Graph convolutional network system and 3D object detection method based on graph convolutional network system

A convolutional network and convolutional neural network technology, applied in three-dimensional object recognition, biological neural network models, character and pattern recognition, etc., can solve the problems of lack of data diversity, achieve strong interpretability, improve accuracy, and gain The effect of final performance

Active Publication Date: 2021-05-14
广东众聚人工智能科技有限公司
View PDF13 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although 2D object detection is relatively mature and widely used in the industry, 3D object detection from 2D images is still a challenging problem due to the lack of data and the diversity of appearance and shape of objects in semantic categories

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
  • Graph convolutional network system and 3D object detection method based on graph convolutional network system
  • Graph convolutional network system and 3D object detection method based on graph convolutional network system
  • Graph convolutional network system and 3D object detection method based on graph convolutional network system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0057] This embodiment proposes a graph convolutional network system for 3D object detection. The system includes: shape semantic extraction module, multi-layer perceptron, proposal generator and proposal reasoning module.

[0058] The shape semantic extraction module is used to receive the point cloud feature of the image, model the geometric position of the point in the point cloud feature, and obtain the global semantic feature.

[0059] The multi-layer perceptron is connected with the shape semantic extraction module, and is used for extracting multi-level semantic features based on the global semantic features, using a multi-layer graph convolutional neural network, and using an attention mechanism to filter the multi-level semantic features.

[0060] The proposal generator is connected with the multi-layer perceptron, and is used for summarizing the filtered multi-level semantic features, and weighting to generate at least one primary proposal.

[0061] The proposal rea...

Embodiment 2

[0113] This embodiment provides a 3D object detection method based on a graph convolutional network system. The method is based on the graph convolutional network system described in Example 1. image 3 It is a flowchart of a 3D object detection method based on a graph convolutional network system provided by an embodiment of the present invention. Such as image 3 As shown, the method includes steps S10-S40.

[0114] S10: Obtain a training data set, wherein the training data set includes a plurality of training data, and each training data is a point cloud feature of an image; perform 3D bounding box labeling and semantic category labeling for each training data.

[0115] S20: Construct any graph convolutional network system in Embodiment 1.

[0116] S30: Using the training data set to train the graph convolutional network system.

[0117]S40: Collect point cloud features of the image to be predicted, input the point cloud features of the image to be predicted into the tr...

Embodiment 3

[0151] Figure 4 It is a schematic structural diagram of a computer device provided by an embodiment of the present invention. Such as Figure 4 As shown, the device includes a processor 410 and a memory 420 . The number of processors 410 may be one or more, Figure 4 A processor 410 is taken as an example.

[0152] As a computer-readable storage medium, the memory 420 can be used to store software programs, computer-executable programs and modules, such as program instructions / modules of the 3D object detection method based on the graph convolutional network system in the embodiment of the present invention. The processor 410 implements the above-mentioned 3D object detection method based on the graph convolutional network system by running software programs, instructions and modules stored in the memory 420 .

[0153] The memory 420 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system and an app...

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 graph convolutional network system and a 3D object detection method based on the graph convolutional network system. The system comprises a shape semantic extraction module used for modeling geometric positions of points in point cloud features of an image; a multi-layer perceptron which is connected with the shape semantic extraction module and is used for extracting multi-level semantic features by using a multi-layer graph convolutional neural network and filtering the multi-level semantic features by using an attention mechanism; a proposal generator which is connected with the multi-layer perceptron and is used for summarizing the multi-level semantic features and weighting to generate a primary proposal; and a proposal reasoning module which is connected with the proposal generator and is used for predicting a 3D bounding box and a semantic category of the object in the image by utilizing the global semantic features and the primary proposal. According to the method, the detection performance of the whole graph convolutional network system is effectively improved, the precision of 3D object detection is improved, and the interpretability of the deep network is higher.

Description

technical field [0001] Embodiments of the present invention relate to the field of computer vision, in particular to a graph convolutional network system and a 3D object detection method based on the graph convolutional network system. Background technique [0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art. [0003] With the development of science and technology, people urgently need to use computer resources to perceive and understand the world, thereby providing more convenience for people's lives. Due to the existence of body organs such as eyes, nose, and ears, human beings perceive the world through vision, smell, hearing, etc. Among them, visual information accounts for more than 80% of the information obtained by humans from the outside world. Just like the eye is to the human body, the discipline of machine vision plays a pivotal role in the field of machine intel...

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): G06K9/00G06K9/32G06K9/62G06N3/04
CPCG06V20/64G06V10/25G06N3/045G06F18/23213G06F18/214
Inventor 杨光远黄瑾张凯丁冬睿
Owner 广东众聚人工智能科技有限公司
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap