Description

Automatic Parking Management System and Parking Fee Collection

ABSTRACT

Searching a suitable parking space in populated metropolitan city is extremely difficult for drivers. Serious traffic congestion may occur due to unavailable parking space. Automatic smart parking system is emerging field and attracted computer vision researchers to contribute in this arena of technology. In this paper, we have presented a vision based smart parking framework to assist the drivers in efficiently finding suitable parking slot and reserve it. Initially, we have segmented the parking area into blocks using calibration. Then, classify each block to identify car and intimate the driver about the status of parking either reserved or free. Potentially, the performance accuracy of recommended system is higher than state of the art hardware solutions, validating the supremacy of the proposed framework.

INTRODUCTION

Now a day’s most of the parking areas are manually managed by human manpower and there is no automatic system to manage the parking area in an efficient way. There is great analogy that when a driver enters any of the parking lot he must look for some kind of information board that tells him about the status of the parking lot that whether it is fully occupied, partly occupied or vacant. Most of the times the drivers have to circle around the parking area in search of the free parking space. This kind of problem mostly occur in cities near the shopping malls, hospitals etc., where the number of vehicles is greater as compared to the parking spaces. The process for searching the free parking space is time consuming and also wastage of fuel. Most of the times the parking spaces remain unoccupied, however the total occupancy is low because of bad management of parking lot. This causes ineffective use of the parking area and also results in traffic jams and congestion near the parking lots. To properly manage the parking lot and display each parking division’s information to the drivers before entering the parking lot have become an important issue to be resolved. In this paper, a system is proposed that will detect the total number of available parking spaces and displays the information to the drivers so that they can easily parked their cars. A web camera is used to get the images of the parking area and image processing techniques are used to detect the presence or absence of cars to count and locate the available parking spaces .The status of the parking lot is updated whenever a car enters or leaves the parking lot.

PROPOSED METHOD

The main flow of framework is shown is Fig. 1. Videos were acquired from the top view of parking arena, from ten feet heighted camera. To strengthen the recognition capacity of system video data was captured at different environmental conditions and temporal shifts. Video is segmented into frames. Then from each segment a key frame is extracted and further processing is applied on this key frame, to reduce computational complexity. When radio controlled toy car enter or leave the parking lot from parking arena, motion of car is estimated by key frame subtraction.

Initially, the parking arena have no parking lines. User will manually input the coordinates of parking area and vehicle intended to be parked. The system automatically generates virtual parking lines keeping in view the size of vehicle. The maximum capacity of parking slots in our training model is fourteen. A unique numeric label is assigned to each parking lot from 1-14. After the parking arena is divided in the virtual blocks, our system will check the existence of car in each block. Binary filter is applied on image and then inverse binary to extract car as region of interest ROI. Computing the value of connected region in ROI and setting the threshold value greater then eighty as reserved parking slot. The number of the free blocks will be indicated to the divers in green and the reserved blocks will be indicated in red color.

BLOCK DIAGRAM  

RESULT

The proposed method is implemented in MATLAB. The online system is getting images from the camera while offline system is getting images from a video file. The result of the online system shows that the proposed algorithms has efficiently detected the available parking slots and notify the drivers. The proposed algorithm is implemented on the model parking lot having space for 14 cars. The Slots having no car are shown as free while the Slots having car in it are shown as reserved to drivers. To test the performance of our proposed algorithm, the accuracy of the system is measured with images taken at different time intervals. The performance is calculated by comparing the results of occupancy to the ground truth after every 5 sec. It is observed that the average performance is 99.5 % and is very high as compared with other parking lot detections applications.

CONCLUSION

The main contribution of this study is to optimize the identification of available parking slots to possibly reduce the congestion in parking arena. Due to advancement in machine learning and vision base technology cost effective automatic parking systems facilitate the drivers to locate available spaces at parking arena. Future researchers can focus on allocation specific location to customers already registered from online parking management system.