Parking Space Verification: Improving Robustness Using A Convolutional Neural Network

With the number of privately owned cars increasing, the issue of locating an available parking space becomes apparant. This paper deals with the verification of vacant parking spaces, by using a vision based system looking over parking areas. In particular the paper proposes a binary classifier system, based on a Convolutional Neural Network, that is capable of determining if a parking space is occupied or not. A benchmark database consisting of images captured from different parking areas, under different weather and illumination conditions, has been used to train and test the system. The system shows promising performance on the database with an accuracy of 99.71% overall and is robust to the variations in parking areas and weather conditions.