摘要 |
Disclosed are an image processing method and device. The method comprises: collecting a video image and a depth image of an object; segmenting, by using the depth image, a video image frame corresponding to the video image captured at the same time with the depth image, to obtain an outline of a foreground image in the video image frame; performing first-time encoding on video image pixel points within the outline of the foreground image in the video image frame according to the outline of the foreground image, and performing second-time encoding on video image pixel points outside the outline in the video image frame, to obtain encoding data corresponding to the video image frame, the encoding rate of the first-time encoding being higher than that of the second-time encoding; and outputting the encoding data corresponding to the video image frame and depth data corresponding to the outline of the foreground image. The embodiments of the present invention can reduce network bandwidth usage in a video image transmission process. |