YOLO-SE: Improved YOLOv8 for Remote Sensing Object Detection and Recognition
Object detection remains a pivotal aspect of remote sensing image analysis, and recent strides in Earth observation technology coupled with convolutional neural networks (CNNs) have propelled the field forward. Despite advancements, challenges persist, especially in detecting objects across diverse...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-12-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/24/12977 |
| _version_ | 1827575858605326336 |
|---|---|
| author | Tianyong Wu Youkou Dong |
| author_facet | Tianyong Wu Youkou Dong |
| author_sort | Tianyong Wu |
| collection | DOAJ |
| description | Object detection remains a pivotal aspect of remote sensing image analysis, and recent strides in Earth observation technology coupled with convolutional neural networks (CNNs) have propelled the field forward. Despite advancements, challenges persist, especially in detecting objects across diverse scales and pinpointing small-sized targets. This paper introduces YOLO-SE, a novel YOLOv8-based network that innovatively addresses these challenges. First, the introduction of a lightweight convolution SEConv in lieu of standard convolutions reduces the network’s parameter count, thereby expediting the detection process. To tackle multi-scale object detection, the paper proposes the SEF module, an enhancement based on SEConv. Second, an ingenious Efficient Multi-Scale Attention (EMA) mechanism is integrated into the network, forming the SPPFE module. This addition augments the network’s feature extraction capabilities, adeptly handling challenges in multi-scale object detection. Furthermore, a dedicated prediction head for tiny object detection is incorporated, and the original detection head is replaced by a transformer prediction head. To address adverse gradients stemming from low-quality instances in the target detection training dataset, the paper introduces the Wise-IoU bounding box loss function. YOLO-SE showcases remarkable performance, achieving an average precision at IoU threshold 0.5 (AP50) of 86.5% on the optical remote sensing dataset SIMD. This represents a noteworthy 2.1% improvement over YOLOv8 and YOLO-SE outperforms the state-of-the-art model by 0.91%. In further validation, experiments on the NWPU VHR-10 dataset demonstrated YOLO-SE’s superiority with an accuracy of 94.9%, surpassing that of YOLOv8 by 2.6%. The proposed advancements position YOLO-SE as a compelling solution in the realm of deep learning-based remote sensing image object detection. |
| first_indexed | 2024-03-08T21:02:55Z |
| format | Article |
| id | doaj.art-c562704001e040368f6e00caee4ff251 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-08T21:02:55Z |
| publishDate | 2023-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-c562704001e040368f6e00caee4ff2512023-12-22T13:49:46ZengMDPI AGApplied Sciences2076-34172023-12-0113241297710.3390/app132412977YOLO-SE: Improved YOLOv8 for Remote Sensing Object Detection and RecognitionTianyong Wu0Youkou Dong1College of Marine Science and Technology, China University of Geosciences, Wuhan 430074, ChinaCollege of Marine Science and Technology, China University of Geosciences, Wuhan 430074, ChinaObject detection remains a pivotal aspect of remote sensing image analysis, and recent strides in Earth observation technology coupled with convolutional neural networks (CNNs) have propelled the field forward. Despite advancements, challenges persist, especially in detecting objects across diverse scales and pinpointing small-sized targets. This paper introduces YOLO-SE, a novel YOLOv8-based network that innovatively addresses these challenges. First, the introduction of a lightweight convolution SEConv in lieu of standard convolutions reduces the network’s parameter count, thereby expediting the detection process. To tackle multi-scale object detection, the paper proposes the SEF module, an enhancement based on SEConv. Second, an ingenious Efficient Multi-Scale Attention (EMA) mechanism is integrated into the network, forming the SPPFE module. This addition augments the network’s feature extraction capabilities, adeptly handling challenges in multi-scale object detection. Furthermore, a dedicated prediction head for tiny object detection is incorporated, and the original detection head is replaced by a transformer prediction head. To address adverse gradients stemming from low-quality instances in the target detection training dataset, the paper introduces the Wise-IoU bounding box loss function. YOLO-SE showcases remarkable performance, achieving an average precision at IoU threshold 0.5 (AP50) of 86.5% on the optical remote sensing dataset SIMD. This represents a noteworthy 2.1% improvement over YOLOv8 and YOLO-SE outperforms the state-of-the-art model by 0.91%. In further validation, experiments on the NWPU VHR-10 dataset demonstrated YOLO-SE’s superiority with an accuracy of 94.9%, surpassing that of YOLOv8 by 2.6%. The proposed advancements position YOLO-SE as a compelling solution in the realm of deep learning-based remote sensing image object detection.https://www.mdpi.com/2076-3417/13/24/12977object detectionremote sensing imagesmulti-scaleloss functions |
| spellingShingle | Tianyong Wu Youkou Dong YOLO-SE: Improved YOLOv8 for Remote Sensing Object Detection and Recognition Applied Sciences object detection remote sensing images multi-scale loss functions |
| title | YOLO-SE: Improved YOLOv8 for Remote Sensing Object Detection and Recognition |
| title_full | YOLO-SE: Improved YOLOv8 for Remote Sensing Object Detection and Recognition |
| title_fullStr | YOLO-SE: Improved YOLOv8 for Remote Sensing Object Detection and Recognition |
| title_full_unstemmed | YOLO-SE: Improved YOLOv8 for Remote Sensing Object Detection and Recognition |
| title_short | YOLO-SE: Improved YOLOv8 for Remote Sensing Object Detection and Recognition |
| title_sort | yolo se improved yolov8 for remote sensing object detection and recognition |
| topic | object detection remote sensing images multi-scale loss functions |
| url | https://www.mdpi.com/2076-3417/13/24/12977 |
| work_keys_str_mv | AT tianyongwu yoloseimprovedyolov8forremotesensingobjectdetectionandrecognition AT youkoudong yoloseimprovedyolov8forremotesensingobjectdetectionandrecognition |