学生课堂行为数据集 (SCB-dataset3)
收藏资源简介:
学生课堂行为数据集(SCB-dataset3)由成都东软学院创建,包含5686张图像和45578个标签,重点关注六种行为:举手、阅读、写作、使用手机、低头和趴桌。数据集覆盖从幼儿园到大学的不同场景,通过YOLOv5、YOLOv7和YOLOv8算法评估,平均精度达到80.3%。该数据集旨在为学生行为检测研究提供坚实基础,解决教育领域中学生行为数据集的缺乏问题。
The Student Classroom Behavior Dataset (SCB-dataset3) was developed by Chengdu Neusoft University. It contains 5,686 images and 45,578 labels, focusing on six core student behaviors: raising hands, reading, writing, using mobile phones, lowering heads, and lying prone on desks. The dataset covers diverse scenarios ranging from kindergarten to higher education. It was evaluated using YOLOv5, YOLOv7 and YOLOv8 algorithms, achieving an average precision of 80.3%. This dataset aims to provide a solid foundation for student behavior detection research and address the scarcity of student behavior datasets in the field of education.

- 1SCB-Dataset3: A Benchmark for Detecting Student Classroom Behavior成都东软学院 · 2023年



