A Lightweight Track Feature Detection Algorithm Based on Element Multiplication and Extended Path Aggregation Networks

Aiming at the problems of excessive computational load, insufficient real-time performance, and an excessive amount of model parameters in track inspection, this paper proposes a lightweight track feature detection module (YOLO-LWTD) based on YOLO11n: first, the StarNet module is integrated into the...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Sensors (Basel, Switzerland) Ročník 25; číslo 18; s. 5753
Hlavní autoři: Qiu, Hong, Yang, Dayong, Cao, Juanhua, Ming, Jingqiang, Jiang, Kun, Wu, Weijun
Médium: Journal Article
Jazyk:angličtina
Vydáno: Switzerland MDPI AG 16.09.2025
Témata:
Accuracy
Algorithms
Analysis
Computer vision
elemental multiplication
Information management
lightweight network
Localization
Optimization
Telecommunication systems
track inspection
YOLO11
lightweight network
YOLO11
track inspection
elemental multiplication
ISSN:1424-8220, 1424-8220
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Aiming at the problems of excessive computational load, insufficient real-time performance, and an excessive amount of model parameters in track inspection, this paper proposes a lightweight track feature detection module (YOLO-LWTD) based on YOLO11n: first, the StarNet module is integrated into the backbone network, and its elemental multiplication operation is utilized to enhance the feature characterization capability; second, in the neck part, a lightweight extended path aggregation network reconstructs the feature pyramid information flow paths by combining with the C3K2-Light module to enhance the efficiency of the multi-scale feature fusion; finally, in the head part, a lighter and more efficient detection header, Detect-LADH, is used to reduce the feature decoding complexity. Experimental validation showed that the improved model outperforms the benchmark model in precision, recall, and mean average precision (MAP) by 0.5%, 2.0%, and 0.8%, respectively, with an inference speed of 163 FPS (a 38.1% improvement). The model volume is compressed to 1.5 MB (a 71.1% lightweight rate). This provides an energy-efficient solution for lightweight track detection tasks geared towards embedded deployment or real-time processing.
Bibliografie: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/s25185753