A method and device for identifying clothing and personal belongings
An identification method and article technology are applied in the field of identification methods and devices for clothing and belongings, which can solve the actual needs of clothing and belongings identification that are not given, identification technical solutions, and cannot meet multiple targets. question
Active Publication Date: 2019-04-30
NETPOSA TECH
View PDF5 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] In the process of realizing the present invention, the inventor found that there are at least the following problems in the related art: the current related art does not provide an effective technical solution for clothing and belongings identification, and thus cannot meet the needs of multi-target clothing in video surveillance images. and the actual needs of personal belongings identification
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0095] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only It is a part of embodiments of the present invention, but not all embodiments. The components of the embodiments of the invention generally described and illustrated in the figures herein may be arranged and designed in a variety of different configurations. Accordingly, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making...
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
Login to View More Abstract
The present invention provides a method and device for identifying clothing and belongings, wherein the method includes: acquiring surveillance video and extracting image information to be identified from the surveillance video; inputting the image information into a combined domain-based deep neural network model , get the score map corresponding to each target category, the score map includes: center domain score map, contour domain score map, and category domain score map; determine each target in the image information according to the score map corresponding to each target category The bounding rectangle, mask graphics, and main category of each target; the attribute information of each target is determined according to the bounding rectangle and mask graphics of each target. In the embodiment of the present invention, target detection and recognition are carried out in the way of combined domains, which can accurately detect and segment multiple clothing and personal belongings in the image information, and accurately extract the attribute information of each target, so as to meet the requirements of video surveillance. The actual demand for multi-target clothing and belongings recognition in images.
Description
technical field [0001] The present invention relates to the technical field of image processing, in particular to a method and device for identifying clothing and personal belongings. Background technique [0002] At present, in the field of video surveillance, there is a huge demand for the detection and identification of pedestrian clothing and belongings. If it is possible to accurately detect and identify information such as the style, texture, and color of everyone's clothing and personal belongings in the video image , thus, it will be able to greatly increase the amount of structured human body information extracted by the intelligent monitoring system, and then have great application value in semantic-based pedestrian retrieval applications. [0003] At present, traditional algorithms in related technologies can only roughly locate the upper and lower body regions of a person and estimate the color therein, which does not meet the needs of clothing recognition in ter...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/00G06K9/46
CPCG06V20/40G06V10/56
Inventor 任鹏远许健李岩张丛喆
Owner NETPOSA TECH