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

Target detection method, system, apparatus and storage medium based on area proposal

A target detection and area technology, applied in the field of image recognition, can solve the problem of large space for target detection accuracy, and achieve the effect of high accuracy and enhanced effectiveness

Pending Publication Date: 2019-03-29
GUANGZHOU HISON COMP TECH
View PDF3 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The disadvantage of the existing target detection algorithm based on region proposal and its improvement is that it only focuses on the improvement of a certain aspect, such as the enhancement of feature information and the positioning ability of the bounding box, but it is difficult to effectively achieve the improvement of all aspects at the same time, so There is still a large space for target detection accuracy

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
  • Target detection method, system, apparatus and storage medium based on area proposal
  • Target detection method, system, apparatus and storage medium based on area proposal

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0047] The present invention includes a method for object detection based on region proposals, referring to figure 1 , including the following steps:

[0048] S1. Input the image to be detected into the target detection network;

[0049] S2. Receive the final bounding box output by the target detection network;

[0050] S3. Determine the target to be detected from the image to be detected according to the final bounding box;

[0051] The target detection network includes a first convolutional layer, a second convolutional layer, a region candidate network, and a plurality of branches with sequential relationships;

[0052] The first convolutional layer is used to receive the image to be detected and perform the first convolution process, thereby outputting the first convolution result; the second convolutional layer is used to receive the first convolution result and perform the second convolution process. Convolution processing, thereby outputting the second convolution re...

Embodiment 2

[0071] The target detection method in this embodiment includes the following steps:

[0072] S1. Input the image to be detected into the target detection network;

[0073] S2. Receive the final bounding box output by the target detection network;

[0074] S3. Determine the target to be detected from the image to be detected according to the final bounding box;

[0075] The target detection network includes a first convolutional layer, a second convolutional layer, a region candidate network, a projection unit, a pooling processing unit, a fusion unit and a prediction network;

[0076] The first convolutional layer is used to receive the image to be detected and perform the first convolution process, thereby outputting the first convolution result; the second convolutional layer is used to receive the first convolution result and perform the second convolution process. Convolution processing, thereby outputting the second convolution result;

[0077] The region candidate net...

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 target detection method, system, and device and a storage medium based on an area proposal. The method comprises the steps of inputting an image to be detected into a targetdetection network, receiving a final boundary frame outputted from the target detection network, and determining a target to be detected from the image to be detected according to the final boundary frame. The invention provides a novel target detection network, A target detection network includes a plurality of branches, Each branch contains local information and global information, and each branch continues to extract and learn feature information based on the processing results of the previous branch, so it can give attention to both local information and global information of the image, and can achieve high accuracy of target detection. The invention is widely applied to the technical field of image recognition.

Description

technical field [0001] The present invention relates to the technical field of image recognition, in particular to an object detection method, system, device and storage medium based on region proposal. Background technique [0002] Target detection algorithms can detect specific targets such as faces or cars in images, and are widely used in the field of image recognition technology. The mainstream target detection algorithms are divided into two categories: region proposal-based algorithms and region-free algorithms. The main principle of the region proposal-based algorithm is to divide the object detection task into two subtasks: in the first subtask, high-quality candidate boxes are generated; in the second subtask, these candidate boxes are classified by a subnetwork And bounding box regression, select the most suitable bounding box, so as to determine the target in the image. [0003] At present, the improvement of the existing target detection method based on region...

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): G06K9/00G06K9/46
CPCG06V20/10G06V10/44
Inventor 郝禄国杨琳葛海玉龙鑫曾文彬李伟儒
Owner GUANGZHOU HISON COMP TECH
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