An Efficient Algorithm for Detection of Vacant Spaces in Delimited and Non-Delimited Parking Lots

Abstract

Smart parking management systems that provide drivers with real-time information about availability and location of parking spaces are high among the wish list of urban dwellers. This paper proposes a machine learning approach for automatic detection of vacant lots in delimited parking spaces where the boundaries of the individual parking lots are predefined, which is then extended to a more general scenario of non-delimited parking spaces. A bag of features (bof) representation for the lots is used with a single svm classifier to discriminate between occupied and vacant lots. For non-delimited spaces, a customized background subtraction algorithm is used to generate proposal regions where vehicles can possibly be found, which are then verified using a bof plus svm approach. When tested on public datasets with images of real parking spaces, the proposed method shows robustness against large intra-class variabilities of vehicles and wide variations in vehicle pose and scale in each parking lot. Compared to state-of-the-art methods, the major advantages of the proposed approach are that it requires fewer images to train the classifier, accepts non-rectangular, variable sized images as input and can also be applied to non-delimited parking spaces, making it suitable for practical deployment.