.54 mm respectively. The number of usable images is increased from 75 to 90 after processing 100 images. These results show that the parameter adaptive adjustment algorithm can effectively improve the precision of image characteristic extraction and the data availability. The algorithm ensures the precision and stability of position and posture measurement system for boom-type roadheader based on machine vision.