UAV Target Detection Algorithm Based on Improved YOLOv8

Wang, Feng; Wang, Hongyuan; Qin, Zhiyong; Tang, Jiaying

doi:10.1109/access.2023.3325677

Cited by 30 publications

(7 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Specific use cases may include real-time people and vehicle detection in surveillance systems, object recognition for self-driving vehicles, robotic operations in warehouse settings, medical image anomaly detection, and product defect identification in industrial processes. YOLOv8m embodies an adept balance of speed, accuracy, and size, making it a valuable asset across a wide spectrum of applications [50], particularly where real-time performance and moderate resource availability are central considerations.…”

Section: Yolov8smentioning

confidence: 99%

Traffic Sign Sensing: A Deep Learning approach for enhanced Road Safety

Gupta,

Mhala,

Mangal

et al. 2024

Preprint

View full text Add to dashboard Cite

There exists paramount importance of traffic signs in ensuring road safety and efficiency, emphasizing their role in communicating vital informa- tion and regulations, transcending language barriers, and aiding drivers in navigating roads and avoiding potential dangers. In light of this significance, our study focuses on harnessing object detection technology, specifically ap- plied to traffic signs, with the goal of accident prevention and enhanced road safety. The dataset employed for our research is Road Sign Detection, and this paper has implemented the latest YOLOv8 versions and YOLO-NAS-l for object detection. Notably, this work achieved impressive mAP50 values, with YOLOv8m at 94.3%, YOLOv8x at 91.9%, YOLOv8l at 92%, YOLOv8s at 94.9%, and YOLOv8n at 95.3%. However, the best results were obtained by YOLO-NAS-l, with an outstanding mAP50 score of 95.72%. In addition to these individual results, this work conducted a comprehensive comparative study, demonstrating that our model leads to an 8% increase in performance over existing approaches. This paper is of great significance as it addresses a critical aspect of road safety and presents a cutting-edge solution that not only outperforms previous models but also sets a new standard for the industry. This research holds the potential to substantially reduce road accidents and enhance overall road safety, making it an invaluable contribution to the field of computer vision and its practical applications in the real world.

show abstract

Section: Yolov8smentioning

confidence: 99%

Traffic Sign Sensing: A Deep Learning approach for enhanced Road Safety

Gupta,

Mhala,

Mangal

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Finally, better experimental results were achieved. For example, to cope with dense fish populations and underwater plants that obscure them, Li et al [22] integrated an innovative module in Real-time Detection Transformer (RT-DETR) into YOLOv8 and applied repulsion loss；aiming at the largescale changes of different forms of traffic signs and the rapid speed of vehicles, Zhang et al [23] implemented multi-scale traffic sign detection based on YOLOv8 by introducing the attention module and RFB module and improving the loss function；in response to the blurriness of UAV-collected images and the large number of small target objects, Wang et al [24] introduced a small target detection structure (STC) and the global attention GAM into YOLOv8.…”

Section: Related Research Work a Object Detectionmentioning

confidence: 99%

YOLOv8n_BT: Research on Classroom Learning Behavior Recognition Algorithm Based on Improved YOLOv8n

Liu,

Jiang,

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Classroom learning behavior recognition can provide effective technical support for teaching and learning. However, in natural classroom teaching scenarios, classroom learning behaviors are often missed or falsely detected due to character occlusion and the small object. To tackle the above issues, this study proposed an improved classroom learning behavior recognition algorithm (YOLOv8n_BT) based on YOLOv8n. On the one hand, for the occlusion problem of classroom learning behaviors, this study incorporated the BRA into the Backbone to better capture feature information; on the other hand, for the small object problem of classroom learning behaviors for back-row-students, this study expanded a Tiny Object Detection Layer (TODL) to detect small targets better. Experiments show that the BRA and the TODL can significantly improve the model performance. The YOLOv8n_BT model, which incorporated both the BRA and the TODL into the YOLOv8n(baseline) model simultaneously, has the most significant performance improvement. Compared with the YOLOv8n(baseline), the YOLOv8n_BT model improved by 3.0%, 6.7%, 5.0%, 3.6%, and 9.0% on P, R, F1, mAP50, and mAP50-90, respectively. The detection performance of YOLOv8n_BT also outperforms other state-of-the-arts.

show abstract

“…Wang et al. ( Wang F et al., 2023 ) addressed the characteristics of small targets in drone images by embedding a small target detection structure (STC) in the Neck of YOLOv8, capturing comprehensive global and contextual information and incorporating a global attention module (GAM), which significantly improved performance but also increased the parameter count. Li et al.…”

Section: Introductionmentioning

confidence: 99%

Research on improved YOLOv8n based potato seedling detection in UAV remote sensing images

Wang,

Yang

et al. 2024

Front. Plant Sci.

View full text Add to dashboard Cite

IntroductionAccurate detection of potato seedlings is crucial for obtaining information on potato seedlings and ultimately increasing potato yield. This study aims to enhance the detection of potato seedlings in drone-captured images through a novel lightweight model.MethodsWe established a dataset of drone-captured images of potato seedlings and proposed the VBGS-YOLOv8n model, an improved version of YOLOv8n. This model employs a lighter VanillaNet as the backbone network in-stead of the original YOLOv8n model. To address the small target features of potato seedlings, we introduced a weighted bidirectional feature pyramid network to replace the path aggregation network, reducing information loss between network layers, facilitating rapid multi-scale feature fusion, and enhancing detection performance. Additionally, we incorporated GSConv and Slim-neck designs at the Neck section to balance accuracy while reducing model complexity. ResultsThe VBGS-YOLOv8n model, with 1,524,943 parameters and 4.2 billion FLOPs, achieves a precision of 97.1%, a mean average precision of 98.4%, and an inference time of 2.0ms. Comparative tests reveal that VBGS-YOLOv8n strikes a balance between detection accuracy, speed, and model efficiency compared to YOLOv8 and other mainstream networks. Specifically, compared to YOLOv8, the model parameters and FLOPs are reduced by 51.7% and 52.8% respectively, while precision and a mean average precision are improved by 1.4% and 0.8% respectively, and the inference time is reduced by 31.0%.DiscussionComparative tests with mainstream models, including YOLOv7, YOLOv5, RetinaNet, and QueryDet, demonstrate that VBGS-YOLOv8n outperforms these models in terms of detection accuracy, speed, and efficiency. The research highlights the effectiveness of VBGS-YOLOv8n in the efficient detection of potato seedlings in drone remote sensing images, providing a valuable reference for subsequent identification and deployment on mobile devices.

show abstract

UAV Target Detection Algorithm Based on Improved YOLOv8

Cited by 30 publications

References 31 publications

Traffic Sign Sensing: A Deep Learning approach for enhanced Road Safety

Traffic Sign Sensing: A Deep Learning approach for enhanced Road Safety

YOLOv8n_BT: Research on Classroom Learning Behavior Recognition Algorithm Based on Improved YOLOv8n

Research on improved YOLOv8n based potato seedling detection in UAV remote sensing images

Contact Info

Product

Resources

About