AI-BASED BUS ENTRY AND EXIT LOGGING SYSTEM: REAL-TIME VEHICLE DETECTION, VIRTUAL TRIPWIRE COUNTING AND WEB DASHBOARD FOR CAMPUS GATE MONITORING

Author

Ms. Swetha Krishna U, Arshad S, Bharanitharan M, Dhanarishvanth T, Aravindhan D

Abstract

 Managing institutional gate traffic manually leads to long delays, human recording errors, traffic congestion during peak hours  and unverified vehicular entries. The AI-Powered Automated Campus Bus Entry & Exit Monitoring System is proposed as an  automated solution that combines real-time vehicle detection, multi-object tracking, proximity-based virtual tripwire line- crossing logic and a persistent SQLite database with an interactive web dashboard. 

The system captures video frames from a webcam feed, detects target vehicles using YOLOv8, tracks them across consecutive  frames, calculates bounding box centre coordinates relative to a virtual horizontal tripwire boundary (LINE_Y = 240) and logs  verified ENTRY or EXIT events. Event logs, containing vehicle track labels, movement direction, timestamps and confidence scores,  are saved directly into SQLite (campus_gate_logs.db). A responsive web dashboard, served through a Python HTTP server on  port 8000, polls Flask backend API endpoints on port 5000 to display real-time counters (Total Entries, Total Exits, Buses Inside  Campus) and detailed log inspection tables. 

Keywords

Computer Vision, Object Detection, YOLOv8, Object Tracking, Virtual Tripwire, Flask REST API, SQLite Database, Real- Time Dashboard.

Full Text:

Download Paper PDF

References

[1]Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. You Only Look Once: Unified, Real-Time Object Detection. Proc. IEEE  Conference on Computer Vision and Pattern Recognition (CVPR), 2016.

[2]Jocher, G., Chaurasia, A., & Qiu, J. Ultralytics YOLOv8. Software, 2023. https://github.com/ultralytics/ultralytics
[3]Bewley, A., Ge, Z., Ott, L., Ramos, F., & Upcroft, B. Simple Online and Realtime Tracking. Proc. IEEE International Conference on Image Processing (ICIWojke, N., Bewley, A., & Paulus, D. Simple Online and Realtime Tracking with a Deep Association Metric. Proc. IEEE ICIP, 2017.

[4]Zhang, Y., Sun, P., Jiang, Y., et al. ByteTrack: Multi-Object Tracking by Associating Every Detection Box. Proc. European Conference on Computer Vision (ECCV), 2022.

[5]Bradski, G. The OpenCV Library. Dr. Dobb's Journal of Software Tools, 2000.

[6]Pallets Projects. Flask Documentation. https://flask.palletsprojects.com
[7]SQLite Consortium. SQLite Documentation. https://www.sqlite.org/docs.html

Share your valuable work from Social Media Buttons