|
|
基于GAM-YOLOv8算法的生活垃圾检测
|
Abstract:
日常生活垃圾分拣是困扰人们的一个难题，生活垃圾的种类繁多，所处环境复杂，常用的目标检测算法无法适应各种复杂的环境，导致精度较低。为了准确的分拣生活垃圾，提出了一种基于GAM注意力机制的YOLOv8生活垃圾检测算法。该算法在YOLOv8优秀的目标检测基础上，加入GAM注意力机制，增强网络对重要通道特征信息的关注能力，提升高层网络中图像特征语义信息的提取能力，提高复杂环境垃圾分类检测精度的效果。实验表明，在40多种生活垃圾类别检测测试中，改进的YOLOv8算法mAP平均精度84.5%，较原始算法YOLOv8提升了0.7%。因此改进的YOLOv8算法可以通过对垃圾图像的分析和识别，帮助人们准确地进行垃圾分类。较好的满足了生活垃圾检测精度的要求。
The sorting of daily household garbage is a difficult problem that troubles people. There are many kinds of household garbage and the environment is complicated. In order to sort domestic waste accurately, a YOLOv8 domestic waste detection algorithm based on GAM attention mechanism was proposed. Based on the excellent target detection of YOLOv8, this algorithm adds GAM attention mechanism to enhance the network’s ability to pay attention to important channel feature information and improve the extraction ability of image feature semantic information in high-level networks. Experiments show that in more than 40 types of domestic waste detection tests, the average accuracy of the improved YOLOv8 algorithm mAP is 84.5%, which is 0.7% higher than that of the original YOLOv8 algorithm. Therefore, the improved YOLOv8 algorithm can help people to classify garbage quickly and accurately through the analysis and recognition of garbage images. It can meet the requirement of detecting precision of domestic waste.
| [1] | Girshick, R., Donahue, J., Darrell, T. and Malik, J. (2014) Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation. 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, 23-28 June 2014, 580-587. https://doi.org/10.1109/CVPR.2014.81 |
| [2] | 马雯, 于炯, 王潇, 陈嘉颖. 基于改进Faster R-CNN的垃圾检测与分类方法[J]. 计算机工程, 2021, 47(8): 294-300. |
| [3] | 邵延华, 张铎, 楚红雨, 张晓强, 饶云波. 基于深度学习的YOLO目标检测综述[J]. 电子与信息学报, 2022, 35(16): 156-162. |
| [4] | 赵珊, 刘子路, 郑爱玲, 高雨. 基于MobileNetV2和IFPN改进的SSD垃圾实时分类检测方法[J]. 计算机应用, 2022, 42(S1): 106-111. |
| [5] | Tan, M.X., Pang, R.M. and Le, Q.V. (2020) Efficient Det: Scalable and Efficient Object Detection. CVPR, 26, 125-163. |
| [6] | Talaat, F.M. and Eldin, H.Z. (2023) An Improved Fire Detection Approach Based on YOLO-v8 for Smart Cities. Neural Computing and Applications, 35, 20939-20954. https://doi.org/10.1007/s00521-023-08809-1 |
| [7] | 袁磊, 唐海, 陈彦蓉, 等. 改进YOLOv5的复杂环境道路目标检测方法[J]. 计算机工程与应用, 2023, 59(16): 268-293. |
| [8] | Wang, C.-Y., Bochkovskiy, A. and Liao, H.-Y.M. (2023) YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detectors. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, 17-24 June 2023, 7464-7475. https://doi.org/10.1109/CVPR52729.2023.00721 |
| [9] | Lin, T.-Y., Dollár, P., Girshick, R., He, K., Hariharan, B. and Belongie, S. (2017) Feature Pyramid Networks for Object Detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, 21-26 July 2017, 2117-2125. https://doi.org/10.1109/CVPR.2017.106 |
| [10] | Li, H., Xiong, P., An, J. and Wang, L. (2018) Pyramid Attention Network for Semantic Segmentation. http://arxiv.org/abs/1805.10180 |
