Abstract: Advanced segmentation techniques in the surveillance domain deal with shadows to avoid distortions when detecting moving objects. Most approaches for shadow detection are still typically restricted to penumbra shadows and cannot cope well with umbra shadows. Consequently, umbra shadow regions are usually detected as part of moving objects, thus aecting the performance of the nal detection. In this paper we address the detection of both penumbra and umbra shadow regions. First, a novel bottom-up approach is presented based on gradient and colour models, which successfully discriminates between chromatic moving cast shadow regions and those regions detected as moving objects. In essence, those regions corresponding to potential shadows are detected based on edge partitioning and colour statistics. Subsequently (i) temporal similarities between textures and (ii) spatial similarities between chrominance angle and brightness distortions are analysed for each potential shadow region for detecting the umbra shadow regions. Our second contribution renes even further the segmentation results: a tracking-based top-down approach increases the performance of our bottom-up chromatic shadow detection algorithm by properly correcting non-detected shadows.
To do so, a combination of motion lters in a data association framework exploits the temporal consistency between objects and shadows to increase
the shadow detection rate. Experimental results exceed current state-of-the-
art in shadow accuracy for multiple well-known surveillance image databases which contain dierent shadowed materials and illumination conditions.

Abstract: In this paper we present a study on the use of Action Units as mid-level features for automatically recognizing basic and subtle emotions. We propose a representation model based on mid-level facial muscular movement features. We encode these movements dynamically using the Facial Action Coding System, and propose to use these intermediate features based on Action Units (AUs) to classify emotions. AUs activations are detected fusing a set of spatiotemporal geometric and appearance features. The algorithm is validated in two applications: (i) the recognition of 7 basic emotions using the publicly available Cohn-Kanade database, and (ii) the inference of subtle emotional cues in the Newscast database. In this second scenario, we consider emotions that are perceived cumulatively in longer periods of time. In particular, we Automatically classify whether video shoots from public News TV channels refer to Good or Bad news. To deal with the different video lengths we propose a Histogram of Action Units and compute it using a sliding window strategy on the frame sequences. Our approach achieves accuracies close to human perception.

Abstract: non-indexed
This article explains how two projects implement semi-automated transcription routines: for census sheets in Norway and marriage protocols from Barcelona. The Spanish system was created to transcribe the marriage license books from 1451 to 1905 for the Barcelona area; one of the world’s longest series of preserved vital records. Thus, in the Project “Five Centuries of Marriages” (5CofM) at the Autonomous University of Barcelona’s Center for Demographic Studies, the Barcelona Historical Marriage Database has been built. More than 600,000 records were transcribed by 150 transcribers working online. The Norwegian material is cross-sectional as it is the 1891 census, recorded on one sheet per person. This format and the underlining of keywords for several variables made it more feasible to semi-automate data entry than when many persons are listed on the same page. While Optical Character Recognition (OCR) for printed text is scientifically mature, computer vision research is now focused on more difficult problems such as handwriting recognition. In the marriage project, document analysis methods have been proposed to automatically recognize the marriage licenses. Fully automatic recognition is still a challenge, but some promising results have been obtained. In Spain, Norway and elsewhere the source material is available as scanned pictures on the Internet, opening up the possibility for further international cooperation concerning automating the transcription of historic source materials. Like what is being done in projects to digitize printed materials, the optimal solution is likely to be a combination of manual transcription and machine-assisted recognition also for hand-written sources.

Abstract: Pedestrian classifiers decide which image windows contain a pedestrian. In practice, such classifiers provide a relatively high response at neighbor windows overlapping a pedestrian, while the responses around potential false positives are expected to be lower. An analogous reasoning applies for image sequences. If there is a pedestrian located within a frame, the same pedestrian is expected to appear close to the same location in neighbor frames. Therefore, such a location has chances of receiving high classification scores during several frames, while false positives are expected to be more spurious. In this paper we propose to exploit such correlations for improving the accuracy of base pedestrian classifiers. In particular, we propose to use two-stage classifiers which not only rely on the image descriptors required by the base classifiers but also on the response of such base classifiers in a given spatiotemporal neighborhood. More specifically, we train pedestrian classifiers using a stacked sequential learning (SSL) paradigm. We use a new pedestrian dataset we have acquired from a car to evaluate our proposal at different frame rates. We also test on a well known dataset: Caltech. The obtained results show that our SSL proposal boosts detection accuracy significantly with a minimal impact on the computational cost. Interestingly, SSL improves more the accuracy at the most dangerous situations, i.e. when a pedestrian is close to the camera.

Abstract: Despite recent significant advances, pedestrian detection continues to be an extremely challenging problem in real scenarios. In order to develop a detector that successfully operates under these conditions, it becomes critical to leverage upon multiple cues, multiple imaging modalities and a strong multi-view classifier that accounts for different pedestrian views and poses. In this paper we provide an extensive evaluation that gives insight into how each of these aspects (multi-cue, multimodality and strong multi-view classifier) affect performance both individually and when integrated together. In the multimodality component we explore the fusion of RGB and depth maps obtained by high-definition LIDAR, a type of modality that is only recently starting to receive attention. As our analysis reveals, although all the aforementioned aspects significantly help in improving the performance, the fusion of visible spectrum and depth information allows to boost the accuracy by a much larger margin. The resulting detector not only ranks among the top best performers in the challenging KITTI benchmark, but it is built upon very simple blocks that are easy to implement and computationally efficient. These simple blocks can be easily replaced with more sophisticated ones recently proposed, such as the use of convolutional neural networks for feature representation, to further improve the accuracy.

Abstract: In this article we provide an overview of color name applications in computer vision. Color names are linguistic labels which humans use to communicate color. Computational color naming learns a mapping from pixels values to color names. In recent years color names have been applied to a wide variety of computer vision applications, including image classification, object recognition, texture classification, visual tracking and action recognition. Here we provide an overview of these results which show that in general color names outperform photometric invariants as a color representation.

Abstract: While depth tends to improve network performances, it also makes gradient-based training more difficult since deeper networks tend to be more non-linear. The recently proposed knowledge distillation approach is aimed at obtaining small and fast-to-execute models, and it has shown that a student network could imitate the soft output of a larger teacher network or ensemble of networks. In this paper, we extend this idea to allow the training of a student that is deeper and thinner than the teacher, using not only the outputs but also the intermediate representations learned by the teacher as hints to improve the training process and final performance of the student. Because the student intermediate hidden layer will generally be smaller than the teacher's intermediate hidden layer, additional parameters are introduced to map the student hidden layer to the prediction of the teacher hidden layer. This allows one to train deeper students that can generalize better or run faster, a trade-off that is controlled by the chosen student capacity. For example, on CIFAR-10, a deep student network with almost 10.4 times less parameters outperforms a larger, state-of-the-art teacher network.