Motorcycle is a very popular mode of transportation in almost every country. However, there is a high risk involved because of less protection. To reduce the involved risk, it is highly desirable for bike-riders to use helmet. Observing the usefulness of helmet, Governments have made it a punishable offense to ride a motorcycle without a helmet. The manual strategies to catch these violators have several drawbacks such as interupt traffic flow, unpleasent weather conditions for police personel, etc.
Figure: Manual checking by the traffic police personals in hot sun on the road. [Sources: Hindustan Times]
Figure: Young men riding motorbikes without helmets during raining in the absence of police personel. [Sources: The Logical Indians]
Existing video surveillance based methods are passive and require significant human assistance. In general, such systems are infeasible due to involvement of humans, whose efficiency decreases over long duration. Automation of this process is highly desirable for reliable and robust monitoring of these violations as well as it also significantly reduces the amount of human resources needed. Also, all major cities accross the world are adopting systems involving surveillance cameras at public places. So, the solution for detecting violators using the existing infrastructure is also cost-effective.
However, the unavailability of benchmark dataset of real traffic videos is the major bottleneck in doing research. We collected a dataset of real sparse traffic videos to start the research on this topic from the surveillance network at Indian Institute of Technology Hyderabad, India (IITH) campus. It is a two-hour surveillance video data collected at 30 frames per second. Figures present sample frames from the collected dataset.
You can download the datasets from the following link
https://www.iith.ac.in/vigil/resources.html
Or write to cs14resch1100 [at] iith [dot] ac [dot] in
Please cite the below paper if you used this dataset.
Dinesh Singh, C. Vishnu, and C. Krishna Mohan, "Visual Big Data Analytics for Traffic Monitoring in Smart City," in Procedings of the IEEE International Conference on Machine Learning and Applications (ICMLA), Dec 2016
@inproceedings{Singh2016icmla,
Author = {Dinesh Singh and C. Vishnu and C. Krishna Mohan},
Title = {Visual Big Data Analytics for Traffic Monitoring in Smart City},
Booktitle = {{IEEE International Conference on Machine Learning and Applications (ICMLA)}}
Address = {Anaheim, CA, USA},
Month = {December 18--20},
Pages = {886--891},
Year = {2016},
DOI = {10.1109/ICMLA.2016.0159}
}
C. Vishnu, Dinesh Singh, C. Krishna Mohan and Ch. Sobhan Babu, "Detection of Motorcyclists without Helmet in Videos using Convolutional Neural Network," in Procedings of the International Joint Conference on Neural Networks (IJCNN), May 2017
Bibtex
@inproceedings{Singh2016tits,
Author = {C. Vishnu and Dinesh Singh and C. Krishna Mohan and Sobhan Babu},
Title = {{Detection of motorcyclists without helmet in videos using convolutional neural network}},
Booktitle = {{2017 International Joint Conference on Neural Networks, (IJCNN)}},
Address = {Anchorage, AK, USA}
Month = {May 14--19}
Pages = {3036--3041},
Year = {2017},
DOI = {10.1109/IJCNN.2017.7966233}
}
Kunal Dahiya, Dinesh Singh, and C. Krishna Mohan, "Automatic Detection of Bike-riders without Helmet using Surveillance Videos in Real-time," in Procedings of the International Joint Conference on Neural Networks (IJCNN), Jul 2016.
Bibtex
@inproceedings{Singh2016tits,
Title = {{Automatic Detection of Bike-riders without Helmet using Surveillance Videos in Real-time}},
Author = {Kunal Dahiya, Dinesh Singh, and C. Krishna Mohan},
Journal = {{International Joint Conference on Neural Networks (IJCNN)}},
Address = {Vancouver, BC, Canada},
Month = {July 24--29},
Pages = {3046--3051},
Year = {2016},
DOI = {10.1109/IJCNN.2016.7727586}
}