Multi-target unlabelled aquatic organism identification tracking method and system

An aquatic organism, multi-target technology, applied in the multi-target unmarked aquatic organism identification tracking and system field, can solve the problems of low biological individual resolution ability, excessive video storage space occupation, etc., to reduce system memory occupation and improve reliability. degree, the effect of solving the error rate

Active Publication Date: 2018-08-07
SHANDONG NORMAL UNIV
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] In order to solve the deficiencies of the prior art, the present invention provides a multi-target and unmarked aquatic biological identification tracking method and system. Through the unmarked identification technology and three-dimensional video processing, it solves the problem of biological individual in the existing biological tracking technology. Problems with low resolution and excessive video storage space usage

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
  • Multi-target unlabelled aquatic organism identification tracking method and system
  • Multi-target unlabelled aquatic organism identification tracking method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] It should be pointed out that the following detailed description is exemplary and intended to provide further explanation to the present application. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0044] In view of the fact that the traditional labeling method is time-consuming, labor-intensive and harmful to identify biological individuals, the present invention uses a label-free method to solve these problems. The main difficulty is that in video data, an individual corresponds to a pixel block, even for the same individual, The models are different in different postures. If we simply identify the area of ​​a single pixel block, it is possible that the moment when a certain fish swims in a C-shaped state is equivalent to the normal swimming area of ​​another fish. The solution we propose is to collect a series of postures of act...

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 multi-target unlabelled aquatic organism identification tracking method and system; the method comprises the following steps: 1, using an aquatic organism culturing system toculture aquatic organisms; 2, using two cameras, arranged on the top and a side face of the aquatic organism culturing system, to respectively gather videos of the aquatic organisms, and sending thegathered videos to a controller; 3, data processing: using the controller to process the video images gathered by the two cameras, thus finally obtaining aquatic organism three dimensional tracks. Theproblems that in existing organism tracer technology the organism individual distinguish capability is low, and too much video storage space is taken are solved via the unlabelled identity identification technology and video three dimensional processing.

Description

technical field [0001] The invention relates to a method and system for identifying and tracking aquatic organisms with multiple targets and without marking. Background technique [0002] Video is a commonly used research method in the study of biological behavior. By tracking the measured organisms in the video to observe various indicators, however, the original video format cannot be used for behavioral data collection. Most of the methods that use video to measure biological behavior The first step of the method is to build a recognition and tracking algorithm to estimate the position and posture of the organism in the area to be tested, and perform primary recognition and matching for each individual. Based on the assumption that the movement of each individual is small and smooth, the tracking is continuous. Organisms under the frame. However, although this method is efficient in the state of separation of individual organisms, when the organisms are close to each oth...

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): G06K9/00G06K9/32G06K9/34
CPCG06V20/46G06V20/40G06V10/62G06V10/24G06V10/267
Inventor 任宗明李尚戈
Owner SHANDONG NORMAL UNIV
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