Main Article Content
High number in usage of Motorcycles has led to increase in road related accidents and injuries. The major reasons for accidents is the motorcyclist not wearing a helmet. One of the method is by traffic police manually monitoring motorcyclists at road junctions for not wearing helmet or through the CCTV footage video, which requires human efforts to detect motorcyclists without helmet. This paper presents an automated machine system for detecting motorcyclists not wearing helmet from video. The system extracts moving objects by background subtraction and classifies them as a motorcycle or other moving objects based on features extracted. Then for classified motorcyclist, head portion is located and it is classified as helmet or non-helmet. The system uses Convolutional Neural Networks trained using transfer learning on top of pre-trained model and combined with computer vision for classification which has helped in achieving greater accuracy. Our results on traffic videos show an accuracy of 98.56% on detection of motorcyclists without helmet.
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
- “4 people die every hour in India because they do not wear a helmet,” https://www.indiatoday.in/diu/story/two-wheeler-death-road-accidents-helmets-states-india-1602794-2019-09-24.
- “Motor Vehicles Bill: Complete list of fines you will pay for traffic violations,”https://economictimes.indiatimes.com/news/economy/policy/new-motor-vehicles-bill-2019-heres-the-complete-list-of-fines-you-will-pay-for-traffic-rule-violations/articleshow/70471748.cms?from=mdr.
- J. Chiverton, "Helmet presence classification with motorcycle detection and tracking," in IET Intelligent Transport Systems, vol. 6, no. 3, pp. 259-269, September 2012.
- R. Waranusast, N. Bundon, V. Timtong, C. Tangnoi and P. Pattanathaburt, "Machine vision techniques for motorcycle safety helmet detection," 2013 28th International Conference on Image and Vision Computing New Zealand (IVCNZ 2013), Wellington, 2013, pp. 35-40
- R. R. V. e. Silva, K. R. T. Aires and R. d. M. S. Veras, "Helmet Detection on Motorcyclists Using Image Descriptors and Classifiers," 2014 27th SIBGRAPI Conference on Graphics, Patterns and Images, Rio de Janeiro, 2014, pp. 141-148
- K. Dahiya, D. Singh and C. K. Mohan, "Automatic detection of bike-riders without helmet using surveillance videos in real-time," 2016 International Joint Conference on Neural Networks (IJCNN), Vancouver, BC, 2016, pp. 3046-3051.
- Contractorr, Dhwani & Pathak, Ketki & Sharma, Sonali & Bhagat, Shreya & Sharma, Tanu, “Cascade Classifier based Helmet Detection using OpenCV in Image Processing,” National Conference on Recent Trends in Computer and Communication Technology (RTCCT 2016) (ISBN: 978-93-5258-824-4), May 2016.
- Li, J., Liu, H., Wang, T., Jiang, M., Wang, S., Li, K., & Zhao, X. (2017, February). Safety helmet wearing detection based on image processing and machine learning. In Advanced Computational Intelligence (ICACI), 2017 Ninth International Conference pp. 201-205.
- C. Vishnu, D. Singh, C. K. Mohan and S. Babu, "Detection of motorcyclists without helmet in videos using convolutional neural network," 2017 International Joint Conference on Neural Networks (IJCNN), Anchorage, AK, 2017, pp. 3036-304.
- “Deep Learning with OpenCV,” Adrian Rosebrock. https://www.pyimagesearch.com/2017/08/21/deeplearning-with-opencv, 2017.(online)
- “Fine-tuning Convolutional Neural Network on own data using Keras Tensorflow,” http://cv-tricks.com/keras/finetuning-tensorflow.(online)
- “MobileNet SSD Object Detection using OpenCV 3.4.1 DNN module,” https://ebenezertechs.com/mobilenet-ssd-using-opencv-3-4-1-deep-learning-module-python.(online)
- “COCO DATASET,” http://cocodataset.org/#download.(online)
- “Basic motion detection and tracking with Python and OpenCV,” https://www.pyimagesearch.com/2015/05/25/basicmotion-detection-and-tracking-with-python-and-opencv,2015.(online)