Scientific Journal of Impact Factor (SJIF): 4.

14
e-ISSN (O): 2348-4470
p-ISSN (P): 2348-6406

International Journal of Advance Engineering and Research

Development
Volume 3, Issue 3, March -2016

VACANT PARKING SPACE DETECTION SYSTEM

Abhishek Belsare1, Shubhangi Jawalkar2, Jennifer Kachhap3, Reshma Padwal4

1-4
Department of Computer Engineering, Zeal College of Engineering and Research,
Pune

Abstract — Traditionally parking in huge malls and organizations was a very tedious job and required great man power.
Therefore, there is a need of an automated, advanced and smart oriented assistance parking system. With the progress of
computer vision techniques, many video surveillance systems provide new kinds of intelligent functions, like object
detection and tracking. Using which it will be possible to design a system which will monitor empty spaces in parking
lots using video surveillance, which will help driver park a car efficiently. Hence we propose a plane-based method
which adopts a structural parking lot model.

Keywords- Histogram of Oriented Gradient, Smart Parking, Vacant Parking Detection

I. INTRODUCTION

parking in huge parking lots was very difficult. That is, driver has to wander inside the parking area in search of empty
parking spot. Also, it required great man power to direct the driver towards empty parking spot. Now recently, video
surveillance systems are being used almost everywhere. So with increasing advancement in Computer Vision Techniques
it is possible to use the surveillance to detect the empty spots in a parking lot. That is we can implement vision based
parking system providing information like location of vacant parking spaces, parking guidance, vehicle finding etc.
Now, to perfectly detect empty spots in parking lot, there are various challenges that we need to take care like dramatic
lighting variations, varying perspective distortion in the image, and inter-object occlusion among parked cars and the
ground plane. Also, insufficient lightning during nighttime is another challenge. Considering these challenges, there can
be four types of this method: Space oriented method, car oriented method, hybrid method and parking lot oriented
method.
The paper is organized as follows: section (II) gives information about proposed system, section (III) gives
methodology of proposed system, , section (IV) gives Mathematical model of the system, section (V) gives conclusion
and references.

II. PROPOSED SYSTEM

Along with different facilities, the system should work all day, which leads to two major issues: The first is about how to
obtain well exposed images, second is about the performance of vacant parking space detection and how to speed up the
system for practical applications. To deal with first issue, we can use a pre-process to enhance the visibility of image
contents, and to deal with second issue, a BHF (Bayesian Hierarchical Framework) is proposed for vacant parking space
detection.
Firstly, parking lot is decomposed into many 3D planer surfaces with which we can utilize texture information for vacant
parking space detection. Also, with many 3D planer surfaces, we can well represent patterns of inter vehicle occlusion.
Fig. 1 shows the flow of proposed system. The system works in two steps: Preprocessing step and Detection step. In
preprocessing step, multi exposed images are captured with different exposer settings. Later, these multi exposed images
are combined to obtain improved quality of image.

@IJAERD-2016, All rights Reserved 729

 International Journal of Advance Engineering and Research Development (IJAERD)
Volume 3, Issue 3, March -2016, e-ISSN: 2348 - 4470, print-ISSN: 2348-6406

Fig. 1

III. SYSTEM METHODOLOGY

The proposed system works in two steps: Preprocessing step and Detection step

3.1. Pre-processing step

As mentioned earlier, in this step, multi-exposed images are captured with different exposer settings. When images in
dark environment are captured, their texture information and color degrades, which ultimately affects performance of
vacant parking space detection system. We can use of multiple images under different exposure settings, to extract useful
image features in both dark and bright areas. To get multi exposure images, special camera like AXIS M 1114 can be
used which can adjust exposure values during image capturing.

3.2. Detection Step.

In this system, parking spaces are treated as set of cuboids, each composed of six patches. These patches are then used for
status inference of parking spaces. Based on 3D cuboid model, parking is viewed as set of 3D planer surfaces. In this step,
those patches of cuboids are classified in different classes like side surface, front or rear surface, ground surface, top
surface.

IV. MATHEMATICAL MODEL

System Description:
Let S be the system, S={input, output, Functions, Success, Failure}

• Input: Video Surveillance or Frequently taken Snapshots from the CCTV footage

• Output: Locations of empty parking spaces in the lot which will be displayed as a 3D model highlighting the
vacant spaces

• Functions : 1. Customer or driver database

2. Vehicle database
3. System analyzer
@IJAERD-2016, All rights Reserved 730
 International Journal of Advance Engineering and Research Development (IJAERD)
Volume 3, Issue 3, March -2016, e-ISSN: 2348 - 4470, print-ISSN: 2348-6406

4. Image classification

• Success Conditions: Vacant parking space found successfully and generate a 3D model.

• Failure Conditions: Unable to detect vacant parking space and fail to form a 3D model.

V. CONCLUSION

Vacant parking detection is useful as it provides secure and reliable parking and pre-reservation of parking slot. Vacant
car parking detection system will become rapid and efficient way of parking in smart cities and project related to it.
Experiments demonstrated that our vacant parking space detection system performed well under various kinds of weather
conditions in both day time as well as night time. Conflicts are also handled very well and required minimum number of
manpower. Results can be quickly transferred to centralized database.

REFERENCES
[1] Ching-Chun Huang, Yu-Shu Tai, and Sheng-Jyh Wang,“ Vacant Parking Space Detection Based on Plane-based
Bayesian Hierarchical Framework”,IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO
TECHNOLOGY, VOL. 23, NO. 9, SEPTEMBER 2013.
[2] Wang Lixia, Jiang Dalin, “A Method of Parking space detection based on image segmentation and LBP”, Fourth
International Conference on Multimedia Information Networking and Security, 2012 IEEE DOI
10.1109/MINES.2012.27.
[3] Aderemi O. Adewumi, Luke O. Joel and Babatunde A. Sawyerr ,“Campus Parking Space Allocation Distribution
Using Pattern Search and Particle Swarm Pattern Search Algorithms”, SCIS&ISIS 2014, Kitakyushu, Japan, December
3-6, 2014.
[4] Zhanlin Ji, Ivan Ganchev, Máirtín O’Droma and Xueji Zhang “ A Cloud-Based Intelligent Car Parking Services for
Smart Cities”,IEEE,2014.
[5] Yanxu Zheng, Sutharshan Rajasegarar, Christopher Leckie, Marimuthu Palaniswami,The University of Melbourne,
Australia, “Smart Car Parking: Temporal Clustering and Anomaly Detection in Urban Car Parking”, 2014 IEEE Ninth
International Conference on Intelligent Sensors, Sensor Networks and Information Processing (ISSNIP) Symposium on
Information Processing Singapore, 21–24 April 2014.
[6] Sanaa Alfatihi, Soukaina Chihab and Yassine Salih Alj,School of Science and Engineering,Al Akhawayn
University,Ifrane, Morocco,“Intelligent Parking System for Car Parking Guidance and Damage Notification”, 2013 4th
International Conference on Intelligent Systems, Modelling and Simulation.
[7] Jin Teong Ang, Siew Wen Chin, Jia Hui Chin, Zyn Xian Choo, Yu Ming Chang,“iSCAPS - Innovative Smart Car
Park System integrated with NFC technology and e-Valet function”,ieee june-2013.
[8] Judith Sen E,Deepa Merlin Dixon K,Ansy , Jinesh K J ,“Advanced License Plate Recognition System For Car
Parking”, International Conference on Embedded Systems - (ICES 2014).
[9] Yanxu Zheng, Sutharshan Rajasegarar, Christopher Leckie National ICT Australia Victoria, Dept. of Computing and
Information Systems,The University of Melbourne, Australia, “Parking Availability Prediction for Sensor-Enabled Car
Parks in Smart Cities”, 2015 IEEE Tenth International Conference on Intelligent Sensors, Sensor Networks and
Information Processing (ISSNIP) Singapore, 7-9 April 2015.
[10] Mrs. D.J. Bonde, Rohit Sunil Shende, Akshay Sambhaji Kedari, Ketan Suresh Gaikwad, Amol Uday
Bhokre,“Automated Car Parking System Commanded By Android Application”, 2014 International Conference on
Computer Communication and Informatics (ICCCI -2014), Jan. 03 – 05, 2014, Coimbatore, INDIA.

@IJAERD-2016, All rights Reserved 731