Fast and accurate object detector for autonomous driving based on improved YOLOv5

Jia, Xiang; Tong, Ying; Qiao, Hongming; Li, Man; Tong, Jiangang; Liang, Baoling

doi:10.1038/s41598-023-36868-w

Cited by 26 publications

(13 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, as a fundamental component of autonomous driving systems, environmental perception 6 enables vehicles to comprehend their surroundings and make intelligent decisions based on this perception. Autonomous Vehicles (AVs) make wise decisions about speed, direction, and safety by recognizing pedestrians, other vehicles, and traffic signs.…”

Section: Advances Toward Technology-enabled Transportmentioning

confidence: 99%

Advanced transport systems: the future is sustainable and technology-enabled

Cao,

Derrible,

Le Pira

et al. 2024

Sci Rep

View full text Add to dashboard Cite

Transport has always played a major role in shaping society. By enabling or restricting the movement of people and goods, the presence or absence of transport services and infrastructure has historically been determining for cultures to connect, for knowledge to be shared, and for societies to evolve and prosper, or, in contrast, for societies to decay and fail. Since the beginning of the twenty-first century, transport has been going through a revolution worldwide. One of the primary goals for the transport sector is clear: it needs to be decarbonized and become more sustainable. At the same time, technological advances are shaping the transport sector toward smart services and societies. The Special Collection showcases some of the latest advances in research towards sustainable and technology-enabled transport.

show abstract

Section: Advances Toward Technology-enabled Transportmentioning

confidence: 99%

Advanced transport systems: the future is sustainable and technology-enabled

Cao,

Derrible,

Le Pira

et al. 2024

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Jia, X. et al present a novel object detection algorithm for autonomous driving based on improved YOLOv5 in [24]. The algorithm enhances the accuracy and speed of the model by using structural re-parameterization, neural architecture search, small object detection layer, and coordinate attention mechanism.…”

Section: Related Workmentioning

confidence: 99%

Enhancing Object Detection in Self-Driving Cars Using a Hybrid Approach

Khan

Lee²,

Lim

2023

Electronics

View full text Add to dashboard Cite

Recent advancements in artificial intelligence (AI) have greatly improved the object detection capabilities of autonomous vehicles, especially using convolutional neural networks (CNNs). However, achieving high levels of accuracy and speed simultaneously in vehicular environments remains a challenge. Therefore, this paper proposes a hybrid approach that incorporates the features of two state-of-the-art object detection models: You Only Look Once (YOLO) and Faster Region CNN (Faster R-CNN). The proposed hybrid approach combines the detection and boundary box selection capabilities of YOLO with the region of interest (RoI) pooling from Faster R-CNN, resulting in improved segmentation and classification accuracy. Furthermore, we skip the Region Proposal Network (RPN) from the Faster R-CNN architecture to optimize processing time. The hybrid model is trained on a local dataset of 10,000 labeled traffic images collected during driving scenarios, further enhancing its accuracy. The results demonstrate that our proposed hybrid approach outperforms existing state-of-the-art models, providing both high accuracy and practical real-time object detection for autonomous vehicles. It is observed that the proposed hybrid model achieves a significant increase in accuracy, with improvements ranging from 5 to 7 percent compared to the standalone YOLO models. The findings of this research have practical implications for the integration of AI technologies in autonomous driving systems.

show abstract

“…The YOLO algorithm and its variants, including YOLOv2 14 , YOLOv3 15 , YOLOv4 16 and other YOLO-based variants 18,19 , have gained significant popularity. YOLOv2 removed the constraint that a grid cell can only anticipate a single object and predicted offsets of the desired center point relative to the grid.…”

Section: Anchor-based Object Detectorsmentioning

confidence: 99%

ACP-YOLO: Asymmetric Center Point Bounding Box Regression Strategy and Angle Loss-based YOLO for Object Detection

Wang

Kong

Zhang

et al. 2023

Preprint

View full text Add to dashboard Cite

The YOLOv4 approach has gained significant popularity in industrial object detection due to its impressive real-time processing speed and relatively favorable accuracy. However, it has been observed that YOLOv4 faces challenges in accurately detecting small objects. Its bounding box regression strategy is rigid and fails to effectively leverage the asymmetric characteristics of objects, limiting its ability to enhance object detection accuracy. This paper proposes an enhanced version of YOLOv4 called ACP-YOLO (asymmetric center point bounding box regression-based YOLOv4). The ACP-YOLO approach introduces two customized modules: an asymmetric center point bounding box regression strategy and an angle-loss function. These modules contribute to improving the algorithm's detection accuracy by enabling more precise localization of objects. Additionally, ACP-YOLO adopts an improved feature fusion technique, which facilitates enhanced information flow within the network, thereby further enhancing accuracy performance. Experimental evaluations conducted on the COCO2017 dataset demonstrate the effectiveness of the proposed method. ACP-YOLO achieves an average precision of 45.6\%, surpassing both YOLOv4 and certain previously developed one-stage detectors. The utilization of an asymmetric center point bounding box regression strategy and the incorporation of robust feature fusion contribute to superior object detection accuracy in ACP-YOLO compared to YOLOv4.

show abstract

Fast and accurate object detector for autonomous driving based on improved YOLOv5

Cited by 26 publications

References 33 publications

Advanced transport systems: the future is sustainable and technology-enabled

Advanced transport systems: the future is sustainable and technology-enabled

Enhancing Object Detection in Self-Driving Cars Using a Hybrid Approach

ACP-YOLO: Asymmetric Center Point Bounding Box Regression Strategy and Angle Loss-based YOLO for Object Detection

Contact Info

Product

Resources

About