TY  - THES
AU  - Ferran Diego
ED  - Joan Serrat
PY  - 2011//
TI  - Probabilistic Alignment of Video Sequences Recorded by Moving Cameras
PB  - Ediciones Graficas Rey
N2  - Video alignment consists of integrating multiple video sequences recorded independently into a single video sequence. This means to register both in time (synchronizeframes) and space (image registration) so that the two videos sequences can be fusedor compared pixel–wise. In spite of being relatively unknown, many applications today may benefit from the availability of robust and efficient video alignment methods.For instance, video surveillance requires to integrate video sequences that are recordedof the same scene at different times in order to detect changes. The problem of aligning videos has been addressed before, but in the relatively simple cases of fixed or rigidly attached cameras and simultaneous acquisition. In addition, most works relyon restrictive assumptions which reduce its difficulty such as linear time correspondence or the knowledge of the complete trajectories of corresponding scene points on the images; to some extent, these assumptions limit the practical applicability of the solutions developed until now. In this thesis, we focus on the challenging problem of aligning sequences recorded at different times from independent moving cameras following similar but not coincident trajectories. More precisely, this thesis covers four studies that advance the state-of-the-art in video alignment. First, we focus on analyzing and developing a probabilistic framework for video alignment, that is, a principled way to integrate multiple observations and prior information. In this way, two different approaches are presented to exploit the combination of several purely visual features (image–intensities, visual words and dense motion field descriptor), andglobal positioning system (GPS) information. Second, we focus on reformulating theproblem into a single alignment framework since previous works on video alignmentadopt a divide–and–conquer strategy, i.e., first solve the synchronization, and thenregister corresponding frames. This also generalizes the ’classic’ case of fixed geometric transform and linear time mapping. Third, we focus on exploiting directly thetime domain of the video sequences in order to avoid exhaustive cross–frame search.This provides relevant information used for learning the temporal mapping betweenpairs of video sequences. Finally, we focus on adapting these methods to the on–linesetting for road detection and vehicle geolocation. The qualitative and quantitativeresults presented in this thesis on a variety of real–world pairs of video sequences show that the proposed method is: robust to varying imaging conditions, different imagecontent (e.g., incoming and outgoing vehicles), variations on camera velocity, anddifferent scenarios (indoor and outdoor) going beyond the state–of–the–art. Moreover, the on–line video alignment has been successfully applied for road detection andvehicle geolocation achieving promising results.
N1  - ADAS
ID  - Ferran Diego2011
U1  - Ph.D. thesis
ER  -