Binocular vision three-dimensional morphology measurement method based on time and space constraints

The invention provides a binocular vision three-dimensional morphology measurement method based on time and space constraints, which belongs to the technical field of computer vision measurement. The binocular vision three-dimensional morphology measurement method based on time and space constraints is for the surface morphology of a large composite structure component, and uses a laser scanning binocular vision measurement system to carry out image acquisition and image processing. Edge information is extracted. The constraints are established. Time dimension information is combined to predict the position of a light strip. An appropriate interested extraction area is established. Laser light strip centers corresponding to left and right light stripe images are fast and accurately extracted. The light stripe center information in a boundary constraint is retained. The light stripe center information beyond the constraint is removed. The retained light strip center information and boundary information are matched and reconstructed. Ultimately, complete three-dimensional morphology information is restored. The method provided by the invention has the advantages of improved measurement efficiency, high measurement accuracy, complete detection information and fast operation speed, and can realize the three-dimensional morphology measurement of the surface of a large part.