We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
YOLO-FNC: An Improved Method for Small Object Detection in Remote Sensing Images Based on YOLOv7.
- Authors
Lanxue Dang; Gang Liu; Yan-e Hou; Hongyu Han
- Abstract
The detection algorithms of small objects in remote sensing images is often challenging due to the complex background and limited pixels. This can lead to reduced accuracy in detection and an increased number of missed small objects. So this paper introduces YOLOFNC, an enhanced network based on YOLOv7. To improve the model's ability to capture features of small objects, an enhanced C3-Faster module based on the C3 module is designed and integrated into the YOLOv7 network. This module helps extract more features related to small objects. Additionally, we employ Normalized Wasserstein Distance (NWD) fusion GIoU as a novel loss function to refine the accuracy of network optimization weights and the small object regression framework. Furthermore, a coordinated attention (CA) mechanism is incorporated at strategic locations in the model to reduce redundant information in the feature layer and prevent the loss of important small object features. we conduct comparison experiments between YOLO-FNC and other commonly used object detection algorithms on DIOR, AITOD, and VisDrone datasets. The experimental results show that YOLO-FNC achieves 84.4% mAP on the DIOR dataset, 35.9% mAP on the AI-TOD dataset, and 52.6% mAP on the VisDrone dataset. Compared to YOLOv7 and other remote sensing object detection models, YOLO-FNC demonstrates better performance in object detection.
- Subjects
OBJECT recognition (Computer vision); REMOTE sensing; ALGORITHMS
- Publication
IAENG International Journal of Computer Science, 2024, Vol 51, Issue 9, p1281
- ISSN
1819-656X
- Publication type
Article