Mutasim Billah Bin Ahmad
ABSTRACT
To guarantee the enforcement of traffic rules, the identification of traffic rule violators is an exceptionally alluring yet difficult assignment to implement and the detection of the wrong-way movement of vehicles is one of them. In this paper, an appearance-based approach is proposed which detects the front and back side of the vehicles on a highway with the help of a deep convolutional neural network and decides whether a vehicle is moving along the wrong-way or not based on the user expectation to see the side of a vehicle on each side of the highway using a handcrafted region divider algorithm. The effectiveness of this strategy has been assessed on a primary data-set built on real-time traffic videos captured from several significantly busy highways of Dhaka Metropolitan City and proven quite productive with an accuracy of 96% on successful detection of wrong-way movement of vehicles.
- Eli Bendersky. The softmax function and its derivative. https://eli.thegreenplace.net/2016/the-softmax-function-and-its-derivative/, 2016. Last accessed 14 January 2020.Google Scholar
- Paras Dahal. Classification and loss evaluation - softmax and cross entropy loss. https://deepnotes.io/softmax-crossentropy. Last accessed 14 January 2020.Google Scholar
- Jifeng Dai, Yi Li, Kaiming He, and Jian Sun. R-fcn: Object detection via region-based fully convolutional networks. In Advances in neural information processing systems, pages 379--387, 2016.Google Scholar
- R. Girshick. Fast r-cnn. In 2015 IEEE International Conference on Computer Vision (ICCV), pages 1440--1448, Dec 2015.Google ScholarDigital Library
- Ross Girshick, Jeff Donahue, Trevor Darrell, and Jitendra Malik. Rich feature hierarchies for accurate object detection and semantic segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 580--587, 2014.Google ScholarDigital Library
- Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE transactions on pattern analysis and machine intelligence, 37(9):1904--1916, 2015.Google Scholar
- Jonathan Krause, Michael Stark, Jia Deng, and Li Fei-Fei. 3d object representations for fine-grained categorization. In Proceedings of the IEEE International Conference on Computer Vision Workshops, pages 554--561, 2013.Google ScholarDigital Library
- Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems, pages 1097--1105, 2012.Google ScholarDigital Library
- Wei Liu, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy, Scott Reed, Cheng-Yang Fu, and Alexander C Berg. Ssd: Single shot multibox detector. In European conference on computer vision, pages 21--37. Springer, 2016.Google ScholarCross Ref
- Gonçalo Monteiro, Miguel Ribeiro, Joao Marcos, and Jorge Batista. Wrongway drivers detection based on optical flow. In 2007 IEEE International Conference on Image Processing, volume 5, pages V--141. IEEE, 2007.Google Scholar
- Paula C Useche Murillo, Robinson Jiménez Moreno, and Javier O Pinzón Arenas. Comparison between cnn and haar classifiers for surgical instrumentation classification. Contemporary Engineering Sciences, 10(28):1351--1363, 2017.Google ScholarCross Ref
- Joseph Redmon, Santosh Divvala, Ross Girshick, and Ali Farhadi. You only look once: Unified, real-time object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 779--788, 2016.Google ScholarCross Ref
- Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. Faster r-cnn: Towards real-time object detection with region proposal networks. In Advances in neural information processing systems, pages 91--99, 2015.Google ScholarDigital Library
- Allach Samir, Ben Ahmed Mohamed, and Boudhir Anouar Abdelhakim. A new architecture based on convolutional neural networks (cnn) for assisting the driver in fog environment. In Proceedings of the 3rd International Conference on Smart City Applications, page 85. ACM, 2018.Google Scholar
- Kaijing Shi, Hong Bao, and Nan Ma. Forward vehicle detection based on incremental learning and fast r-cnn. In 2017 13th International Conference on Computational Intelligence and Security (CIS), pages 73--76. IEEE, 2017.Google ScholarCross Ref
- C Vishnu, Dinesh Singh, C Krishna Mohan, and Sobhan Babu. Detection of motorcyclists without helmet in videos using convolutional neural network. In 2017 International Joint Conference on Neural Networks (IJCNN), pages 3036--3041. IEEE, 2017.Google ScholarCross Ref
- Lixin Wang, Junguo Liao, and Chaoqian Xu. Vehicle detection based on drone images with the improved faster r-cnn. In Proceedings of the 2019 11th International Conference on Machine Learning and Computing, pages 466--471. ACM, 2019.Google ScholarDigital Library
Index Terms
- An Appearance-based Approach to Detect the Wrong-way Movement of Vehicles Using Deep Convolutional Neural Network
Recommendations
An intelligent traffic detection approach for vehicles on highway using pattern recognition and deep learning
AbstractIntelligent transportation system (ITS) is widely employed in dynamic traffic management to alleviate roadside congestion and increase traffic efficiency for solving the increasingly critical traffic congestion problems. With the advancement in ...
Deep Convolutional Neural Network to Detect J-UNIWARD
IH&MMSec '17: Proceedings of the 5th ACM Workshop on Information Hiding and Multimedia SecurityThis paper presents an empirical study on applying convolutional neural networks (CNNs) to detecting J-UNIWARD -- one of the most secure JPEG steganographic method. Experiments guiding the architectural design of the CNNs have been conducted on the JPEG ...
Improved YOLOv5l for vehicle detection: an application to estimating traffic density and identifying over speeding vehicles on highway scenes
AbstractVehicle detection and counting are getting progressively significant in highway administration due to the varying sizes of vehicles. This paper proposes a vision-based vehicle detection and counting framework. Initially, the COCO and BDD100K ...
Comments