Innovative Way to Check the Status of Vacancy in Outdoor Parking Lots
Neeru Mago1, Satish Kumar2

1Neeru Mago, Assist. Professor, DCSA, PUSSGRC, Hoshiarpur, Punjab, India.
2Dr. Satish Kumar, Associate Professor in Department of Computer Science and Applications in Panjab University, Chandigarh, India.
Manuscript received on November 20, 2019. | Revised Manuscript received on December 15, 2019. | Manuscript published on December 30, 2019. | PP: 961-965 | Volume-9 Issue-2, December, 2019. | Retrieval Number:  A2089109119/2020©BEIESP | DOI: 10.35940/ijeat.A2089.129219
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (

Abstract: With the unprecedented increase in number of private vehicles, the availability of parking space has become a daunting task for vehicle owners. Be it a shopping mall or a government building, it is hard for drivers to find an appropriate space almost everywhere in the present times. This makes it necessary to find out novel ways to resolve the issues regarding car-parking. Though there are many systems in place for detection of space availability, but one has to shed huge amounts for their implementation. Also there are constraints in using rides-based technologies as they do not consider climatic changes and conditions. The study consists of designing a hybrid model to detect outdoor parking vacant lots and the lots getting vacant in the real-time scenario. The dataset for training, validating and testing the system is extracted from online source which consists of various images of parking lots collected from varied heights and angles. The proposed work in this paper is the advancement of our previous work [1] in which we are going to apply more advanced machine learning techniques to classify vacant and occupied parking lots in the outdoor parking areas.
Keywords: Innovative Parking Management, Image processing, Noise removal, Feature extraction, Machine learning.