Evaluation of Deep Learning Benchmarks in Retrieving Outfalls Into Rivers With UAS Images
文献类型：期刊论文
| 作者 | Huang, Yaohuan; Wu, Chengbin |
| 刊名 | IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
 |
| 出版日期 | 2023 |
| 卷号 | 61页码:4703912 |
| 关键词 | Benchmark deep learning model performance optimization outfall retrieval |
| ISSN号 | 0196-2892 |
| DOI | 10.1109/TGRS.2023.3296157 |
| 产权排序 | 1 |
| 文献子类 | Article |
| 英文摘要 | Outfall surveys are critical to basin environmental and ecosystem protection. High-spatial-resolution remote sensing has been a key technology in outfall surveys. However, manual visual interpretation of outfalls from unmanned aircraft system (UAS) images is inefficient. Recently, the convolutional neural network (CNN) deep learning method has been demonstrated to be an efficient and accurate method for retrieving specific objects from remote sensing imagery. However, CNN's architecture and features are often proposed to detect common objects from universal images that are less complex than the specific remote sensing objects. Thus, an optimal CNN benchmark is significant to the performance of CNN-based approaches in the field of remote sensing. In this study, we evaluate the performance of several state-of-the-art CNN architectures and features for improving the geo-deep learning CNN for outfalls (GDCNN-outfalls) we proposed. We found that Faster R-CNN combined with feature pyramid network (FPN) and generalized intersection over union (GIoU) or complete intersection over union (CIoU) are the most suitable benchmarks, with AP(50) values of 68.7 and 67.0, respectively, which are better than those of cascade R-CNN (AP(50) of 64.6) and Libra R-CNN (AP(50) of 62.7). You only look once (YOLO)-v4 can be an alternative with an AP(50) of 66.8 and comprehensively considers retrieval accuracy, the current GPU performance, and the application needs. This result indicates that the latest CNN models in the field of computer vision are not always the most suitable benchmarks for specific object retrievals from remote sensing imagery. Our study also provides a typical workflow for the relevant CNN-based model designs and applications. |
| WOS关键词 | OBJECT DETECTION ; WATER-QUALITY ; LAND-USE ; SEGMENTATION ; NETWORK |
| WOS研究方向 | Geochemistry & Geophysics ; Engineering ; Remote Sensing ; Imaging Science & Photographic Technology |
| 语种 | 英语 |
| WOS记录号 | WOS:001043257600013 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 源URL | [http://ir.igsnrr.ac.cn/handle/311030/194618]  |
| 专题 | 资源与环境信息系统国家重点实验室_外文论文 |
| 作者单位 | 1.Institute of Geographic Sciences & Natural Resources Research, CAS 2.University of Chinese Academy of Sciences, CAS 3.Chinese Academy of Sciences |
| 推荐引用方式 GB/T 7714 | Huang, Yaohuan,Wu, Chengbin. Evaluation of Deep Learning Benchmarks in Retrieving Outfalls Into Rivers With UAS Images[J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING,2023,61:4703912. |
| APA | Huang, Yaohuan,&Wu, Chengbin.(2023).Evaluation of Deep Learning Benchmarks in Retrieving Outfalls Into Rivers With UAS Images.IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING,61,4703912. |
| MLA | Huang, Yaohuan,et al."Evaluation of Deep Learning Benchmarks in Retrieving Outfalls Into Rivers With UAS Images".IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 61(2023):4703912. |
入库方式： OAI收割
来源：地理科学与资源研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。