• Hanumanthavajjala Bharat Chandra
• K. Sree Lakshmi Sravya
• Bheesetti Eshitha
• Boyidi Sai Ram
• Lenin Sai Priya

According to records, 57% of accidents in India occur on roads. One of the main reasons behind accidents is drivers that gets distracted by various tasks. Chances are getting more for the number of accidents to get increased due to the development of new mobile technologies, which can negatively affect the attention level of the driver. According to the reports from The National Highway Traffic Safety Administration (NHTSA), over 25% of police reported crashes involved inattentive drivers. This finding is not surprising since it is estimated that about 30% of the time that drivers are in a moving vehicle, they are engaged in secondary tasks. Detecting driver's distraction tasks is an important research problem to prevent accidents and increase the security on the roads. Commonly performed secondary tasks can deviate the attention of the drivers from the primary driving task. These in cab demands can produce visual, cognitive, auditory, psychological and physical distractions. Therefore, it is very important to understand the effect induced by different secondary tasks on the drivers. A key step in the analysis is to define reference metrics or criteria to assess the attention level of the driver. These reference labels can be used as ground truth to train to detect distracted drivers Developing feedback systems that can detect the attention level of the driver plays a key role in preventing accidents by alerting the driver about possible hazardous situations. Monitoring driver distraction is an important research topic, and various forms of technology are available for drivers that can interfere with key driving tasks. An important issue is how to define a reference label that can be used as a ground truth for training and detecting distracted drivers. The answer to this question is not easy, as drivers are affected by visual, cognitive, auditory, psychological and physical distractions. This paper examines three different approaches that characterize driver distraction. Perceptual assessment by an external evaluator, self-assessment from a post-driving questionnaire, and analysis of the differences observed between multimodal characteristics and standard patterns. The driver usually feels distracted from the road while performing various tasks that can lead to traffic accidents. This document proposes a solution to detect driver distraction and generate reports that provide insight into driver performance. We use different models such as Convolutional Neural Networks (CNN), namely: CNN, VGG16 for the classification of distracted drivers. The deep learning library used for this is TensorFlow. Our best result is 94% accuracy on the validation set and 98% accuracy on the test data.

Classification, image segmentation, accuracy, over fitting, dashboard, convolution neural network.

"Analysis On Driver Distraction Detection And Performance Monitoring System", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 5, page no.j101-j108, May-2022, Available :http://www.jetir.org/papers/JETIR2205A16.pdf

"Analysis On Driver Distraction Detection And Performance Monitoring System", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 5, page no. ppj101-j108, May-2022, Available at : http://www.jetir.org/papers/JETIR2205A16.pdf