A method and device for insect behavior recognition based on spatio-temporal context

A technology of spatiotemporal context and recognition method, applied in the field of insect behavior recognition, can solve the problems of complicated acquisition of training data and low accuracy of insect behavior recognition, and achieve the goal of improving accuracy, facilitating labeling and classification, lowering the threshold for use and collecting training data. effect of difficulty

Active Publication Date: 2021-05-04
YANGTZE UNIVERSITY
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to overcome the above-mentioned technical deficiencies, provide an insect behavior recognition method, device and computer storage medium based on spatio-temporal context, and solve the technical problems of low insect behavior recognition accuracy and complicated training data acquisition in the prior art

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 method and device for insect behavior recognition based on spatio-temporal context
  • A method and device for insect behavior recognition based on spatio-temporal context
  • A method and device for insect behavior recognition based on spatio-temporal context

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0022] Such as figure 1 As shown, Embodiment 1 of the present invention provides an insect behavior recognition method based on spatio-temporal context, comprising the following steps:

[0023] S1. Acquire the insect behavior video, and obtain the manually-labeled original image in the insect behavior video;

[0024] S2. Extracting the area where the target insect is located from the original image to obtain an insect image, and converting the original image into a grayscale image;

[0025] S3. Generate a spatial image from the insect image through a time window, and generate a time image from the grayscale image through a time window;

[0026] S4. Generate a feature image according to the spatial image and the time image, mark the insect behavior in the feature image, and classify it according to the behavior;

[0027] S5. Using the classified feature images as training samples to train the neural network to obtain an insect behavior recognition model;

[0028] S6. Using t...

Embodiment 2

[0094] Embodiment 2 of the present invention provides an insect behavior recognition device based on spatio-temporal context, including a processor and a memory, and a computer program is stored on the memory, and when the computer program is executed by the processor, the method provided by Embodiment 1 is realized. Insect behavior recognition method based on spatio-temporal context.

[0095] The insect behavior recognition device based on the spatiotemporal context provided by the embodiment of the present invention is used to realize the method. Therefore, the technical effect of the insect behavior recognition method based on the spatiotemporal context is also possessed by the insect behavior recognition device based on the spatiotemporal context. Let me repeat.

Embodiment 3

[0097] Embodiment 3 of the present invention provides a computer storage medium, on which a computer program is stored. When the computer program is executed by a processor, the insect behavior recognition method based on spatio-temporal context provided in Embodiment 1 is implemented.

[0098] The computer storage medium provided by the embodiment of the present invention is used to implement the insect behavior recognition method based on the spatiotemporal context. Therefore, the technical effects of the insect behavior recognition method based on the spatiotemporal context are also possessed by the computer storage medium, and will not be repeated here.

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 present invention relates to the technical field of insect behavior recognition, and discloses a spatio-temporal context-based insect behavior recognition method, device, and computer storage medium, comprising the following steps: acquiring insect behavior videos, and acquiring artificially marked original images of insect behavior videos. image; extract the insect image from the original image where the target insect is located, and convert the original image into a grayscale image; generate a spatial image from the insect image through a time window, and generate a time image from the grayscale image through a time window; according to the spatial image and the time image to generate feature images, mark the insect behavior in the feature image, and classify according to the behavior; use the classified feature image as a training sample to train the neural network to obtain the insect behavior recognition model; use the insect behavior recognition model to test Recognition of insect behavior in video. The invention has the technical effects of high insect behavior recognition accuracy and simple acquisition of training data.

Description

technical field [0001] The present invention relates to the technical field of insect behavior recognition, in particular to a spatio-temporal context-based insect behavior recognition method, device and computer storage medium. Background technique [0002] With the rapid development of computer vision technology in recent years, it has become an inevitable trend to use computers to process and analyze video data in various industries to reduce manual labor. However, in the field of agricultural insect behavior analysis, we know that most researchers are still using manual observation and statistical methods, which are not only inefficient, but also cause statistical errors caused by the increase in personnel fatigue in the case of long-term observation. Gradually increase. Therefore, it is of great practical significance to develop a technology that can quickly and accurately identify the current behavior of insects, allowing researchers to devote more time and energy to ...

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): G06K9/00G06N3/04G06N3/08
CPCG06N3/08G06V40/20G06V20/41G06N3/045
Inventor 詹炜张智亮邹亚峰
Owner YANGTZE UNIVERSITY
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