Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A three-dimensional depth image segmentation algorithm based on a multi-edge fusion mechanism

A technology of depth image and segmentation algorithm, applied in image analysis, image enhancement, image data processing, etc., can solve the problem of incomplete particle image, achieve the effect of ensuring integrity and reducing over-segmentation and under-segmentation

Active Publication Date: 2019-01-08
CHANGAN UNIV
View PDF3 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Aiming at the incomplete particle image caused by occlusion in the structured light 3D vision system, the purpose of this invention is to propose a 3D depth image segmentation algorithm based on the multi-edge fusion mechanism, which can detect coarse aggregate more completely It can lay a solid foundation for the three-dimensional non-destructive testing of aggregate particles in particle size and gradation automatic detection.

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
  • A three-dimensional depth image segmentation algorithm based on a multi-edge fusion mechanism
  • A three-dimensional depth image segmentation algorithm based on a multi-edge fusion mechanism
  • A three-dimensional depth image segmentation algorithm based on a multi-edge fusion mechanism

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0057]The 3D vision technology based on structured light has become a very competitive characterization solution for particle industrial detection due to its fast scanning speed, low requirements on the imaging environment, and compared with 2D vision technology, it can effectively characterize the 3D characteristics of particles. However, due to the widespread existence of problems such as laser occlusion or camera occlusion, there are problems such as incompleteness in the edge of the depth image of the scanned particle, which in turn will affect the accuracy of the particle characterization results. In order to solve this problem, this algorithm is based on three different particle edge images, and uses two fusion algorithms to generate particle edge images. Finally, according to the characteristics of the depth image, the particle segmentation is realized by combining the watershed algorithm. The concrete steps of the inventive method are as follows:

[0058] A three-dimen...

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 discloses a three-dimensional depth image segmentation algorithm based on a multi-edge fusion mechanism, which comprises the following steps: obtaining a depth image of aggregate particles and performing pretreatment to obtain a pretreated depth map, extracting an edge image from the pretreated depth map and performing thinning treatment on the edge image; fusing the edge image of the occluded region with the thinned image for the first time, and fusing the edge image of the aggregate particles with the image of the missing data for the second time; then using the watershed algorithm to segment the aggregate particles. The invention aims at the problem of missing depth data of the particle depth image because the image is shielded, adopts two fusion methods to form the particle edge image, and completes the missing edge, thereby ensuring the integrity of the particle shape and the edge corner feature. Seed region calibration and distance transform function in the watershed algorithm are optimized to reduce over-segmentation and under-segmentation effectively.

Description

technical field [0001] The invention belongs to the technical field of road engineering and relates to an image processing method, in particular to a three-dimensional depth image segmentation algorithm based on a multi-edge fusion mechanism. Background technique [0002] Aggregate is the main material that constitutes the load-bearing skeleton of asphalt concrete, and plays a key role in filling the skeleton of the entire pavement. The morphological characteristics of aggregate particles, aggregate gradation, and real-time non-destructive testing of particles directly determine the service life and use of asphalt pavement. performance. Morphological characteristics of aggregate particles include aggregate particle shape, size, angularity, and texture. The shape of aggregate particles has a great influence on the strength and stability of asphalt concrete. [0003] As an important part of concrete materials, mineral mixtures are composed of aggregate particles of different...

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
IPC IPC(8): G06T7/10G06T7/13G06T7/136
CPCG06T2207/10028G06T2207/20152G06T2207/20221G06T7/10G06T7/13G06T7/136
Inventor 沙爱民孙朝云刘汉烨李伟郝雪丽徐倩倩
Owner CHANGAN UNIV
Features
  • Generate Ideas
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com