Abstract: Image mosaicking applications require both geometrical and photometrical registrations between the images that compose the mosaic. This paper proposes a probabilistic color correction algorithm for correcting the photometrical disparities. First, the image to be color corrected is segmented into several regions using mean shift. Then, connected regions are extracted using a region fusion algorithm. Local joint image histograms of each region are modeled as collections of truncated Gaussians using a maximum likelihood estimation procedure. Then, local color palette mapping functions are computed using these sets of Gaussians. The color correction is performed by applying those functions to all the regions of the image. An extensive comparison with ten other state of the art color correction algorithms is presented, using two different image pair data sets. Results show that the proposed approach obtains the best average scores in both data sets and evaluation metrics and is also the most robust to failures.

Abstract: In this paper, the registration problem is formulated as a point to model distance minimization. Unlike most of the existing works, which are based on minimizing a point-wise correspondence term, this formulation avoids the correspondence search that is time-consuming. In the first stage, the target set is described through an implicit function by employing a linear least squares fitting. This function can be either an implicit polynomial or an implicit B-spline from a coarse to fine representation. In the second stage, we show how the obtained implicit representation is used as an interface to convert point-to-point registration into point-to-implicit problem. Furthermore, we show that this registration distance is smooth and can be minimized through the Levengberg-Marquardt algorithm. All the formulations presented for both stages are compact and easy to implement. In addition, we show that our registration method can be handled using any implicit representation though some are coarse and others provide finer representations; hence, a tradeoff between speed and accuracy can be set by employing the right implicit function. Experimental results and comparisons in 2D and 3D show the robustness and the speed of convergence of the proposed approach.

Abstract: Impact factor 2010: 2.92
IF 2011/2012?: 3.32
Interest point detection is an important research area in the field of image processing and computer vision. In particular, image retrieval and object categorization heavily rely on interest point detection from which local image descriptors are computed for image matching. In general, interest points are based on luminance, and color has been largely ignored. However, the use of color increases the distinctiveness of interest points. The use of color may therefore provide selective search reducing the total number of interest points used for image matching. This paper proposes color interest points for sparse image representation. To reduce the sensitivity to varying imaging conditions, light-invariant interest points are introduced. Color statistics based on occurrence probability lead to color boosted points, which are obtained through saliency-based feature selection. Furthermore, a principal component analysis-based scale selection method is proposed, which gives a robust scale estimation per interest point. From large-scale experiments, it is shown that the proposed color interest point detector has higher repeatability than a luminance-based one. Furthermore, in the context of image retrieval, a reduced and predictable number of color features show an increase in performance compared to state-of-the-art interest points. Finally, in the context of object recognition, for the Pascal VOC 2007 challenge, our method gives comparable performance to state-of-the-art methods using only a small fraction of the features, reducing the computing time considerably.

Abstract: Deep convolutional networks can achieve impressive results on RGB scene recognition thanks to large data sets such as places. In contrast, RGB-D scene recognition is still underdeveloped in comparison, due to two limitations of RGB-D data we address in this paper. The first limitation is the lack of depth data for training deep learning models. Rather than fine tuning or transferring RGB-specific features, we address this limitation by proposing an architecture and a two-step training approach that directly learns effective depth-specific features using weak supervision via patches. The resulting RGB-D model also benefits from more complementary multimodal features. Another limitation is the short range of depth sensors (typically 0.5 m to 5.5 m), resulting in depth images not capturing distant objects in the scenes that RGB images can. We show that this limitation can be addressed by using RGB-D videos, where more comprehensive depth information is accumulated as the camera travels across the scenes. Focusing on this scenario, we introduce the ISIA RGB-D video data set to evaluate RGB-D scene recognition with videos. Our video recognition architecture combines convolutional and recurrent neural networks that are trained in three steps with increasingly complex data to learn effective features (i.e., patches, frames, and sequences). Our approach obtains the state-of-the-art performances on RGB-D image (NYUD2 and SUN RGB-D) and video (ISIA RGB-D) scene recognition.

Abstract: Impact factor 2010: 2.92
Impact factor 2011/12?: 3.32
Head pose and eye location for gaze estimation have been separately studied in numerous works in the literature. Previous research shows that satisfactory accuracy in head pose and eye location estimation can be achieved in constrained settings. However, in the presence of nonfrontal faces, eye locators are not adequate to accurately locate the center of the eyes. On the other hand, head pose estimation techniques are able to deal with these conditions; hence, they may be suited to enhance the accuracy of eye localization. Therefore, in this paper, a hybrid scheme is proposed to combine head pose and eye location information to obtain enhanced gaze estimation. To this end, the transformation matrix obtained from the head pose is used to normalize the eye regions, and in turn, the transformation matrix generated by the found eye location is used to correct the pose estimation procedure. The scheme is designed to enhance the accuracy of eye location estimations, particularly in low-resolution videos, to extend the operative range of the eye locators, and to improve the accuracy of the head pose tracker. These enhanced estimations are then combined to obtain a novel visual gaze estimation system, which uses both eye location and head information to refine the gaze estimates. From the experimental results, it can be derived that the proposed unified scheme improves the accuracy of eye estimations by 16% to 23%. Furthermore, it considerably extends its operating range by more than 15° by overcoming the problems introduced by extreme head poses. Moreover, the accuracy of the head pose tracker is improved by 12% to 24%. Finally, the experimentation on the proposed combined gaze estimation system shows that it is accurate (with a mean error between 2° and 5°) and that it can be used in cases where classic approaches would fail without imposing restraints on the position of the head.

Abstract: The usage of both off-the-shelf and end-to-end trained deep networks have significantly improved the performance of visual tracking on RGB videos. However, the lack of large labeled datasets hampers the usage of convolutional neural networks for tracking in thermal infrared (TIR) images. Therefore, most state-of-the-art methods on tracking for TIR data are still based on handcrafted features. To address this problem, we propose to use image-to-image translation models. These models allow us to translate the abundantly available labeled RGB data to synthetic TIR data. We explore both the usage of paired and unpaired image translation models for this purpose. These methods provide us with a large labeled dataset of synthetic TIR sequences, on which we can train end-to-end optimal features for tracking. To the best of our knowledge, we are the first to train end-to-end features for TIR tracking. We perform extensive experiments on the VOT-TIR2017 dataset. We show that a network trained on a large dataset of synthetic TIR data obtains better performance than one trained on the available real TIR data. Combining both data sources leads to further improvement. In addition, when we combine the network with motion features, we outperform the state of the art with a relative gain of over 10%, clearly showing the efficiency of using synthetic data to train end-to-end TIR trackers.

Abstract: In this work, we address the problem of aligning two video sequences. Such alignment refers to synchronization, i.e., the establishment of temporal correspondence between frames of the first and second video, followed by spatial registration of all the temporally corresponding frames. Video synchronization and alignment have been attempted before, but most often in the relatively simple cases of fixed or rigidly attached cameras and simultaneous acquisition. In addition, restrictive assumptions have been applied, including linear time correspondence or the knowledge of the complete trajectories of corresponding scene points; to some extent, these assumptions limit the practical applicability of any solutions developed. We intend to solve the more general problem of aligning video sequences recorded by independently moving cameras that follow similar trajectories, based only on the fusion of image intensity and GPS information. The novelty of our approach is to pose the synchronization as a MAP inference problem on a Bayesian network including the observations from these two sensor types, which have been proved complementary. Alignment results are presented in the context of videos recorded from vehicles driving along the same track at different times, for different road types. In addition, we explore two applications of the proposed video alignment method, both based on change detection between aligned videos. One is the detection of vehicles, which could be of use in ADAS. The other is online difference spotting videos of surveillance rounds.