Date of Award
5-2024
Document Type
Project
Degree Name
Master of Science in Computer Science
Department
School of Computer Science and Engineering
First Reader/Committee Chair
Dr. Qingquan Sun
Abstract
Accidents pose a significant risk to both individual and property safety, requiring effective detection and response systems. This work introduces an accident detection system using a convolutional neural network (CNN), which provides an impressive accuracy of 86.40%. Trained on diverse data sets of images and videos from various online sources, the model exhibits complex accident detection and classification and is known for its prowess in image classification and visualization.
CNN ensures better accident detection in various scenarios and road conditions. This example shows its adaptability to a real-world accident scenario and enhances its effectiveness in detecting early events. A key contributor to this project was a real-time alert system that quickly notifies authorities when an accident is detected. The CNN algorithm captures high-resolution images, which are then sent to designated email addresses, facilitating coordinated responses and providing visual evidence for post-accident investigations.
Implementing accident detection systems shows a significant improvement in road safety, enabling faster and more accurate accident detection. Using email alerts and their integration into hybrid crash data systems helps improve both response time and road safety efforts and can save lives by reducing serious crashes. Future improvements will focus on improving accuracy, speed, and efficiency to further reduce the frequency and severity of accidents, ultimately saving lives and reducing their social impact.
Recommended Citation
Muddam, Yogesh Reddy, "Crash Detecting System Using Deep Learning" (2024). Electronic Theses, Projects, and Dissertations. 1959.
https://scholarworks.lib.csusb.edu/etd/1959