We found a match
Your institution may have rights to this item. Sign in to continue.
- Title
多尺度融合与FMB改进的YOLOv8 异常行为检测方法.
- Authors
石洋宇; 左景; 谢承杰; 郑棣文; 卢树华
- Abstract
To resolve the problems of anomaly behavior detection including multi-scale variations, miss and false detection, and complex background interference, a method is proposed by incorporating the fusion of multi-scale features and fast multi-cross block (FMB) for anomaly behavior detection. Based on YOLOv8 as the baseline network, a FMB has been designed in the backbone to enhance context information awareness and reduce network parameters. Meanwhile, a spatial-progressive convolution pooling (S-PCP) module has been proposed to achieve multi-scale information fusion, thereby reducing the issues of miss and false detection caused by scale differences and improving detection accuracy. A SimAM attention mechanism has been introduced in the neck to suppress complex background interference and improve object detection performance. And WIoU has been used to balance the penalty force on anchor boxes, enhancing the model's generalization performance. The proposed method has been extensively validated on the UCSD-Ped1 and UCSD-Ped2 datasets, and its generalization has been tested on the OPIXray dataset. The results indicate that the proposed method with fewer parameters achieves different improvements in anomaly behavior recognition accuracy compared to many advanced detection algorithms, demonstrating an excellent detection method for pedestrian anomaly behavior.
- Publication
Journal of Computer Engineering & Applications, 2024, Vol 60, Issue 9, p101
- ISSN
1002-8331
- Publication type
Article
- DOI
10.3778/j.issn.1002-8331.2401-0240