A Feature Points Matching Method Based on Window Unique Property of Pseudo-Random Coded Image

Proposed a method for object feature points matching used in active machine vision technique. By projecting pseudo-random coded structured light onto the object to add code information, its feature points can be easily identified exclusively taking advantage of the window unique property of pseudo-random array. Then, the 3D coordinates of object both on camera plane and code plane can be obtained by decoding process, which will provide the foundation for further 3D reconstruction. Result of simulation shows that this method is easy to operate, calculation simple and of high matching precision for object feature points matching.