Next Article in Journal
Multi-Aligned and Multi-Scale Augmentation for Occluded Person Re-Identification
Previous Article in Journal
Hardware, Algorithms, and Applications of the Neuromorphic Vision Sensor: A Review
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

LCW-YOLO: A Lightweight Multi-Scale Object Detection Method Based on YOLOv11 and Its Performance Evaluation in Complex Natural Scenes

School of Computer Science and Technology, Zhejiang University of Science and Technology, Hangzhou 310023, China
*
Author to whom correspondence should be addressed.
Sensors 2025, 25(19), 6209; https://doi.org/10.3390/s25196209
Submission received: 21 July 2025 / Revised: 17 September 2025 / Accepted: 1 October 2025 / Published: 7 October 2025
(This article belongs to the Section Remote Sensors)

Abstract

Accurate object detection is fundamental to computer vision, yet detecting small targets in complex backgrounds remains challenging due to feature loss and limited model efficiency. To address this, we propose LCW-YOLO, a lightweight detection framework that integrates three innovations: Wavelet Pooling, a CGBlock-enhanced C3K2 structure, and an improved LDHead detection head. The Wavelet Pooling strategy employs Haar-based multi-frequency reconstruction to preserve fine-grained details while mitigating noise sensitivity. CGBlock introduces dynamic channel interactions within C3K2, facilitating the fusion of shallow visual cues with deep semantic features without excessive computational overhead. LDHead incorporates classification and localization functions, thereby improving target recognition accuracy and spatial precision. Extensive experiments across multiple public datasets demonstrate that LCW-YOLO outperforms mainstream detectors in both accuracy and inference speed, with notable advantages in small-object, sparse, and cluttered scenarios. Here we show that the combination of multi-frequency feature preservation and efficient feature fusion enables stronger representations under complex conditions, advancing the design of resource-efficient detection models for safety-critical and real-time applications.
Keywords: LCW-YOLO; wavelet pooling; CGBlock; LDHead; target detection; deep learning LCW-YOLO; wavelet pooling; CGBlock; LDHead; target detection; deep learning

Share and Cite

MDPI and ACS Style

Li, G.; Fang, J. LCW-YOLO: A Lightweight Multi-Scale Object Detection Method Based on YOLOv11 and Its Performance Evaluation in Complex Natural Scenes. Sensors 2025, 25, 6209. https://doi.org/10.3390/s25196209

AMA Style

Li G, Fang J. LCW-YOLO: A Lightweight Multi-Scale Object Detection Method Based on YOLOv11 and Its Performance Evaluation in Complex Natural Scenes. Sensors. 2025; 25(19):6209. https://doi.org/10.3390/s25196209

Chicago/Turabian Style

Li, Gang, and Juelong Fang. 2025. "LCW-YOLO: A Lightweight Multi-Scale Object Detection Method Based on YOLOv11 and Its Performance Evaluation in Complex Natural Scenes" Sensors 25, no. 19: 6209. https://doi.org/10.3390/s25196209

APA Style

Li, G., & Fang, J. (2025). LCW-YOLO: A Lightweight Multi-Scale Object Detection Method Based on YOLOv11 and Its Performance Evaluation in Complex Natural Scenes. Sensors, 25(19), 6209. https://doi.org/10.3390/s25196209

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop