Towards robust autonomous driving systems through adversarial test set generation

Ünal, Devrim; Çatak, Ferhat Özgür; Houkan, Mohammad Talal; Mudassir, Mohammed; Hammoudeh, Mohammad

doi:10.1016/j.isatra.2022.11.007

Cited by 9 publications

(4 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The NEXET dataset is an emerging dataset of urban traffic scenes, providing highresolution video sequences and detailed object annotations [32]. It includes various traffic scenarios such as urban streets, highways, etc., encompassing vehicles, pedestrians, bicycles, and other traffic participants.…”

Section: Datasetmentioning

confidence: 99%

YOLOv8-BCC: Lightweight Object Detection Model Boosts Urban Traffic Safety

Jun,

Lai,

et al. 2024

Preprint

View full text Add to dashboard Cite

With the rapid development of urbanization, the role of urban transportation systems has become increasingly prominent. However, traditional methods of traffic management are struggling to cope with the growing demands of traffic and the complexity of urban environments. In response to this situation, we propose the YOLOv8-BCC algorithm to address existing shortcomings. Leveraging advanced technologies such as CFNet, CBAM attention modules, and BIFPN structure, our algorithm aims to enhance the accuracy, real-time performance, and adaptability of urban traffic intelligent detection systems. Experimental results demonstrate significant improvements in detection accuracy and real-time performance compared to traditional methods. The introduction of the YOLOv8-BCC algorithm provides a robust solution for enhancing urban traffic safety and intelligent management.

show abstract

Section: Datasetmentioning

confidence: 99%

YOLOv8-BCC: Lightweight Object Detection Model Boosts Urban Traffic Safety

Jun,

Lai,

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…The NEXET dataset is released by the Nexar company, mainly for training and validating autonomous driving algorithms [45]. It comprises 500,000 images for vehicle detection, with five categories.…”

Section: Datasetmentioning

confidence: 99%

Revolutionizing Target Detection in Intelligent Traffic Systems: YOLOv8-SnakeVision

Liu,

Lin

2023

Electronics

View full text Add to dashboard Cite

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

show abstract

“…The pressure variations given to the electric fuel pump are 2.7bar, 2.94bar, 3.5bar and 3.8bar. there is an influence of changes in the value of power, engine torque, fuel efficiency and exhaust emissions with the overall result being that the vehicle's ideal pressure for power, torque and gas emissions and meets the specified threshold for injection motorbikes is found at a pressure of 2.94 bar -3.5 bar use at high engine speed [16], [17]. There is an influence on fuel pressure on power and torque.…”

Section: Introductionmentioning

confidence: 99%

The Effect of Fuel Pump Pressure and Number of Injector Holes on 150cc Matic Motorcycle Performance

Santoso,

Yulianto,

Yudiyanto

et al. 2024

ajse

View full text Add to dashboard Cite

This study aims to evaluate the effects of increasing fuel pump pressure and varying the number of holes in the injector on engine performance. The fuel system in the engine has evolved from carburettor to injection system to improve the efficiency of fuel usage. In this study, the fuel pump pressure was increased to three levels, namely 2.5 bar, 3 bar, and 3.5 bar. In addition, variations in the number of holes in the injector were also tested using 3-hole, 6-hole, and 8-hole injectors. Engine performance was evaluated based on the power and torque produced. The research method used is experimental with power and torque measurements as engine performance data. The results showed that increasing fuel pump pressure and varying the number of holes in the injector had a significant effect on engine performance. Increasing the fuel pump pressure to 3.5 bar results in an increase in engine power and torque. The best power test results were obtained at a fuel pump pressure of 3 bar with a combination of 6-hole injectors, producing a maximum power of 11.63 HP at 6000 rpm engine speed. While the best torque test results were obtained at a fuel pump pressure of 3.5 bar with a combination of 3-hole injectors, producing a maximum torque of 43.10 Nm at 3000 rpm. The variation in the number of holes in the injector shows that the use of injectors with more holes tends to increase engine power and torque. Keywords: Engine Performance, Fuel Pump Pressure, Fuel Efficiency Injector Holes, Injection System

show abstract

Towards robust autonomous driving systems through adversarial test set generation

Cited by 9 publications

References 22 publications

YOLOv8-BCC: Lightweight Object Detection Model Boosts Urban Traffic Safety

YOLOv8-BCC: Lightweight Object Detection Model Boosts Urban Traffic Safety

Revolutionizing Target Detection in Intelligent Traffic Systems: YOLOv8-SnakeVision

The Effect of Fuel Pump Pressure and Number of Injector Holes on 150cc Matic Motorcycle Performance

Contact Info

Product

Resources

About