Aiming at the problem of robot pose measurement under certain working conditions, a simple pose measurement system based on monocular vision is studied and designed, and an accurate target detection algorithm combined with monocular vision measurement method is proposed to measure robot pose. At first, the coordinates of the target in the image are extracted by image preprocessing and target detection algorithm, in which the image preprocessing includes median filtering, edge detection and image morphological expansion. And then, the calibration of the measurement model is performed, and the model parameter is solved by least square method. The established measurement model is used to convert the coordinate system, and the two-dimensional pixel coordinates of the obtained target images are converted into three-dimensional world coordinates to obtain the pose of the target in the world coordinate system. At last, the accuracy and effectiveness of the method are proved by experiments, which meet the measurement requirements.