| 引用本文: | 王殿伟,赵文博,房杰,许志杰.多类场景下无人机航拍视频烟雾检测算法[J].哈尔滨工业大学学报,2023,55(10):122.DOI:10.11918/202205119 |
| WANG Dianwei,ZHAO Wenbo,FANG Jie,XU Zhijie.Smoke detection algorithm for UAV aerial video in multiple scenarios[J].Journal of Harbin Institute of Technology,2023,55(10):122.DOI:10.11918/202205119 |
|
| 摘要: |
| 在无人机航拍视频烟雾检测领域中,由于不同检测场景差异大,导致现有烟雾检测算法经常出现检测精度低、速度慢等问题。为了解决以上问题,建立了一个基于无人机视角的多类场景下的烟雾数据集（UAV smoke dataset,USD）,并提出了一种改进YOLOx的多类场景下无人机视频烟雾检测算法。首先,在YOLOx网络模型中引入改进的注意力机制,分别改进通道特征和空间特征的提取过程,提取更加具有表征能力的烟雾特征；然后,提出一种双向特征融合模块,增强多尺度特征融合模块对小目标烟雾特征的融合能力；最后,引入Focal-EIOU损失函数,解决训练过程中出现正负样本不平衡,以及预测框和真实框不相交时无法反映两个框的距离远近和重合度大小等问题。实验结果表明,所提算法在应用于多类场景下无人机视频烟雾检测任务时具有较好的鲁棒性,对比多个经典烟雾检测算法,本文算法在不同数据集上的烟雾检测准确率均有不同的提升,比如对比原有的YOLOx-s模型,准确率提升2.7%,召回率提升3%,速度达到73.6帧/s。 |
| 关键词: 烟雾检测 无人机航拍视频 多场景 YOLOx 注意力机制 改进特征金字塔 |
| DOI：10.11918/202205119 |
| 分类号:X932;TP391.41 |
| 文献标识码:A |
| 基金项目:公安部科技强警基础工作专项(2019GABJC42);西安邮电大学研究生创新基金(CXJJZL2021022) |
|
| Smoke detection algorithm for UAV aerial video in multiple scenarios |
|
WANG Dianwei1,ZHAO Wenbo1,FANG Jie1,XU Zhijie2
|
|
（1.School of Communications and Information Engineering, Xian University of Posts and Telecommunications, Xian 710121, China;2.School of Computing and Engineering, University of Huddersfield, Huddersfield HD1 3DH, UK)
|
| Abstract: |
| In the field of UAV smoke detection, due to the significant variations in different detection scenes, existing smoke detection algorithms often suffer from issues such as low detection accuracy and slow speed. To address these issues, in this paper we constructed a new UAV smoke dataset (USD) in multiple scenes, and proposed an improved YOLOx UAV smoke detection algorithm in multiple scenes. Firstly, we introduced an improved attention module into the YOLOx network to improve the extraction process of channel features and spatial features respectively, which can extract more representational smoke features. Then, we presented a two-way fusion network to enhance the fusion ability of multi-scale feature fusion module for small smoke target features. Finally, we utilized a Focal-EIOU loss function to address the issues such as the imbalance of positive and negative samples in the training process, and the distance and coincidence degree of two frames cannot be reflected when the prediction frame and real frame do not intersect. Experimental results show that the proposed algorithm has good robustness when applied to UAV smoke detection tasks in multiple scenarios. Compared with several classical smoke detection algorithms, the accuracy of the proposed smoke detection method on different data sets has been improved respectively. For instance, compared with the original YOLOx-s model, the accuracy was improved by 2.7%, the recall rate was improved by 3%, and the speed reached 73.6 frames per second. |
| Key words: smoke detection UAV aerial video multiple scenarios YOLOx attention mechanism improved feature pyramid |
