Autonomous detection and classification of change using aerial robots

Abstract

This work proposes a strategy for autonomous change detection and classification using aerial robots. The aerial robots are initially armed with the capacity to autonomously explore unknown environments. Subsequently the online-derived inspection path is repeated in the next missions in order to detect change. For aerial robotic missions that were conducted in different spatio-temporal conditions, the pose-annotated camera data are first compared for similarity in order to identify the correspondence map among the different image sets. Then, efficient feature matching techniques relying on binary descriptors are used to estimate the geometric transformations among the corresponding images from different mission runs, and finally image subtraction and filtering are performed, enabling robust change detection results. To further decrease the computational load, the known poses of the images from different runs are used to create local subsets within which similar images are expected to be found. Once change detection is accomplished, a small set of the images that present the maximum levels of change are used to classify the change by searching to recognize a list of known objects through a bag-of-features approach. The proposed algorithm is initially verified using handheld-smartphone collected data, and eventually evaluated in experiments using an autonomous aerial robot.