Impervious surfaces are essential elements for the urban ecological environment. Machine-learning-based approaches have achieved successful breakthroughs in impervious surface extraction. These methods require large sets of labeled impervious surface data to train a model. However, it is a challenge to acquire massive impervious surface sample data because of the complexity, time consumption, and high cost. To address this issue, we explore a method to generate massive impervious surface training samples using points of interest (POIs) data and vehicle trajectory global positioning system (GPS) data. Furthermore, a neural-network-based method was proposed for impervious surface extraction based on the generated training samples. One Landsat-8 image of Shenzhen City, China, was selected to test our approach. The extraction accuracy of the impervious surface was 90.88%, and the overall accuracy based on this method was improved by 8.57% and 8.45% compared with the support vector data description (SVDD) and weighted one-class support vector machine (WOC-SVM) methods, respectively. The results show that the method integrating POI, trajectory data, and satellite imagery can be a viable candidate for impervious surface extraction.

The effective extraction of impervious surfaces is critical to monitor their expansion and ensure the sustainable development of cities. Open geographic data can provide a large number of training samples for machine learning methods based on remote-sensed images to extract impervious surfaces due to their advantages of low acquisition cost and large coverage. However, training samples generated from open geographic data suffer from severe sample imbalance. Although one-class methods can effectively extract an impervious surface based on imbalanced samples, most of the current one-class methods ignore the fact that an impervious surface comprises varied geographic objects, such as roads and buildings. Therefore, this paper proposes an object-oriented deep multi-sphere support vector data description (OODMSVDD) method, which takes into account the diversity of impervious surfaces and incorporates a variety of open geographic data involving OpenStreetMap (OSM), Points of Interest (POIs), and trajectory GPS points to automatically generate massive samples for model learning, thereby improving the extraction of impervious surfaces with varied types. The feasibility of the proposed method is experimentally verified with an overall accuracy of 87.43%, and its superior impervious surface classification performance is shown via comparative experiments. This provides a new, accurate, and more suitable extraction method for complex impervious surfaces.