Object volume calculating method based on Kinect

Abstract

The invention discloses an object volume calculating method based on Kinect. The method comprises the steps of (1), acquiring a depth image and a color image by means of Kinect; (2), calibrating a color camera of the Kinect; (3), setting an ROI area of the depth image, performing image segmentation by means of a foreground color image which comprises a measured object and a background color image of a measurement platform that does not comprise the measured object, and obtaining a binary image of the measured object; (4), converting a background depth image ROI area to a background distance matrix, and performing preprocessing on the background distance matrix, filling in elements which are zero on the background distance matrix, and converting the foreground depth image ROI area to a foreground distance matrix; (5), obtaining a height matrix according to difference between the foreground distance matrix and the background distance matrix; and (6), calculating length, width, height and volume of the object. The object volume calculating method effectively settles problems of high labor intensity and long measurement time in traditional manual measurement, and is a noncontact measurement means. Damage of the measurement object is prevented. A requirement for automatic is satisfied and furthermore measurement precision is improved.

Description

technical field [0001] The invention relates to a Kinect-based object volume calculation method, which belongs to the field of computer vision. Background technique [0002] With the development of digital signal processing and computer technology, the new technology formed by converting the external environment image acquired by the camera into a digital signal, and using the computer to realize the whole process of visual information processing is called computer vision. Apply computer vision to precise measurement and positioning of spatial geometric dimensions, resulting in visual measurement technology. As one of today's high-tech, visual measurement has developed rapidly on the basis of continuous maturity and improvement of image processing and computer technology, and has been widely used in product inspection, reverse engineering, robot navigation and other fields. Computer vision measurement technology uses image sensors as a means to detect the three-dimensional ...

AI Technical Summary

Problems solved by technology

[0005] Purpose: Aiming at the deficiencies of the prior art, the present invention provides a Kinect-based object volume calculation method. Through a non-contact measurement method, the measurement target is not damaged, and the natural state of the measured object is not disturbed. It can be used under certain conditions and is easy to disassemble and install, which solves the problems of long measurement time and high cost of traditional measurement methods

Images