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

A Weakly Supervised Object Detection Method Based on False Truth Search

A technology of object detection and weak supervision, applied in image analysis, instrumentation, computing, etc., can solve problems such as inconsistent categories and inaccurate object position detection

Active Publication Date: 2020-09-15
HARBIN INST OF TECH
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to solve the problem that existing full-supervised object detectors need to rely on a large number of databases with labeled information, and at the same time solve the problem of inaccurate object position detection due to labeling errors when there are multiple objects in the picture and the objects are occluded from each other, and the actual The objects that need to be detected in the application may not match the object categories of the database or far exceed the shortcomings of the categories in these databases, and a weakly supervised object detection method based on the false truth search method is proposed, including:

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 Weakly Supervised Object Detection Method Based on False Truth Search
  • A Weakly Supervised Object Detection Method Based on False Truth Search
  • A Weakly Supervised Object Detection Method Based on False Truth Search

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0023] Specific implementation mode 1: The weakly supervised object detection method based on the false truth search method of this implementation mode includes:

[0024] Step 1), constructing training samples;

[0025] Step 2), input the picture in the training sample into the weakly supervised object detector based on multiple-instance learning method (Multiple-Instance Learning);

[0026] Step 3), performing non-maximum suppression processing on the output result of the weakly supervised object detector, retaining bounding boxes exceeding a predetermined score threshold in the processing results, and removing bounding boxes lower than the score threshold;

[0027] Step 4), among the bounding boxes retained in step 3), delete bounding boxes that are completely contained in other bounding boxes;

[0028] Step 5), for each bounding box obtained in step 4), calculate the overlapping area of ​​the bounding box and other bounding boxes, and fuse the bounding boxes whose overlapp...

specific Embodiment approach 2

[0036] Specific implementation mode two: the difference between this implementation mode and specific implementation mode one is that step one specifically includes:

[0037] Step 1.1), receiving keywords input by the user; the keywords are used to indicate the category of the object;

[0038] Step 1.2), use the keyword to search in the search engine, select a preset number of search results and use the keyword as the annotation information of the search result.

[0039] That is, the present invention only needs to know the simple object category information in the picture, and can train the model without complex object position information. The simple object category information here can be obtained in many ways, such as searching for pictures in the search engine in the form of keywords ("pedestrians", "vehicles", etc.), and downloading the top few thousand pictures can be used as training samples , no manual labeling is required.

[0040] It can be understood that, when u...

specific Embodiment approach 3

[0042] Specific embodiment three: the difference between this embodiment and specific embodiment one or two is: in step 1), the training sample set can be any one of PASCAL VOC 2007 / 2012, MC COCO, WIDER FACE and FDDB database, or is The database constructed according to the method of the second specific embodiment.

[0043] Other steps and parameters are the same as those in Embodiment 1 or Embodiment 2.

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 weakly-supervised object detection method based on a pseudo-true value search method. The method is proposed to solve the problems that existing fully-supervised object detectors need to rely on a large quantity of databases with annotation information, and when multiple objects are contained in a picture and the objects are sheltered by one another, object position detection is not accurate. The method comprises the steps that a picture in a training sample is input into a weakly-supervised object detector; non-maximum suppression (NMS) processing is performed on anoutput result of the weakly-supervised object detector, and boundary boxes exceeding a predetermined score threshold value are reserved; among the reserved boundary boxes, the boundary boxes completely contained in other boundary boxes are deleted; superposition areas of the boundary boxes and other boundary boxes are calculated, and the boundary boxes with the superposition areas greater than acertain threshold value are fused; and information of the boundary boxes after fusion is used as pseudo-true value information, the pseudo-true value information is input into a fully-supervised object detector, and a detection result is obtained. The method is applicable to object detection technologies and particularly general object detection technologies in real scenes.

Description

technical field [0001] The invention relates to the field of machine vision, in particular to a weakly supervised object detection method based on a false truth search method. Background technique [0002] Object detection is a very important research topic in the field of machine vision. It is the basic technology for advanced tasks such as image segmentation, object tracking, and behavior analysis and recognition. In addition, with the development of mobile Internet technology, the number of images and videos is increasing in an explosive manner. There is an urgent need for a technology that can quickly and accurately identify and locate objects in images and videos, so as to intelligently classify subsequent images and videos and identify key information. Obtain. Now object detection technology is widely used in modern society, such as face detection and pedestrian detection in the security field, traffic sign recognition in intelligent transportation, vehicle detection ...

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 Patents(China)
IPC IPC(8): G06T7/73G06T7/77
CPCG06T7/75G06T7/77
Inventor 张永强丁明理李贤杨光磊董娜
Owner HARBIN INST OF 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