MUMBAI, India, Oct. 5 -- Intellectual Property India has published a patent application (202621099245 A) filed by Dr. Ajay Varma on August 17, 2026, for Machine Learning Approach To Boost Urban Parking Efficiency Through Model Integration.
Inventors include Dr. Geeta Santhosh; Dr. Anita Mahajan; Prof. Dheeraj Kumar Mishra; Prof. Neha Nama; Prof. Harshita Sharma; Prof. Amit Nilosey; and Prof. Zahira Noor Qureishi.
The application for the patent was published on October 02, 2026, under issue no. 40/2026.
Abstract: The complexity of transportation has grown substantially in recent years due to the rapid expansion in the world's population. As a result, the mountain movement of different institutions is accompanied by an upsurge in vehicle traffic. The demand for a solution to the problem of vehicle parking is growing rapidly. Because we still use a manual vehicle parking system in India, we have to manually park our cars every time we want to park them, which uses a lot of fuel and necessitates a lot of light. Another problem is that there is no organized system for parking, so it can be somewhat chaotic. Damage to automobiles might occur when leaving or entering the parking lot since anybody can park anywhere. Safety is another concern. We are launching a new automobile parking system—a method to assist drivers in effectively locating and reserving the most suitable parking spot—to address these issues. The rising number of vehicles on the road and the ineffective use of available space pose serious problems for urban parking management. In order to maximize the effectiveness of urban parking, this project presents a state-of-the-art machine learning- driven system that incorporates many models, such as YOLO, OpenCV, Convolutional Neural Networks (CNNs), and polygon testing. To improve mobility and decrease congestion, the suggested solution uses adaptive space allocation, predictive analytics, and real-time vehicle identification. Accurate car recognition, simplified parking allocation, and enhanced security measures are all achieved by integrating numerous machine learning models in the system. Also, it's scalable and can adapt to different types of urban contexts because to its user-friendly interface, which makes data-driven decisions easier. Optimization of space use, enhancement of parking forecast accuracy, and overall user experience may all be achieved by utilizing ML techniques, such as computer vision and predictive analytics, in urban parking systems. KEY WORDS: Machine learning, Convolutional Neural Networks (CNNs), YOLO, OpenCV, Polygon testing, Real-time vehicle detection, Predictive analytics.
Disclaimer: Curated by HT Syndication.
