BristolGorillas2020
收藏资源简介:
BristolGorillas2020数据集由布里斯托大学创建,专注于动物园环境中西部低地大猩猩的面部识别。该数据集包含628个视频片段和5428个标注的面部图像,这些图像来自布里斯托动物园的7只大猩猩。数据收集过程中,使用GoPro和Crosstour Action相机捕捉面部近景视频,每周两次,持续6周。该数据集旨在通过深度学习技术,特别是YOLOv3框架,解决动物园环境中大猩猩个体的面部识别问题,从而支持动物福利和相关研究。
The BristolGorillas2020 dataset was developed by the University of Bristol, focusing on facial recognition of western lowland gorillas in zoo environments. This dataset includes 628 video clips and 5,428 annotated facial images originating from 7 gorillas at Bristol Zoo. During the data collection process, close-up facial videos were captured using GoPro and Crosstour Action cameras twice a week for 6 consecutive weeks. This dataset aims to address the issue of individual facial recognition of gorillas in zoo environments via deep learning technologies, particularly the YOLOv3 framework, so as to support animal welfare and related research.




