A Fast and Accurate Real-Time Vehicle Detection Method Using Deep Learning for Unconstrained Environments

Farid, Annam; Hussain, Fawad; Khan, Khalid Amin; Shahzad, Mohsin; Khan, Uzair; Mahmood, Zahid

doi:10.3390/app13053059

Cited by 48 publications

(27 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Here 43,52 have lowest ranks. In rain situation our method produces best results followed by 57,45,48,50,51 . Here 52 has lowest rank.…”

Section: Evaluation Criteriamentioning

confidence: 89%

Smart Traffic Management of Vehicles using Faster R-CNN based Deep Learning Method

Chaudhuri

2024

Preprint

View full text Add to dashboard Cite

With constant growth of civilization and modernization of cities all across the world since past few centuries smart traffic management of vehicles is one of the most sorted after problem by research community. Smart traffic management basically involves segmentation of vehicles, estimation of traffic density and tracking of vehicles. The vehicle segmentation from videos helps realization of niche applications such as monitoring of speed and estimation of traffic. When occlusions, background with clutters and traffic with density variations, this problem becomes more intractable in nature. Keeping this motivation in this research work, we investigate Faster R-CNN based deep learning method towards segmentation of vehicles. This problem is addressed in four steps viz minimization with adaptive background model, Faster R-CNN based subnet operation, Faster R-CNN initial refinement and result optimization with extended topological active nets. The computational framework uses adaptive background modeling. It also addresses shadow and illumination issues. Higher segmentation accuracy is achieved through topological active net deformable models. The topological and extended topological active nets help to achieve stated deformations. Mesh deformation is achieved with minimization of energy. The segmentation accuracy is improved with modified version of extended topological active net. The experimental results demonstrate superiority of this framework.

show abstract

“…Here 43,52 have lowest ranks. In rain situation our method produces best results followed by 57,45,48,50,51 . Here 52 has lowest rank.…”

Section: Evaluation Criteriamentioning

confidence: 89%

Smart Traffic Management of Vehicles using Faster R-CNN based Deep Learning Method

Chaudhuri

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Faris et al [ 115 ] proposed a Yolo-v5 architecture vehicle detector using the techniques of transfer learning on publicly available datasets, namely, PKU, COCO, and DAWN. The experimental result showed that the proposed model achieved a state-of-the-art in the detection of various vehicles.…”

Section: Application Of Dcnn For Vehicle Detection and Classificationmentioning

confidence: 99%

Deep Learning Techniques for Vehicle Detection and Classification from Images/Videos: A Survey

Berwo

Khan

Fang

et al. 2023

Sensors

View full text Add to dashboard Cite

Detecting and classifying vehicles as objects from images and videos is challenging in appearance-based representation, yet plays a significant role in the substantial real-time applications of Intelligent Transportation Systems (ITSs). The rapid development of Deep Learning (DL) has resulted in the computer-vision community demanding efficient, robust, and outstanding services to be built in various fields. This paper covers a wide range of vehicle detection and classification approaches and the application of these in estimating traffic density, real-time targets, toll management and other areas using DL architectures. Moreover, the paper also presents a detailed analysis of DL techniques, benchmark datasets, and preliminaries. A survey of some vital detection and classification applications, namely, vehicle detection and classification and performance, is conducted, with a detailed investigation of the challenges faced. The paper also addresses the promising technological advancements of the last few years.

show abstract

“…WANG et al [8] proposed the YOLOv5-NAM algorithm, which added the NAM attention module and proposed methods for tracking small target vehicles, embedding the feature extraction process into the joint training of the prediction head. Moreover, Farid et al [9] enhanced the accuracy of vehicle detection by modifying YOLO weights and utilizing transfer learning. Nitika et al [10] employed a region-based convolutional neural network to detect moving vehicles both during the day and at night, optimizing the detection performance under different weather conditions.…”

Section: Introductionmentioning

confidence: 99%

SSB-YOLO: A vehicle object detection algorithm based on improved YOLOv8

Wang,

Ren

2023

Preprint

View full text Add to dashboard Cite

In the field of computer vision, vehicle object detection has been a topic of significant and complex interest. With the rise of intelligent transportation systems and autonomous driving technology, the importance of vehicle object detection continues to be highlighted. Given the current issues of low precision, high miss rate, and poor robustness in existing algorithms, this study introduces an improved vehicle detection algorithm, SSB-YOLO, based on the YOLOv8 model. The SSB-YOLO algorithm integrates the Shuffle Attention mechanism to filter out unimportant factors and enhance model performance; it also incorporates the spatial and channel reconstruction convolution mechanism to reduce spatial and channel redundancy between features in convolutional neural networks. Furthermore, a new and better algorithm based on Wise-IoU optimization is proposed, which yields superior bounding box regression performance throughout the training period. The model demonstrated improved detection accuracy and reduced computational cost. The experimental results indicate that, compared to the YOLOv8n model, SSB-YOLO achieves a 1.6% increase in mAP@50. This approach outperforms other object detection algorithms, enhancing the overall system's robustness and accuracy and thereby providing higher precision in the field of vehicle detection.

show abstract

A Fast and Accurate Real-Time Vehicle Detection Method Using Deep Learning for Unconstrained Environments

Cited by 48 publications

References 41 publications

Smart Traffic Management of Vehicles using Faster R-CNN based Deep Learning Method

Smart Traffic Management of Vehicles using Faster R-CNN based Deep Learning Method

Deep Learning Techniques for Vehicle Detection and Classification from Images/Videos: A Survey

SSB-YOLO: A vehicle object detection algorithm based on improved YOLOv8

Contact Info

Product

Resources

About