Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Weakly supervised object detection method based on pseudo true value adaptive method

A technology of object detection and self-adaptive method, applied in neural learning methods, biological neural network models, image data processing, etc., can solve the problems of inaccurate object position detection and incompatible categories

Active Publication Date: 2018-03-23
HARBIN INST OF TECH
View PDF3 Cites 21 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 pseudo-truth adaptive 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
  • Weakly supervised object detection method based on pseudo true value adaptive method
  • Weakly supervised object detection method based on pseudo true value adaptive method
  • Weakly supervised object detection method based on pseudo true value adaptive method

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 adaptive method of this implementation mode includes:

[0024] Step 1), constructing training samples;

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

[0026] Step 3), the output result of the weakly supervised object detector is subjected to non-maximum suppression processing, and the bounding box with the highest score of each object is selected in the processing result picture;

[0027] Step 4), according to the position information of the selected bounding box in step 3), train the candidate region generation network, use the candidate region generation network to generate a plurality of candidate regions, and keep all candidate regions whose overlapping area ratio with the true value is greater than a certain threshold; Objects of ...

specific Embodiment approach 2

[0035] Specific implementation mode two: the difference between this implementation mode and specific implementation mode one is that step one specifically includes:

[0036] Step 1.1), receiving keywords input by the user; the keywords are used to indicate the category of the object;

[0037] 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 label information of the search result.

[0038] That is to say, 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 ("pedestrian", "vehicle", etc.), and downloading the top few thousand pictures can be used as training samples , no manual labeling is required.

[0039] It can be understood that, when u...

specific Embodiment approach 3

[0041] 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 A database constructed according to the method of Embodiment 2. The above English names are the names of the databases.

[0042] 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 adaptive method in order to solve a problem that a conventional full supervised object detector requires a large number of databases with labeling information and is inaccurate in object position detection when multiple objects are included in a picture and shield one another. The method comprises inputting a picture into a weakly supervised object detector, performing non-maximal suppression on the output result of the detector, and selecting the highest-scored boundary frame of each object froma processed result; training a candidate region generation network based on the position information of the selected boundary frames, and retaining the boundary frame whose overlapped area with the highest-scored boundary frame is larger than a certain value, averaging the pixel coordinates of candidate regions corresponding to the same object, and determining the unique boundary frame of each object based on a calculation result; inputting the boundary frame information into the fully supervised object detector as a pseudo true value. The weakly supervised object detection method is suitablefor object detection technology, especially general object detection technology 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 pseudo-truth adaptive 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 key information. Obtain. Object detection technology is now widely used in modern society, such as face detection and pedestrian detection in the security field, traffic sign recognition in intelligent transportation, vehicle detection and tr...

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): G06T7/00G06K9/62G06N3/08
CPCG06N3/084G06T7/0002G06T2207/20081G06F18/24
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 Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
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