Abstract-Very often, the only reliable information available to perform change detection is the description of some unchanged regions. Since sometimes these regions do not contain all the relevant information to identify their counterpart (the changes), we consider the use of unlabeled data to perform Semi-Supervised Novelty detection (SSND). SSND can be seen as an unbalanced classification problem solved using the Cost-Sensitive Support Vector Machine (CS-SVM), but this requires a heavy parameter search. We propose here to use entire solution path algorithms for the CS-SVM in order to facilitate and accelerate the parameter selection for SSND. Two algorithms are considered and evaluated. The first one is an extension of the CS-SVM algorithm that returns the entire solution path in a single optimization. This way, the optimization of a separate model for each hyperparameter set is avoided. The second forces the solution to be coherent through the solution path, thus producing classification boundaries that are nested (included in each other). We also present a low density criterion for selecting the optimal classification boundaries, thus avoiding the recourse to cross-validation that usually requires information about the "change" class. Experiments are performed on two multitemporal change detection datasets (flood and fire detection). Both algorithms tracing the solution path provide similar performances than the standard CS-SVM while being significantly faster. The low density criterion proposed achieves results that are close to the ones obtained by cross-validation, but without using information about the changes.
Very often in change detection only few labels or even none are available. In order to perform change detection in these extreme scenarios, they can be considered as novelty detection problems, semi-supervised (SSND) if some labels are available otherwise unsupervised (UND). SSND can be seen as an unbalanced classification between labeled and unlabeled samples using the Cost-Sensitive Support Vector Machine (CS-SVM). UND assumes novelties in low density regions and can be approached using the One-Class SVM (OC-SVM). We propose here to use nested entire solution path algorithms for the OC-SVM and CS-SVM in order to accelerate the parameter selection and alleviate the dependency to labeled "changed" samples. Experiments are performed on two multitemporal change detection datasets (flood and fire detection) and the performance of the two methods proposed compared.
This paper presents an algorithm for near-real time registration of airborne video sequences with reference images from a different sensor type. Phase-correlation using Fourier-Melin Invariant (FMI) descriptors allow to retrieve the rigid transformation parameters in a fast and non-iterative way. The robustness to multi-sources images is obtained by an enhanced image representation based on the gradient norm and by the extrapolation of registration parameters by motion estimation between frames. A phase-correlation score, indicator of the registration quality, is introduced to regulate between frame-toreference image registration and extrapolation from previous frames only. Our Robust Phase-Correlation based registration algorithm using Motion Estimation (RPCME) is compared with a Mutual Information (MI) algorithm for the registration of two different panchromatic airborne videos with Geoeye reference images. The RPCME algorithm registered most of the frames accurately, retrieving much better orientation than MI. It shows robustness and good accuracy to multisource images with the advantage of being a direct (non-iterative) method.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.