Small Object Detection Algorithm Based on Improved YOLOv8 for Remote Sensing

Due to the limitations of small targets in remote sensing images such as background noise, poor information, and so on, the results of commonly used detection algorithms in small target detection is not satisfactory. To improve the accuracy of detection results, we develop an improved algorithm base...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE journal of selected topics in applied earth observations and remote sensing Ročník 17; s. 1 - 15
Hlavní autoři: Yi, Hao, Liu, Bo, Zhao, Bin, Liu, Enhai
Médium: Journal Article
Jazyk:angličtina
Vydáno: Piscataway IEEE 01.01.2024
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
Algorithms
Ambient noise
Attention mechanism
Background noise
Deep learning
Detection
Detection algorithms
Feature extraction
Feature maps
Modules
Object recognition
Optical imaging
Optical sensors
Parameter modification
Real-time systems
Remote sensing
Target detection
Transformers
Vision transformer
YOLOv8
ISSN:1939-1404, 2151-1535
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Due to the limitations of small targets in remote sensing images such as background noise, poor information, and so on, the results of commonly used detection algorithms in small target detection is not satisfactory. To improve the accuracy of detection results, we develop an improved algorithm based on YOLOv8, called LAR-YOLOv8. First, in the feature extraction network, the local module is enhanced by using the dual-branch architecture attention mechanism, while the vision transformer block is used to maximize the representation of the feature map. Second, an attention-guided bi-directional feature pyramid network is designed to generate more discriminative information by efficiently extracting feature from the shallow network through a dynamic sparse attention mechanism, and adding top-down paths to guide the subsequent network modules for feature fusion. Finally, the RIOU loss function is proposed to avoid the failure of the loss function and improve the shape consistency between the predicted and ground truth box. Experimental results on NWPU VHR-10, RSOD and CARPK datasets verify that LAR-YOLOv8 achieves satisfactory results in terms of mAP (small), mAP, model parameters and FPS, and can prove that our modifications made to the original YOLOv8 model are effective.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1939-1404
2151-1535
DOI:10.1109/JSTARS.2023.3339235