Animal abnormal behavior detection method based on skeleton sequence

Through spatiotemporal feature modeling and deep learning methods based on skeleton sequences, combined with self-supervised comparative learning, the problem of insufficient accuracy and robustness of animal behavior detection in complex environments is solved, and efficient abnormal behavior recognition is achieved.

CN120340069APending Publication Date: 2025-07-18KASHGAR ELECTRONIC INFORMATION IND TECH RES INST
0 Cites 3 Cited by

Patent Information

Application Number
CN202510485443.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-04-17
Publication Date
2025-07-18

AI Technical Summary

Technical Problem

Existing animal behavior detection methods have poor accuracy and robustness in complex environments, making it difficult to effectively distinguish between normal and abnormal behaviors, especially lacking effective mining when processing spatiotemporal information.

Method used

Using a skeleton sequence-based method, the spatial and temporal characteristics of animal behavior are extracted through adaptive adjacency matrix and graph convolution network, and combined with deep learning and self-supervised comparison learning, the detection of animal abnormal behavior is carried out.

Benefits of technology

It realizes efficient and accurate animal abnormal behavior detection in complex environments, improves the robustness and generalization ability of detection, and can adapt to behavioral analysis of different scenarios and animal species.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention provides an animal abnormal behavior detection method based on a skeleton sequence, and belongs to animal behavior detection. Firstly, collected animal behavior videos are preprocessed, animal targets are detected, bounding box positions of the animal targets are obtained, then skeleton key points are estimated, and an animal skeleton sequence is generated. On the basis, spatial-temporal feature modeling is carried out on the skeleton sequence, animal behavior modes are analyzed, and abnormal behaviors (such as falling, attacking and the like) are accurately recognized. According to the method, the abnormal behavior detection result can be output in real time, and model optimization is performed according to feedback. The method is suitable for the scenes of animal behavior monitoring, health state evaluation, abnormal behavior early warning and the like, has high efficiency, expandability and practical application value, and solves the problems of low accuracy and poor robustness of animal behavior anomaly detection in a complex environment.
Need to check novelty before this filing date? Find Prior Art