[1]LIANG Liming,FENG Yao,LONG Pengwei,et al.Remote sensing image object detection based on MobileViT and multiscale feature aggregation[J].CAAI Transactions on Intelligent Systems,2024,19(5):1168-1177.[doi:10.11992/tis.202310022]
Copy
Remote sensing image object detection based on MobileViT and multiscale feature aggregation
CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume:
19
Number of periods:
2024 5
Page number:
1168-1177
Column:
学术论文—机器感知与模式识别
Public date:
2024-09-05
- Title:
- Remote sensing image object detection based on MobileViT and multiscale feature aggregation
- Keywords:
- deep learning; remote sensing image; object detection; YOLOv7-tiny; MobileViT module; multi-scale feature fusion; contextual information; Wise-IoU
- CLC:
- TP391
- DOI:
- 10.11992/tis.202310022
- Abstract:
- A new algorithm is proposed based on MobileViT and multi-scale feature aggregation (referred to as FWM-YOLOv7t) to address problems such as complex background interference, difficulty in extracting small objects, and object multi-scale differences in remote sensing image object detection. First, we design a multi-scale feature aggregation module to establish context dependencies for remote sensing targets, which improves the accuracy of detecting multi-scale and small targets. Then, we utilize the MobileViT module to fuse the advantages of convolutional neural networks and vision transformers for effective local and global information encoding to suppress non-target noise interference. Finally, we introduce the Wise-IoU loss function, which focuses on ordinary quality anchor boxes to enhance the detection performance of the algorithm. Experimental evaluations on the public RSOD and NWPU VHR-10 dataset demonstrate that FWM-YOLOv7t can significantly improve the average accuracy of remote sensing image target detection. Furthermore, compared with other object detection algorithms, the FWM-YOLOv7t algorithm exhibits superior effectiveness in detecting complex, small, and multiscale objects in remote sensing imagery.
- References:
-
[1] 赵文清, 康怿瑾, 赵振兵, 等. 改进YOLOv5s的遥感图像目标检测[J]. 智能系统学报, 2023, 18(1): 86-95.
ZHAO Wenqing, KANG Yijin, ZHAO Zhenbing, et al. A remote sensing image object detection algorithm with improved YOLOv5s[J]. CAAI transactions on intelligent systems, 2023, 18(1): 86-95.
[2] MING Qi, MIAO Lingjuan, ZHOU Zhiqiang, et al. CFC-net: a critical feature capturing network for arbitrary-oriented object detection in remote-sensing images[J]. IEEE transactions on geoscience and remote sensing, 2022, 60: 5605814.
[3] CONG Runmin, ZHANG Yumo, FANG Leyuan, et al. RRNet: relational reasoning network with parallel multiscale attention for salient object detection in optical remote sensing images[J]. IEEE transactions on geoscience and remote sensing, 2021, 60: 5613311.
[4] SEDAGHAT A, EBADI H. Remote sensing image matching based on adaptive binning SIFT descriptor[J]. IEEE transactions on geoscience and remote sensing, 2015, 53(10): 5283-5293.
[5] DALAL N, TRIGGS B. Histograms of oriented gradients for human detection[C]//2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Diego: IEEE, 2005: 886-893.
[6] 吴珺, 董佳明, 刘欣, 等. 注意力优化的轻量目标检测网络及应用[J]. 智能系统学报, 2023, 18(3): 506-516.
WU Jun, DONG Jiaming, LIU Xin, et al. Lightweight object detection network and its application based on the attention optimization[J]. CAAI transactions on intelligent systems, 2023, 18(3): 506-516.
[7] 梁礼明, 詹涛, 雷坤, 等. 多分辨率融合输入的U型视网膜血管分割算法[J]. 电子与信息学报, 2023, 45(5): 1795-1806.
LIANG Liming, ZHAN Tao, LEI Kun, et al. Multi-resolution fusion input U-shaped retinal vessel segmentation algorithm[J]. Journal of electronics & information technology, 2023, 45(5): 1795-1806.
[8] GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//2014 IEEE Conference on Computer Vision and Pattern Recognition. Columbus: IEEE, 2014: 580-587.
[9] GIRSHICK R. Fast R-CNN[C]//2015 IEEE International Conference on Computer Vision. Santiago: IEEE, 2015: 1440-1448.
[10] REN Shaoqing, HE Kaiming, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[J]. IEEE transactions on pattern analysis and machine intelligence, 2017, 39(6): 1137-1149.
[11] LIU Wei, ANGUELOV D, ERHAN D, et al. SSD: single shot MultiBox detector[C]//European Conference on Computer Vision. Cham: Springer, 2016: 21-37.
[12] FARHADI A, REDMON J. YOLOv3: an incremental improvement[C]//2018 IEEE/CVF Conference on Compu- ter Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 1804-2767.
[13] BOCHKOVSKIY A, WANG C Y, LIAO H M, et al. YOLOv4: optimal speed and accuracy of object detection[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2020: 2-7.
[14] WANG C Y, BOCHKOVSKIY A, LIAO H Y M. YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors[C]//2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Vancouver: IEEE, 2023: 7464-7475.
[15] 吴萌萌, 张泽斌, 宋尧哲, 等. 基于自适应特征增强的小目标检测网络[J]. 激光与光电子学进展, 2023, 60(6): 65-72.
WU Mengmeng, ZHANG Zebin, SONG Yaozhe, et al. Small-target detection network based on adaptive feature enhancement[J]. Laser & optoelectronics progress, 2023, 60(6): 65-72.
[16] 李美霖, 芮杰, 金飞, 等. 基于改进YOLOX的遥感影像目标检测算法[J]. 吉林大学学报(地球科学版), 2023, 53(4): 1313-1322.
LI Meilin, RUI Jie, JIN Fei, et al. Remote sensing image target detection algorithm based on improved YOLOX[J]. Journal of Jilin University (earth science edition), 2023, 53(4): 1313-1322.
[17] WANG Xin, HE Ning, HONG Chen, et al. Improved YOLOX-X based UAV aerial photography object detection algorithm[J]. Image and vision computing, 2023, 135: 104697.
[18] AKYON F C, ONUR ALTINUC S, TEMIZEL A. Slicing aided hyper inference and fine-tuning for small object detection[C]//2022 IEEE International Conference on Image Processing. Bordeaux: IEEE, 2022: 966-970.
[19] 梁礼明, 何安军, 朱晨锟, 等. 融合Transformer和跨级相位感知的结肠息肉分割方法[J]. 生物医学工程学杂志, 2023, 40(2): 234-243.
LIANG Liming, HE Anjun, ZHU Chenkun, et al. Colorectal polyp segmentation method based on fusion of transformer and cross-level phase awareness[J]. Journal of biomedical engineering, 2023, 40(2): 234-243.
[20] ZHU Xingkui, LYU Shuchang, WANG Xu, et al. TPH-YOLOv5: improved YOLOv5 based on transformer prediction head for object detection on drone-captured scenarios[C]//2021 IEEE/CVF International Conference on Computer Vision Workshops. Montreal: IEEE, 2021: 2778-2788.
[21] SAHIN O, OZER S. YOLODrone: improved YOLO architecture for object detection in UAV images[C]//2022 30th Signal Processing and Communications Applications Conference. Safranbolu: IEEE, 2022: 1-4.
[22] DOSOVITSKIY A, BEYER L, KOLESNIKOV A, et al. An image is worth 16x16 words: transformers for image recognition at scale[C]//International Conference on Learning Representations. NewOrleans: ICLR, 2021: 1-22.
[23] MEHTA S, RASTEGARI M. MobileViT: light-weight, general-purpose, and mobile-friendly vision transformer[EB/OL]. (2021-10-05)[2023-10-17]. https://arxiv.org/abs/2110.02178.
[24] ZHENG Zhaohui, WANG Ping, LIU Wei, et al. Distance-IoU loss: faster and better learning for bounding box regression[C]//Proceedings of the AAAI Conference on Artificial Intelligence. New York: AAAI, 2020: 12993-13000.
[25] TONG Zanjia, CHEN Yuhang, XU Zewei, et al. Wise-IoU: bounding box regression loss with dynamic focusing mechanism[EB/OL]. (2023-01-24)[2023-10-17]. https://arxiv.org/abs/2301.10051.
[26] LONG Yang, GONG Yiping, XIAO Zhifeng, et al. Accurate object localization in remote sensing images based on convolutional neural networks[J]. IEEE transactions on geoscience and remote sensing, 2017, 55(5): 2486-2498.
[27] CHENG Gong, ZHOU Peicheng, HAN Junwei. Learning rotation-invariant convolutional neural networks for object detection in VHR optical remote sensing images[J]. IEEE transactions on geoscience and remote sensing, 2016, 54(12): 7405-7415.
- Similar References:
Memo
-
Last Update:
2024-09-05