About the research
The goal of this project was to detect wrong-way driving using only closed circuit television (CCTV) camera data on a real-time basis with no need to manually pre-calibrate the camera. Based on this goal, a deep learning model was implemented to detect and track vehicles, and a machine learning model was trained to classify the road into different directions and extract vehicle properties for further comparisons.
The objective of this project was to detect wrong-way driving on Iowa highways in 10 different locations. When wrong-way driving was detected, the system would record the violation scene and send the video file via email to any recipient in charge of appropriate reactions for the event.
This report covers the background and methodology for the work and the models and modules implemented to compare them to one another. The Conclusions and Key Findings chapter provides a brief summary of the work and the findings. The final chapter, Implementation Recommendations Based on Cloud Computing for the Future, includes a discussion of costs and requirements, along with an economic analysis and future computing suggestions.