Detecting Human Interventions on the Landscape: KAZE Features, Poisson Point Processes, and a Construction Dataset
This work addresses the need for automated monitoring of construction and other human interventions, which is important for urban planning and environmental management, though it appears incremental with improvements in feature matching and dataset creation.
The paper tackled the problem of detecting human-induced changes on Earth's surface using remote sensing imagery, achieving a more than two-fold increase in average match rates over previous standards and making precise, accurate change proposals on two-thirds of scenes in a benchmark dataset.
We present an algorithm capable of identifying a wide variety of human-induced change on the surface of the planet by analyzing matches between local features in time-sequenced remote sensing imagery. We evaluate feature sets, match protocols, and the statistical modeling of feature matches. With application of KAZE features, k-nearest-neighbor descriptor matching, and geometric proximity and bi-directional match consistency checks, average match rates increase more than two-fold over the previous standard. In testing our platform, we developed a small, labeled benchmark dataset expressing large-scale residential, industrial, and civic construction, along with null instances, in California between the years 2010 and 2012. On the benchmark set, our algorithm makes precise, accurate change proposals on two-thirds of scenes. Further, the detection threshold can be tuned so that all or almost all proposed detections are true positives.