Papers › In-Car driver response classification using Deep Learning (CNN) based Computer Vision
In-Car driver response classification using Deep Learning (CNN) based Computer Vision
Japesh Methuku
The number of vehicle accidents increase every year globally. Considering the advancements in technology, it is possible to assess the causes of these accidents and mitigate the fatalities. Driver’s behavior and responses during the travel are crucial for analysis and in this paper, I have discussed how a deep learning system can be used to classify the responses of in-car driver and create an alert system. This paper is a brief description of the architecture of Convolutional Neural Network (CNN) used and the analysis of results obtained. The deep learning system was designed using transfer learning with ResNet50 and the model was able to achieve an accuracy of 89.71%. The model was evaluated on a video of real-world driving environment and key conclusions were drawn to support the research. The scope of the research beyond the academics and the importance in real-world application has been discussed in this paper.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
No leaderboard rows for this paper in the archive.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections