Method for fusing a color depth image and a gray scale depth image

Abstract

The invention discloses a method for fusing a color depth image and a gray scale depth image. The method comprises the following steps: calibrating internal and external parameters of a depth sensor and an RGB sensor of three-dimensional depth sensing equipment; a gray-scale depth image is acquired through a depth sensor, a corresponding YUV depth image is generated, and meanwhile, an RGB color image is acquired through an RGB sensor; converting the YUV depth image into an RGB depth image, compressing and encoding the RGB depth image and the RGB color image, and outputting the RGB depth image;decompressing the RGB depth image subjected to compressed encoding and the RGB color image, converting the decompressed RGB depth image into a YUV depth image, and recovering the depth value of eachpixel in the gray scale depth image mapped to the YU or YV channel; carrying out registration on the YUV depth image and the RGB color image; and fusing the depth value of each pixel in the restored gray scale depth image and the texture information of the registered RGB color image to generate a color and gray scale fused depth image.

Description

technical field [0001] The disclosure belongs to the technical fields of image processing, computer vision and human-computer interaction, and in particular relates to a method for fusing color and grayscale depth images. Background technique [0002] Vision is the most direct and main way for human beings to observe and perceive the world. We live in a three-dimensional world. Human vision can not only perceive the brightness, color, texture information, and movement of an object's surface, but also judge its shape, space, and spatial position (depth, distance). The real-time acquisition of in-depth information is conducive to the interaction between the real physical world and the virtual network world, strengthens communication and learning between people, people and machines, and machines and machines, and enhances the intelligence level of machines. [0003] The high-precision depth information (distance) in the projected space can be obtained in real time through the ...

AI Technical Summary

Problems solved by technology

The human eye's ability to distinguish color information is much greater than that of grayscale information. The grayscale depth image is a monochrome image, and the scene information provided by it and the pseudo-color depth image is limited, and it is difficult to fully reflect the depth information of the physical space.

The color image conforms to the observation mode of the human eye, but the color image does not contain the depth information of the physical space

Images