Improved Small Object Detection Algorithm CRL-YOLOv5

Detecting small objects in images poses significant challenges due to their limited pixel representation and the difficulty in extracting sufficient features, often leading to missed or false detections. To address these challenges and enhance detection accuracy, this paper presents an improved smal...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Sensors (Basel, Switzerland) Ročník 24; číslo 19; s. 6437
Hlavní autori: Wang, Zhiyuan, Men, Shujun, Bai, Yuntian, Yuan, Yutong, Wang, Jiamin, Wang, Kanglei, Zhang, Lei
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Switzerland MDPI AG 01.10.2024
MDPI
Predmet:
Accuracy
Algorithms
attention mechanisms
contextual information
digital images
Medical imaging equipment
Remote sensing
Semantics
small object detection
spatial resolution
Telecommunication systems
Telematics
YOLOv5
small object detection
spatial resolution
YOLOv5
contextual information
attention mechanisms
digital images
ISSN:1424-8220, 1424-8220
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:Detecting small objects in images poses significant challenges due to their limited pixel representation and the difficulty in extracting sufficient features, often leading to missed or false detections. To address these challenges and enhance detection accuracy, this paper presents an improved small object detection algorithm, CRL-YOLOv5. The proposed approach integrates the Convolutional Block Attention Module (CBAM) attention mechanism into the C3 module of the backbone network, which enhances the localization accuracy of small objects. Additionally, the Receptive Field Block (RFB) module is introduced to expand the model’s receptive field, thereby fully leveraging contextual information. Furthermore, the network architecture is restructured to include an additional detection layer specifically for small objects, allowing for deeper feature extraction from shallow layers. When tested on the VisDrone2019 small object dataset, CRL-YOLOv5 achieved an mAP50 of 39.2%, representing a 5.4% improvement over the original YOLOv5, effectively boosting the detection precision for small objects in images.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:1424-8220
1424-8220
DOI:10.3390/s24196437