Object recognition and localization based on kinect camera in complex environment

Kinect camera is a new developed cheap senor, which captures color images along with per-pixel depth information. In this paper, a new object localization method, based on RGB-D image, is presented. On the basis of traditional image segmentation, the system determines the motion tracing object according to current environment. Then by using Back projection algorithm, the system implements the object segmentation of color image from kinect camera. After that, the system extracts the foreground by depth information of Kinect image. In the segment region, by analyzing the depth image, this paper presents a ball recognition algorithm based on component depth gradient. An extensive experiment with implementation of the proposed method demonstrates that every international standard basketball can be recognized and localized rapidly and effectively.