Abstract
The proposed method comprises a computer vision-based system highly applicable in the detection of a possible accident while driving. A stereo depth camera is placed in front of the vehicle at a point through which all crucial viewing angles are captured. The camera will be covering a viewing angle of 180°. This idea proposes an efficient framework for accurate object detection using CNN along with an object tracking algorithm. This system will determine the probability of an accident based on the three parameters, which are: object approaching towards the line of movement, relative distance between the object and vehicle, and relative speed of the object with respect to the vehicle. It will provide a reliable technique to attain an efficient rate of detection with less erroneous indication of an accident. Since it covers 180°, it can accurately detect any object/vehicle coming from either side. By judging the speed of the vehicle and the trajectory of the object, the system will calculate the expected time of collision and in order to avoid the impact, an automatic braking mechanism will take place to cautiously reduce the speed of the vehicle in a calculated manner. In conclusion, this computer vision-based system will be a game-changer in accident detection and will make driving safer, easier, and more efficient.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Road Accidents per Annum Worldwide. https://www.who.int/news-room/fact-sheets/detail/road-traffic-injuries#:~:text=Approximately%201.35%20million%20people%20die,of%20their%20gross%20domestic%20product
Joukhadar, A., Issa, H., Kalaji, Y.: Design and implementation of auto car driving system with collision avoidance. Cogent Eng 5(1), 1485458 (2018). https://doi.org/10.1080/23311916.2018.1485458
Detection System Available at: Murugan, S., Bose, N (2013) Automatic braking system assisted by image & video processing for pedestrian and vehicle detection using matlab. Int. J. Inf. Technol. Comput. Sci. 2, 361– 369
Saito, T., Okubo, T., Takahashi, N.: Robust and accurate object velocity detection by stereo camera for autonomous driving. In: 2020 IEEE Intelligent Vehicles Symposium (IV), pp. 1242–1248 (2020). https://doi.org/10.1109/IV47402.2020.9304742. http://www.ncbi.nlm.nih.gov
Yang, L., Li, M., Song, X., Xiong, Z., Hou, C., Qu, B.: Vehicle speed measurement based on binocular stereovision system. IEEE Access, 1–1 (2019). https://doi.org/10.1109/access.2019.2932120
Tourani, A., Shahbahrami, A., Akoushideh, A., Khazaee, S., Suen. C.Y.: Motion-based vehicle speed measurement for intelligent transportation systems. Int. J. Image, Graphics Signal Process 11(4), 2019
To find more information on parallax visit the wikipedia page at https://en.wikipedia.org/wiki/Parallax
Autonomous Braking System. https://in.mathworks.com/help/driving/ug/autonomous-emergency-braking-with-sensor-fusion.html
Simulation of software in game. https://pythonprogramming.net/detecting-distances-self-driving-car/
Edge Computing. Kim, K., Hong, Y.: Autonomous network traffic control system based on intelligent edge computing. In: 2019 21st International Conference on Advanced Communication Technology (ICACT), pp. 164–167 (2019). https://doi.org/10.23919/ICACT.2019.8701939
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Singh, T., Sheikh, F., Sharma, A., Pandya, R., Singh, A. (2022). A Smart Driver Assistance System for Accident Prevention. In: Chen, J.IZ., Wang, H., Du, KL., Suma, V. (eds) Machine Learning and Autonomous Systems. Smart Innovation, Systems and Technologies, vol 269. Springer, Singapore. https://doi.org/10.1007/978-981-16-7996-4_18
Download citation
DOI: https://doi.org/10.1007/978-981-16-7996-4_18
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-7995-7
Online ISBN: 978-981-16-7996-4
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)