Mobile based vehicle stationary system using drone and interactive machine learning technique

The enormous amount of vehicles continually needing access to congested areas in cities means that finding an optimal public parking (stationary) place is often difficult and causes problems for drivers and citizens alike. The provincial governments of Pakistan especially Punjab also considered thes

2025-06-28 16:34:09 - Adil Khan

Project Title

Mobile based vehicle stationary system using drone and interactive machine learning technique

Project Area of Specialization Computer ScienceProject Summary

The enormous amount of vehicles continually needing access to congested areas in cities means that finding an optimal public parking (stationary) place is often difficult and causes problems for drivers and citizens alike. The provincial governments of Pakistan especially Punjab also considered these burgeoning parking (stationary) problems in its different metropolitan areas which need to be solved imperatively. In this context, strategies that guide vehicles from one point to another, by looking at the driver's behavior, routing strategies, obstacle detection, and empty slots analysis, etc. are needed. Most contributions in the literature are either focused on improving routing strategies, obstacle detection, and sensor management individually or specifically. These studies are limited in capturing data and providing solutions with maximize resource utilization. To overcome, these gaps we use a multidisciplinary hybrid approach which is the combination of different tools (i.e., Android Studio, Python, Java, PHP, MySQL, Machine Learning toolkit), techniques(i.e., machine learning, geospatial Image processing, recommendation algorithms ), and technologies(i.e., Smartphones and Drone). Our proposed system is a cloud client/server-based mobile application. The basic modules of the proposed solution are Mobile Application, parking slot occupancy monitoring, Automatic License Plate Recognition, Drone Navigation Handler, and Recommendation Engine. The proposed solution will utilize minimal resources (e.g., less manpower, low cost) and provide an efficient solution to be implemented in the general environment. The proposed solution will not only facilitate the building authorities (e.g., Lahore Parking Company, Lahore Development Authority, Transportation Management, and Design) by providing an optimal solution but also provide a new direction for the researchers to be explored.

Project Objectives

The objectives of the proposed idea are

Project Implementation Method

In this project, a UAV-assisted quick and efficient vehicle parking management solution for real-time stationing vehicles through automatic vehicle number (e.g., cars, bus) detection and empty slot occupancy detection techniques have been proposed. Initially, the system will offer a Mobile Application module that provides interfacing for users (e.g., citizen, driver) through which they can register their selves, select preferences regarding slots, and get recommendations from the system associated with the nearest available preferred slots. A Drone Navigation Handler module is created in which a drone-mounted camera has been used to record videos of the parking slot.  The parking slots images will be extracted and detected using geospatial image processing algorithms.  For drones, the outdoor obstacle detection and avoidance will be handling by deep neural network based algorithms. The dynamic programing algorithm based routing algorithm will be proposed which provides the shortest path for parking. A deep neural network-based parking (stationary) slot occupancy monitoring system is used to determine the number of occupied and vacant spots in parking (stationary). A recommendation engine will be developed which will first be trained according to the driver's behavior by using user behavior analysis (UBA) and deep neural networking techniques and then provide an assistant to the drivers for the selection of suitable parking (stationary) slots using Hybrid filtering techniques. The automatic license plate recognition (ALPR) algorithm (i.e. KNN algorithm) is used for recognizing the plates of the vehicle. Finally, experimental results are verified using a web-based mobile application that is connected with a cloud database.

Benefits of the Project

The major benefits of the proposed project are

Technical Details of Final Deliverable

In the end, we will deliver the code and the documentation in the form of a final project report containing all the proposed algorithms pseudo and implementation code.

Final Deliverable of the Project Software SystemCore Industry ITOther Industries Transportation Core Technology Artificial Intelligence(AI)Other Technologies OthersSustainable Development Goals Sustainable Cities and CommunitiesRequired Resources
Item Name Type No. of Units Per Unit Cost (in Rs) Total (in Rs)
Total in (Rs) 80000
Wi-fi based drone Equipment15000050000
Mobile phone Equipment21000020000
Documentation Miscellaneous 11000010000

More Posts