Next Article in Journal
OMCTrack: Integrating Occlusion Perception and Motion Compensation for UAV Multi-Object Tracking
Previous Article in Journal
Joint Resource Scheduling of the Time Slot, Power, and Main Lobe Direction in Directional UAV Ad Hoc Networks: A Multi-Agent Deep Reinforcement Learning Approach
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

A Lightweight Real-Time Infrared Object Detection Model Based on YOLOv8 for Unmanned Aerial Vehicles

College of Information Science and Technology, Donghua University, Shanghai 201620, China
*
Author to whom correspondence should be addressed.
Drones 2024, 8(9), 479; https://doi.org/10.3390/drones8090479
Submission received: 3 August 2024 / Revised: 10 September 2024 / Accepted: 10 September 2024 / Published: 12 September 2024

Abstract

Deploying target detection models on edge devices such as UAVs is challenging due to their limited size and computational capacity, while target detection models typically require significant computational resources. To address this issue, this study proposes a lightweight real-time infrared object detection model named LRI-YOLO (Lightweight Real-time Infrared YOLO), which is based on YOLOv8n. The model improves the C2f module’s Bottleneck structure by integrating Partial Convolution (PConv) with Pointwise Convolution (PWConv), achieving a more lightweight design. Furthermore, during the feature fusion stage, the original downsampling structure with ordinary convolution is replaced with a combination of max pooling and regular convolution. This modification retains more feature map information. The model’s structure is further optimized by redesigning the decoupled detection head with Group Convolution (GConv) instead of ordinary convolution, significantly enhancing detection speed. Additionally, the original BCELoss is replaced with EMASlideLoss, a newly developed classification loss function introduced in this study. This loss function allows the model to focus more on hard samples, thereby improving its classification capability. Compared to the YOLOv8n algorithm, LRI-YOLO is more lightweight, with its parameters reduced by 46.7% and floating-point operations (FLOPs) reduced by 53.1%. Moreover, the mean average precision (mAP) reached 94.1%. Notably, on devices with moderate computational power that only have a Central Processing Unit (CPU), the detection speed reached 42 frames per second (FPS), surpassing most mainstream models. This indicates that LRI-YOLO offers a novel solution for real-time infrared object detection on edge devices such as drones.
Keywords: infrared object detection; YOLOv8; UAVs; lightweight network structure; real-time detection infrared object detection; YOLOv8; UAVs; lightweight network structure; real-time detection

Share and Cite

MDPI and ACS Style

Ding, B.; Zhang, Y.; Ma, S. A Lightweight Real-Time Infrared Object Detection Model Based on YOLOv8 for Unmanned Aerial Vehicles. Drones 2024, 8, 479. https://doi.org/10.3390/drones8090479

AMA Style

Ding B, Zhang Y, Ma S. A Lightweight Real-Time Infrared Object Detection Model Based on YOLOv8 for Unmanned Aerial Vehicles. Drones. 2024; 8(9):479. https://doi.org/10.3390/drones8090479

Chicago/Turabian Style

Ding, Baolong, Yihong Zhang, and Shuai Ma. 2024. "A Lightweight Real-Time Infrared Object Detection Model Based on YOLOv8 for Unmanned Aerial Vehicles" Drones 8, no. 9: 479. https://doi.org/10.3390/drones8090479

APA Style

Ding, B., Zhang, Y., & Ma, S. (2024). A Lightweight Real-Time Infrared Object Detection Model Based on YOLOv8 for Unmanned Aerial Vehicles. Drones, 8(9), 479. https://doi.org/10.3390/drones8090479

Article Metrics

Back to TopTop