SIH2024 IDEA Presentation Format-2
SIH2024 IDEA Presentation Format-2
TITLE PAGE
• Problem Statement ID – 1607
• Problem Statement Title- AI-based traffic
management system with real-time monitoring
and adaptive traffic light control for heavy
traffic routes
• PS Category- Software
• Team ID-
Gaussian blur
Model training
Color conversion
Vehicle detection
Lane Detection
Camera Vehicle detection + counting
Edge detection
feed
Contour detection
3
TEJAS FEASIBILITY AND VIABILITY
➢ Technical feasibility: Current technology supports real-time ➢ Data Accuracy: Ensuring accurate vehicle detection and
vehicle detection and dynamic signal adjustment. Scalable classification in varying weather conditions (rain, fog, etc.)
across intersections. and lighting (nighttime, shadows).
➢ Economic: High initial cost, but long-term savings in fuel and ➢ Integration: Seamless transition with existing infrastructure
time make it worthwhile. is crucial.
➢ Legal: Requires data privacy measures and compliance with ➢ Infrastructure Upgrades: Scaling the system city-wide might
local traffic laws. require extensive upgrades to existing hardware, such as
➢ Social/Environmental: Public acceptance needed; offers additional cameras and network infrastructure.
significant environmental benefits by reducing emissions ➢ Privacy concern : Constant monitoring could be perceived
as a form of surveillance.
❖ Strategies for overcoming these challenges
4
TEJAS IMPACT AND BENEFITS
5
TEJAS RESEARCH AND REFERENCES
❖ References
➢ https://github.com/ultralytics/ultralytics
➢ https://www.researchgate.net/publication/260833477_Smart_Traffic_Management_System
➢ https://sumo.dlr.de/docs/index.html
➢ https://storage.googleapis.com/openimages/web/index.html
➢ https://www.geeksforgeeks.org/opencv-real-time-road-lane-detection