A Fire and Smoke Detection Model Based on YOLOv8 Improvement DOI Open Access

Pengcheng Gao

International Journal of Advanced Computer Science and Applications, Journal Year: 2024, Volume and Issue: 15(3)

Published: Jan. 1, 2024

The warning of fire and smoke provides security for people's lives properties. utilization deep learning has been an active area research, especially the use target detection algorithms achieved significant results. For improving performance model in different scenarios, a high-precision lightweight improvement based on You Only Look Once (YOLO), is developed. It utilizes partial convolutions to reduce complexity model, add attention block acquire cross-space capability. In addition, neck network redesigned realize bidirectional feature fusion. Experiments show that it significantly improved results all metrics public Fire-Smoke dataset, size also widely reduced. Comparisons with other popular models under same conditions indicate best as well. order have more visual comparison detectability original heatmap experiments are established, which demonstrate characterized by less leakage rate focused attention.

Language: Английский

Revolutionizing Target Detection in Intelligent Traffic Systems: YOLOv8-SnakeVision DOI Open Access
Qi Liu, Yang Liu, Da Lin

et al.

Electronics, Journal Year: 2023, Volume and Issue: 12(24), P. 4970 - 4970

Published: Dec. 12, 2023

Intelligent traffic systems represent one of the crucial domains in today’s world, aiming to enhance management efficiency and road safety. However, current intelligent still face various challenges, particularly realm target detection. These challenges include adapting complex scenarios lack precise detection for multiple objects. To address these issues, we propose an innovative approach known as YOLOv8-SnakeVision. This method introduces Dynamic Snake Convolution, Context Aggregation Attention Mechanisms, Wise-IoU strategy within YOLOv8 framework performance. Convolution assists accurately capturing object shapes features, especially cases occlusion or overlap. The Mechanisms allow model better focus on critical image regions effectively integrate information, thus improving its ability recognize obscured targets, small objects, patterns. combines dynamic non-monotonic focusing mechanisms, more precisely regress bounding boxes, low-quality examples. We validate our BDD100K NEXET datasets. Experimental results demonstrate that YOLOv8-SnakeVision excels scenarios. It not only enhances but also strengthens targets. provides robust support development holds promise achieving further breakthroughs future applications.

Language: Английский

Citations

25
GC-YOLOv9: Innovative smart city traffic monitoring solution DOI Creative Commons
Ru An, Xiaochun Zhang, Maopeng Sun

et al.

Alexandria Engineering Journal, Journal Year: 2024, Volume and Issue: 106, P. 277 - 287

Published: July 13, 2024

Language: Английский

Citations

14
YOLOv10 to Its Genesis: A Decadal and Comprehensive Review of The You Only Look Once Series DOI Open Access
Ranjan Sapkota, Rizwan Qureshi, Marco Flores-Calero

et al.

Published: June 20, 2024

This review systematically examines the progression of You Only Look Once (YOLO) object detection algorithms from YOLOv1 to recently unveiled YOLOv10. Employing a reverse chronological analysis, this study advancements introduced by YOLO algorithms, beginning with YOLOv10 and progressing through YOLOv9, YOLOv8, subsequent versions explore each version's contributions enhancing speed, accuracy, computational efficiency in real-time detection. The highlights transformative impact across five critical application areas: automotive safety, healthcare, industrial manufacturing, surveillance, agriculture. By detailing incremental technological that iteration brought, not only chronicles evolution but also discusses challenges limitations observed earlier versions. signifies path towards integrating multimodal, context-aware, General Artificial Intelligence (AGI) systems for next decade, promising significant implications future developments AI-driven applications.

Language: Английский

Citations

12
Comparative Analysis of YOLOv8 and YOLOv10 in Vehicle Detection: Performance Metrics and Model Efficacy DOI Creative Commons

Athulya Sundaresan Geetha,

Mujadded Al Rabbani Alif,

Muhammad Hussain

et al.

Vehicles, Journal Year: 2024, Volume and Issue: 6(3), P. 1364 - 1382

Published: Aug. 10, 2024

Accurate vehicle detection is crucial for the advancement of intelligent transportation systems, including autonomous driving and traffic monitoring. This paper presents a comparative analysis two advanced deep learning models—YOLOv8 YOLOv10—focusing on their efficacy in across multiple classes such as bicycles, buses, cars, motorcycles, trucks. Using range performance metrics, precision, recall, F1 score, detailed confusion matrices, we evaluate characteristics each model.The findings reveal that YOLOv10 generally outperformed YOLOv8, particularly detecting smaller more complex vehicles like bicycles trucks, which can be attributed to its architectural enhancements. Conversely, YOLOv8 showed slight advantage car detection, underscoring subtle differences feature processing between models. The buses motorcycles was comparable, indicating robust features both YOLO versions. research contributes field by delineating strengths limitations these models providing insights into practical applications real-world scenarios. It enhances understanding how different architectures optimized specific tasks, thus supporting development efficient precise systems.

Language: Английский

Citations

8
LANE AND TRAFFIC SIGN DETECTION FOR AUTONOMOUS VEHICLES: ADDRESSING CHALLENGES ON INDIAN ROAD CONDITIONS DOI Creative Commons

H. S. Gowri Yaamini,

K M Swathi,

N Manohar

et al.

MethodsX, Journal Year: 2025, Volume and Issue: 14, P. 103178 - 103178

Published: Jan. 20, 2025

Accurate and precise detection of lanes traffic signs is predominant for the safety efficiency autonomous vehicles these two significant tasks should be addressed to handle Indian conditions. There are several state-of-art You Only Live Once (YOLO) models trained on benchmark datasets which fails cater challenges roads. To address issues, need with a wide variety data samples perform better in India. YOLOv8 algorithm has its but gives precision results nano variant widely used as it computationally less complex comparatively. Through rigorous evaluations diverseness datasets, proposed YOLOv8n transfer learning exhibits remarkable performance mean Average Precision (mAP) 90.6 % inference speed 117 frames per second (fps) lane whereas, notable mAP 81.3 sign model processing 56 fps.•YOLOv8n Transfer Learning approach by adjusting architecture diverse Urban, Suburban, Highway scenarios.•Dataset 22,400 images normal scenarios include crude weathering roads, conditions, tropical weather partially occluded erased lanes, signs.•The frame wise inference.

Language: Английский

Citations

1
Real-time detection of plastic part surface defects using deep learning- based object detection model DOI
Miraç Tuba Çelik, Seher Arslankaya, Aytaç Yıldız

et al.

Measurement, Journal Year: 2024, Volume and Issue: 235, P. 114975 - 114975

Published: May 24, 2024

Language: Английский

Citations

8
YOLOv8-Lite: A Lightweight Object Detection Model for Real-time Autonomous Driving Systems DOI
Yang Ming, Xiangyu Fan

Published: April 7, 2024

With the rapid development of autonomous driving technology, demand for real-time and efficient object detection systems has been increasing to ensure vehicles can accurately perceive respond surrounding environment. Traditional models often suffer from issues such as large parameter sizes high computational resource consumption, limiting their applicability on edge devices. To address this issue, we propose a lightweight model called YOLOv8-Lite, based YOLOv8 framework, improved through various enhancements including adoption FastDet structure, TFPN pyramid CBAM attention mechanism. These improvements effectively enhance performance efficiency model. Experimental results demonstrate significant our NEXET KITTI datasets. Compared traditional methods, exhibits higher accuracy robustness in tasks, better addressing challenges fields driving, contributing advancement intelligent transportation systems.

Language: Английский

Citations

8
An End-to-End Platform for Managing Third-Party Risks in Oil Pipelines DOI Creative Commons
Edmundo Casas, Leo Ramos, Cristian Romero

et al.

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 77831 - 77851

Published: Jan. 1, 2024

Ensuring the safe and reliable operation of underground oil pipelines is crucial to prevent environmental disasters maintain uninterrupted energy supply. Yet, this vast network faces threats from third-party activities, natural disasters, aging infrastructure, posing risks catastrophic consequences if left unaddressed. In response need, paper presents a computer vision system for detecting (vehicular movement) near pipelines. Our primary objective showcase practical application cutting-edge models in real-world operational environments. For this, we construct dataset comprising 1,003 aerial images, covering seven classes vehicles commonly encountered pipelines, including trucks, forklifts, machinery, pickups, tractors, vehicles, buses. This serves as foundation training hyperparameter optimization YOLOv8x-based detection model, used work. The optimized model exhibits strong performance across precision, recall, F1-score, mean average precision metrics compared baseline model. Additionally, graphical tests illustrated that demonstrates higher confidence scores reduction false positives. addition, platform has been developed seamlessly integrate offers range functionalities, enabling users access alert history, prioritize alerts, track actions taken on each alert, visualize alerts geographically, receive notifications identified risks, generate detailed reports comprehensive analysis decision-making.

Language: Английский

Citations

5
Enhancing autonomous driving safety: A robust traffic sign detection and recognition model TSD-YOLO DOI
Ruixin Zhao,

Sai Hong Tang,

Jiazheng Shen

et al.

Signal Processing, Journal Year: 2024, Volume and Issue: 225, P. 109619 - 109619

Published: July 14, 2024

Language: Английский

Citations

5
YOLO-Fusion and Internet of Things: Advancing object detection in smart transportation DOI Creative Commons
Jun Tang,

Caixian Ye,

Xianlai Zhou

et al.

Alexandria Engineering Journal, Journal Year: 2024, Volume and Issue: 107, P. 1 - 12

Published: Sept. 17, 2024

Language: Английский

Citations

5