教授
发布时间：2022-07-11
点击次数：
| 影响因子： | 1.309 |
| DOI码： | 10.1007/s10905-022-09802-7 |
| 所属单位： | 长江大学计算机科学学院 |
| 发表刊物： | Journal of Insect Behavior |
| 刊物所在地： | Cham, Switzerland |
| 项目来源： | 中国高校产学研创新基金新一代信息技术创新项目2020（2020ITA03012） |
| 关键字： | Bactrocera minax · grooming behavior · behavior recognition · object detection · object tracking · spatio-temporal feature |
| 摘要： | Studying the grooming behavior of Bactrocera minax adults at rest and the behavioral interference among multiple adults can provide a research basis for related animal behavior studies. The traditional method of manual recording grooming behavior is time-consuming and error-prone. Based on computer vision and deep learning technology, we first build the improved Yolov5 object detection algorithm to detect B. minax in the video data, and then combine the detector and the improved DeepSort object tracker to track each B. minax individual, and finally build the spatio-temporal feature detection model to recognize and quantify the grooming behavior of each B. minax individual. Using our method to recognize the grooming behavior of a total of 23 B. minax from 4 videos, the results show that the average accuracy rate is over 96%, and the standard deviation is less than 3%. Compared with the existing methods, our method has a higher accuracy rate, and the deviation is controlled within a certain range. Therefore, while significantly improving the quantification efficiency, the method described also guarantees the accuracy of grooming behavior recognition and provides new ideas and methods for studying insect behaviors. |
| 合写作者： | Tianyu Dong, Jinhui She, Chao Min, Huazi Huang, Yong Sun |
| 第一作者： | Shengbing Hong |
| 论文类型： | 期刊论文 |
| 通讯作者： | Wei Zhan |
| 论文编号： | 20260830-014 |
| 学科门类： | 工学 |
| 一级学科： | 计算机科学与技术 |
| 文献类型： | 期刊 |
| 卷号： | 35 |
| 期号： | 4 |
| 页面范围： | 67-81 |
| 字数： | 4854 |
| ISSN号： | 0892-7553; 1572-8889 |
| 发表时间： | 2022-07-11 |
