Monocular vision box body volume measuring method based on multi-line structural light image recognition

A multi-line structured light and image recognition technology, applied in the direction of measuring devices, optical devices, instruments, etc., can solve the problems of difficult box measurement, high algorithm complexity, complex application scenarios, etc., and meet the requirements of portability and algorithm The effect of low complexity and low method complexity

Active Publication Date: 2019-07-30
上海拓今智能科技有限公司
View PDF8 Cites 23 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Its application scenarios are relatively complex, so how to quickly, accurately and efficiently measure the volume of the box in a complex environment is an urgent problem to be solved in these industries. In addition, how to develop portable volume measuring instruments on the basis of good performance is also a problem for these industries. Urgent needs
At present, there are many measurement methods: manual detection, manual measurement by ruler, which is not only inefficient but also prone to errors; grating measurement method, automatic measurement by equipment, high measurement accuracy, but it requires manpower to move the box to a fixed position. It is very difficult to measure a box higher than 1 meter, which is labor-intensive and the cost of the instrument is high; the volume measurement method based on binocular stereo vision has high algorithm complexity, difficult stereo matching, low accuracy in measuring large-sized boxes, and is not suitable for logistics, etc. Complex Measurement Scenarios

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Monocular vision box body volume measuring method based on multi-line structural light image recognition
  • Monocular vision box body volume measuring method based on multi-line structural light image recognition
  • Monocular vision box body volume measuring method based on multi-line structural light image recognition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0085] Taking the first surface of a well-shaped structured light regular box, the measurement process of double parallel structured light measuring the adjacent surface is taken as an example, and the actual measurement experiment is carried out. The structured light projected by the laser is projected onto the surface of the regular box to form a straight line of light. Due to the influence of the surface pattern of the regular box, the surrounding complex background, and the lighting conditions, the structured light strip pattern captured by the camera appears as an incomplete light strip, and the bright part in the center of the light strip is white, and the edge part is red. Figure 5 It is a schematic diagram of the measurement of the box by the well-shaped and double-parallel structured light of the present invention, and the resolution of the image is 2592×1944 pixels. According to the multi-line structured light-based monocular vision box volume measurement method pro...

Embodiment 2

[0091] In the process of measurement, if some slender cabinets are encountered, method 1 and method 2 cannot work normally at this time. At this time, the cross-shaped line structured light is used to measure the length of the cabinet. The cross-structured light projected by the laser is projected onto the surface of the regular box to form a straight line of light. During the operation, try to control the parallelism between the cross laser and the edge of the box, and take the measurement pictures obtained as follows: Figure 5 As shown, the picture resolution is 2592×1944 pixels. According to the measurement method three in the monocular vision box volume measurement method based on multi-line structured light proposed by the present invention, the slender box is measured, and it is realized by c++ and java programming.

[0092] Table 3 Cross-shaped laser light strip detection results

[0093] endpoint 1 endpoint 2 slope intercept line segment 1 (1...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention relates to a monocular vision box body volume measuring method based on multi-line structural light image recognition. The monocular vision box body volume measuring method comprises thefollowing steps that (1) a camera is calibrated, and multi-line laser plane parameters are acquired; (2) calculation of mapping of two-dimensional coordinates to three-dimensional spatial coordinatesis conducted; (3) the box edges are detected and the laser central line is extracted by using a deep learning method; and (4) structural light with a well shape, structural light with a dual-parallel-line and structural light with a cross shape are correspondingly used for measuring different box bodies to obtain the volumes of inerratic box bodies. According to the monocular vision box body volume measuring method based on multi-line structural light image recognition, the multi-line structural light (the well shape, the cross shape and the parallel line shape) is casted on the measured boxbody plane, intersection points of the line structural light and the edges of the boxed are detected through imaging processing, the points are converted from the two-dimensional coordinates to three-dimensional spatial coordinates according to a structural light triangulation measuring theory to calculate the lengths, the widths and the heights of the inerratic box bodies, and the volumes are further calculated. According to the monocular vision box body volume measuring method based on multi-line structural light image recognition, the complexity of the algorithm is low, the method can be greatly applied to PC terminals and mobile terminal devices, real-time on-line measuring can be conducted, and the requirement of portability is met.

Description

technical field [0001] The invention belongs to a method for measuring the volume of a box, in particular to a method for measuring the volume of a box with monocular vision based on multi-line structured light image recognition. Background technique [0002] Box volume measurement is mainly used in logistics, e-commerce, warehouse storage, aviation warehouses and other fields, providing various services such as freight calculation, cargo placement, box recommendation, etc. Its application scenarios are relatively complex, so how to quickly, accurately and efficiently measure the volume of the box in a complex environment is an urgent problem to be solved in these industries. In addition, how to develop portable volume measuring instruments on the basis of good performance is also a problem for these industries. Urgent needs. At present, there are many measurement methods: manual detection, manual measurement by ruler, which is not only inefficient but also prone to errors;...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G01B11/00
CPCG01B11/00
Inventor 袁三华郑和生彭涛
Owner 上海拓今智能科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products