Method and device for measuring two-dimensional size of an object

Abstract

The present disclosure discloses a method for measuring the two-dimensional size of an object, including: calibrating the RGB-D camera; obtaining color images and depth images of the area where the object to be measured is located and the background area; registering the RGB-D camera; Separate the color image of the object to be tested from the color image of the area where the object is to be tested and the color image of the background area; perform binarization and morphological processing on the color image of the object to be tested to obtain a mask image of the object to be tested; perform a hole in the depth image of the area where the object to be tested Fill in to obtain the improved depth image of the object to be measured; perform 3D reconstruction of the improved depth image of the object to be measured to obtain a 3D point cloud of the object to be measured; find the minimum circumscribed cuboid of the 3D point cloud of the object to be measured, and calculate the object to be measured according to the side length of the cuboid length and width. The disclosure is applicable to the measurement of the two-dimensional size of objects placed in any direction, has the advantages of automatic measurement, fast and accurate, and effectively improves the speed and accuracy of object size measurement.

Description

technical field [0001] The disclosure belongs to the technical field of computer vision and image processing, and in particular relates to a method and a measuring device for measuring two-dimensional dimensions of an object. Background technique [0002] In recent years, with the development and progress of computer vision, the two-dimensional size measurement technology of objects based on computer vision has gradually replaced the traditional tape measurement and estimation method. It has the advantages of simple operation, time-saving and labor-saving, and is widely used in various fields. Such as cargo size and logistics packaging box measurement, size estimation of agricultural and sideline products, industrial parts assembly line measurement, etc. [0003] The two-dimensional size measurement technology of objects based on computer vision usually consists of two parts: image acquisition equipment and image processing algorithms. Based on single-purpose image acquisit...

AI Technical Summary

Problems solved by technology

Based on single-purpose image acquisition, a single camera shoots the object to be measured, and generally calculates the object size based on the image pixel distance and adding the actual scale. This method requires multiple manual selection of the object to be measured, and the real-time performance is insufficient and the degree of automation is not high.

The image acquisition based on RGB-D camera generally uses the RGB-D camera to perform three-dimensional reconstruction of the object to be measured, and then uses the point cloud processing algorithm to extract the outer boundary size of the point cloud as the size of the object to be measured; the existing RGB-D camera based For example, it is difficult to obtain a stable boundary by extracting the point cloud of the edge of the object for calculation, and the existing methods often ignore the imaging defects of the RGB-D camera itself, such as the light absorption, reflectivity or self-destructiveness of the object to be measured. Incomplete image data caused by factors such as occlusion, especially for objects with irregular shapes, this problem is more prominent, resulting in large errors in the measurement results

Images