Vacant Parking Lot Detection System Using Random Forest Classification

Intelligent parking system is an essential attribute nowadays as the time is being wasted in finding the vacant slot for parking. The proposed method focuses on detecting any vacant space that is out of human vision. A camera is used for capturing the images of parking space. Then a combination of both canny edge detection and LUV based colour variation detection methods are used to precisely extract the edges of each parking slot. The extracted features are then trained using Random Forest classifier to obtain the model which is used to classify the parking space as empty and occupied. For experimentation, parking lot images from the PKlot dataset captured under different weather conditions has been used. When trained with a subset of the dataset with 37,680 parking spaces, after extracting the features and applying the Random Forest classification algorithm the proposed method can able to achieve a better accuracy of 98.31% compared to the existing methods.