DeepBhvTracking: A Novel Behavior Tracking Method for Laboratory Animals Based on Deep Learning

Sun, Guanglong and Lyu, Chenfei and Cai, Ruolan and Yu, Chencen and Sun, Hao and Schriver, Kenneth E. and Gao, Lixia and Li, Xinjian (2021) DeepBhvTracking: A Novel Behavior Tracking Method for Laboratory Animals Based on Deep Learning. Frontiers in Behavioral Neuroscience, 15. ISSN 1662-5153

[thumbnail of pubmed-zip/versions/2/package-entries/fnbeh-15-750894-r1/fnbeh-15-750894.pdf] Text
pubmed-zip/versions/2/package-entries/fnbeh-15-750894-r1/fnbeh-15-750894.pdf - Published Version

Download (1MB)

Abstract

Behavioral measurement and evaluation are broadly used to understand brain functions in neuroscience, especially for investigations of movement disorders, social deficits, and mental diseases. Numerous commercial software and open-source programs have been developed for tracking the movement of laboratory animals, allowing animal behavior to be analyzed digitally. In vivo optical imaging and electrophysiological recording in freely behaving animals are now widely used to understand neural functions in circuits. However, it is always a challenge to accurately track the movement of an animal under certain complex conditions due to uneven environment illumination, variations in animal models, and interference from recording devices and experimenters. To overcome these challenges, we have developed a strategy to track the movement of an animal by combining a deep learning technique, the You Only Look Once (YOLO) algorithm, with a background subtraction algorithm, a method we label DeepBhvTracking. In our method, we first train the detector using manually labeled images and a pretrained deep-learning neural network combined with YOLO, then generate bounding boxes of the targets using the trained detector, and finally track the center of the targets by calculating their centroid in the bounding box using background subtraction. Using DeepBhvTracking, the movement of animals can be tracked accurately in complex environments and can be used in different behavior paradigms and for different animal models. Therefore, DeepBhvTracking can be broadly used in studies of neuroscience, medicine, and machine learning algorithms.

Item Type: Article
Subjects: Universal Eprints > Biological Science
Depositing User: Managing Editor
Date Deposited: 16 Feb 2023 06:39
Last Modified: 05 Mar 2024 03:40
URI: http://journal.article2publish.com/id/eprint/424

Actions (login required)

View Item
View Item