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

Three-dimensional target detection method and system based on deep neural network

A technology of deep neural network and 3D target, which is applied in the field of 3D target detection method and system based on deep neural network, which can solve the problems of increasing cost and achieve the effects of small amount of calculation, good adaptability, good versatility and real-time performance

Pending Publication Date: 2021-01-22
HOHAI UNIV CHANGZHOU
View PDF7 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The complex deep neural network will greatly increase the required cost, and in many occasions it is necessary to meet the real-time requirements, which is a major problem in the application of 3D object 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
  • Three-dimensional target detection method and system based on deep neural network
  • Three-dimensional target detection method and system based on deep neural network
  • Three-dimensional target detection method and system based on deep neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0025] Such as figure 1 As shown, a 3D object detection method based on deep neural network, including: a. Obtain the color image and point cloud information of the environment where the target object is located; b. Use the deep neural network YOLO6D and YOLOv2 to jointly detect the color image, frame Select the target object, respectively obtain the 2D bounding box and the 3D bounding box of the target object on the color image; c, map the point cloud information to the image coordinate system of the color image, and obtain the coordinate information of the point cloud information in the color image; d 1. According to the 2D bounding box and 3D bounding box of the target object on the color image, combined with the coordinate information of the point cloud information in the color image, the depth information of the 2D bounding box and the 3D bounding box are obtained respectively; e, according to the 2D bounding box and the 3D bounding box The depth information of the boundi...

Embodiment 2

[0045] Based on the method for detecting a three-dimensional object based on a deep neural network described in Embodiment 1, this embodiment provides a three-dimensional object detection system based on a deep neural network, including:

[0046] The first module is used to obtain color images and point cloud information of the environment where the target object is located;

[0047] The second module is used to jointly detect the color image using the deep neural network YOLO6D and YOLOv2, frame the target object, and obtain the 2D bounding box and 3D bounding box of the target object on the color image respectively;

[0048] The third module is used to map the point cloud information to the image coordinate system of the color image, and obtain the coordinate information of the point cloud information in the color image;

[0049] The fourth module is used to obtain the depth information of the 2D bounding box and the 3D bounding box respectively according to the 2D bounding ...

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 target detection method and system based on a deep neural network, and belongs to the technical field of three-dimensional target detection. The three-dimensional target detection method and system based on the deep neural network have the advantages of being accurate in target detection, small in neural network layer number, small in calculated amount,low in hardware requirement, high in universality and real-time performance and the like. The method comprises the steps of obtaining a color image and point cloud information of an environment wherea target object is located; adopting a deep neural network YOLO6D and YOLOv2 to carry out joint detection on the color image, and respectively obtaining a 2D bounding box and a 3D bounding box of thetarget object on the color image; mapping the point cloud information to an image coordinate system of the color image, and obtaining coordinate information of the point cloud information in the colorimage; according to the 2D bounding box and the 3D bounding box of the target object on the image and combining the coordinate information of the point cloud information in the color image, respectively obtaining depth information of the 2D bounding box and the 3D bounding box; and according to the depth information of the 2D bounding box and the 3D bounding box and combining the dimension of thepoint cloud information, obtaining the category, size and pose information of the target object.

Description

technical field [0001] The invention belongs to the technical field of three-dimensional target detection, and in particular relates to a three-dimensional target detection method and system based on a deep neural network. Background technique [0002] With the development of deep learning theory, it has been widely used in various fields such as target recognition, face recognition, moving target detection and style transfer. However, with the deepening of the network, the neural network function is becoming more and more powerful, but its The requirements for hardware are getting higher and higher, especially in the field of 3D object detection. The complex deep neural network will greatly increase the required cost, and in many occasions it is necessary to meet the real-time requirements, which is a major problem in the application of 3D object detection. Contents of the invention [0003] In order to solve the deficiencies in the prior art, the present invention provi...

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): G06T17/00G06T7/90G06T7/70G06N3/08G06N3/04
CPCG06T17/00G06N3/08G06T7/90G06T7/70G06T2207/10028G06N3/045Y02T10/40
Inventor 沈金荣赵鸣晖彭娟
Owner HOHAI UNIV CHANGZHOU
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com