Method and device for retrieving objects and method and device for verifying retrieval

A technology of objects and object images, which is applied in digital data information retrieval, still image data retrieval, image data processing, etc., can solve the problems of inability to effectively retrieve objects, low accuracy of retrieval results, and inability to express objects well Features and other issues

Active Publication Date: 2014-04-09
NEC (CHINA) CO LTD
View PDF4 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Since the color histogram can only reflect the overall matching degree between images, the application range of object retrieval through the color histogram has certain limitations; in addition, because the color of the object is greatly affected by factors such as illumination Therefore, when the lighting and other conditions change, neither the object retrieval method through the color distribution of the object nor the object retrieval method through the color histogram can effectively retrieve the object. , resulting in inaccurate search results

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
  • Method and device for retrieving objects and method and device for verifying retrieval
  • Method and device for retrieving objects and method and device for verifying retrieval
  • Method and device for retrieving objects and method and device for verifying retrieval

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0106] This embodiment provides a method for object retrieval. The method retrieves an object image in a video by using local feature points of a specified area in an object image to be retrieved, and realizes object retrieval through a local area of ​​the image. see figure 1 , the method flow provided by this embodiment is specifically as follows:

[0107] 101: Acquire the image of the object to be retrieved and a specified area in the image of the object to be retrieved, and calculate the local feature points of the specified area in the image of the object to be retrieved, where the specified area is a distinguishing area selected by the user through the GUI;

[0108] 102: Find an index matching the local feature points of the specified area in the pre-built index set, the index set is constructed according to the local feature points of the object image in the video;

[0109] Further, before searching the index matching the local feature points of the specified area in th...

Embodiment 2 Embodiment 3

[0153] Embodiment two

[0154] This embodiment provides a method for object retrieval, because when retrieving objects, the object image will contain some distinguishing local regions, and the local feature points can be used to detect and describe the local features in the image, therefore, In order to expand the application range of object retrieval, the method provided in this embodiment retrieves object images in video by using local feature points in a specified area of ​​the object image to be retrieved, and realizes object retrieval through local regions of images. Combining the content of the first embodiment above, for the convenience of description, this embodiment takes local feature points as SIFT (Scale-Invariant Feature Transform, scale-invariant feature transform) points as an example for description. see image 3 , the method flow provided by this embodiment is specifically as follows:

[0155] 301: Obtain an object image in the video, and calculate the SIFT ...

Embodiment 4

[0213] This embodiment provides an object retrieval device, which is used to implement the object retrieval methods provided in the first and second embodiments above. see Figure 9 , the device consists of:

[0214] The first acquiring module 901 is configured to acquire the image of the object to be retrieved and the designated area of ​​the image of the object to be retrieved, where the designated area is a distinguishing area selected by the user through the GUI;

[0215] A calculation module 902, configured to calculate local feature points of a designated area in the image of the object to be retrieved acquired by the first acquisition module 901;

[0216] A search module 903, configured to search for an index matching the local feature points of the designated area calculated by the calculation module 902 in the pre-built index set, the index set is constructed according to the local feature points of the object image in the video;

[0217] The second acquiring module...

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 method and a device for retrieving objects and a method and a device for verifying retrieval, and belongs to the field of video monitoring technologies. The method for retrieving the objects includes acquiring to-be-retrieved object images and specified regions of the to-be-retrieved object images, and computing local feature points of the specified regions in the to-be-retrieved object images; searching indexes in preliminarily created index sets; acquiring object images corresponding to the found indexes and using the acquired object images as object images retrieved in video. The indexes are matched with the local feature points of the specified regions. The methods and the devices have the advantages that the object images are retrieved in the video by the aid of the local feature points of the specified regions in the to-be-retrieved object images, so that the objects can be retrieved in the local regions of the images, the object retrieval application range can be expanded, and the accuracy of retrieval results can be improved; the retrieved object images are verified after the object images are retrieved, so that unmatched object images can be removed, and the accuracy of the retrieval results can be further improved.

Description

technical field [0001] The invention relates to the technical field of video monitoring, in particular to an object retrieval method, a retrieval verification method and a device. Background technique [0002] With the continuous development of video technology, the application range of video surveillance is becoming wider and wider. How to retrieve the specified objects in the video while managing the captured video has become an urgent problem to be solved and developed. [0003] In the prior art, when retrieving an object in a video, one way is to search for an object image having the same main color as the image of the object to be retrieved in the captured video after determining the main color of the image of the object to be retrieved; One way is to measure the matching degree between each image in the captured video and the image of the object to be retrieved according to the color histogram after calculating the color histogram of the object image to be retrieved, a...

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): G06F17/30G06T7/00
CPCG06K9/00H04N7/18G06F17/30244G06F16/7837G06V10/255G06V10/757
Inventor 唐绍鹏梁大为曾炜
Owner NEC (CHINA) CO LTD
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