Ivan Huerta, Michael Holte, Thomas B. Moeslund, & Jordi Gonzalez. (2015). Chromatic shadow detection and tracking for moving foreground segmentation. IMAVIS - Image and Vision Computing, 41, 42–53.
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 a ecting 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 di erent shadowed materials and illumination conditions.
Keywords: Detecting moving objects; Chromatic shadow detection; Temporal local gradient; Spatial and Temporal brightness and angle distortions; Shadow tracking
|
Antonio Lopez, Gabriel Villalonga, Laura Sellart, German Ros, David Vazquez, Jiaolong Xu, et al. (2017). Training my car to see using virtual worlds. IMAVIS - Image and Vision Computing, 38, 102–118.
Abstract: Computer vision technologies are at the core of different advanced driver assistance systems (ADAS) and will play a key role in oncoming autonomous vehicles too. One of the main challenges for such technologies is to perceive the driving environment, i.e. to detect and track relevant driving information in a reliable manner (e.g. pedestrians in the vehicle route, free space to drive through). Nowadays it is clear that machine learning techniques are essential for developing such a visual perception for driving. In particular, the standard working pipeline consists of collecting data (i.e. on-board images), manually annotating the data (e.g. drawing bounding boxes around pedestrians), learning a discriminative data representation taking advantage of such annotations (e.g. a deformable part-based model, a deep convolutional neural network), and then assessing the reliability of such representation with the acquired data. In the last two decades most of the research efforts focused on representation learning (first, designing descriptors and learning classifiers; later doing it end-to-end). Hence, collecting data and, especially, annotating it, is essential for learning good representations. While this has been the case from the very beginning, only after the disruptive appearance of deep convolutional neural networks that it became a serious issue due to their data hungry nature. In this context, the problem is that manual data annotation is a tiresome work prone to errors. Accordingly, in the late 00’s we initiated a research line consisting of training visual models using photo-realistic computer graphics, especially focusing on assisted and autonomous driving. In this paper, we summarize such a work and show how it has become a new tendency with increasing acceptance.
|
Pau Rodriguez, Miguel Angel Bautista, Sergio Escalera, & Jordi Gonzalez. (2018). Beyond Oneshot Encoding: lower dimensional target embedding. IMAVIS - Image and Vision Computing, 75, 21–31.
Abstract: Target encoding plays a central role when learning Convolutional Neural Networks. In this realm, one-hot encoding is the most prevalent strategy due to its simplicity. However, this so widespread encoding schema assumes a flat label space, thus ignoring rich relationships existing among labels that can be exploited during training. In large-scale datasets, data does not span the full label space, but instead lies in a low-dimensional output manifold. Following this observation, we embed the targets into a low-dimensional space, drastically improving convergence speed while preserving accuracy. Our contribution is two fold: (i) We show that random projections of the label space are a valid tool to find such lower dimensional embeddings, boosting dramatically convergence rates at zero computational cost; and (ii) we propose a normalized eigenrepresentation of the class manifold that encodes the targets with minimal information loss, improving the accuracy of random projections encoding while enjoying the same convergence rates. Experiments on CIFAR-100, CUB200-2011, Imagenet, and MIT Places demonstrate that the proposed approach drastically improves convergence speed while reaching very competitive accuracy rates.
Keywords: Error correcting output codes; Output embeddings; Deep learning; Computer vision
|
Julio C. S. Jacques Junior, Xavier Baro, & Sergio Escalera. (2018). Exploiting feature representations through similarity learning, post-ranking and ranking aggregation for person re-identification. IMAVIS - Image and Vision Computing, 79, 76–85.
Abstract: Person re-identification has received special attention by the human analysis community in the last few years. To address the challenges in this field, many researchers have proposed different strategies, which basically exploit either cross-view invariant features or cross-view robust metrics. In this work, we propose to exploit a post-ranking approach and combine different feature representations through ranking aggregation. Spatial information, which potentially benefits the person matching, is represented using a 2D body model, from which color and texture information are extracted and combined. We also consider background/foreground information, automatically extracted via Deep Decompositional Network, and the usage of Convolutional Neural Network (CNN) features. To describe the matching between images we use the polynomial feature map, also taking into account local and global information. The Discriminant Context Information Analysis based post-ranking approach is used to improve initial ranking lists. Finally, the Stuart ranking aggregation method is employed to combine complementary ranking lists obtained from different feature representations. Experimental results demonstrated that we improve the state-of-the-art on VIPeR and PRID450s datasets, achieving 67.21% and 75.64% on top-1 rank recognition rate, respectively, as well as obtaining competitive results on CUHK01 dataset.
|
Meysam Madadi, Sergio Escalera, Alex Carruesco Llorens, Carlos Andujar, Xavier Baro, & Jordi Gonzalez. (2018). Top-down model fitting for hand pose recovery in sequences of depth images. IMAVIS - Image and Vision Computing, 79, 63–75.
Abstract: State-of-the-art approaches on hand pose estimation from depth images have reported promising results under quite controlled considerations. In this paper we propose a two-step pipeline for recovering the hand pose from a sequence of depth images. The pipeline has been designed to deal with images taken from any viewpoint and exhibiting a high degree of finger occlusion. In a first step we initialize the hand pose using a part-based model, fitting a set of hand components in the depth images. In a second step we consider temporal data and estimate the parameters of a trained bilinear model consisting of shape and trajectory bases. We evaluate our approach on a new created synthetic hand dataset along with NYU and MSRA real datasets. Results demonstrate that the proposed method outperforms the most recent pose recovering approaches, including those based on CNNs.
|
Aitor Alvarez-Gila, Adrian Galdran, Estibaliz Garrote, & Joost Van de Weijer. (2019). Self-supervised blur detection from synthetically blurred scenes. IMAVIS - Image and Vision Computing, 92, 103804.
Abstract: Blur detection aims at segmenting the blurred areas of a given image. Recent deep learning-based methods approach this problem by learning an end-to-end mapping between the blurred input and a binary mask representing the localization of its blurred areas. Nevertheless, the effectiveness of such deep models is limited due to the scarcity of datasets annotated in terms of blur segmentation, as blur annotation is labor intensive. In this work, we bypass the need for such annotated datasets for end-to-end learning, and instead rely on object proposals and a model for blur generation in order to produce a dataset of synthetically blurred images. This allows us to perform self-supervised learning over the generated image and ground truth blur mask pairs using CNNs, defining a framework that can be employed in purely self-supervised, weakly supervised or semi-supervised configurations. Interestingly, experimental results of such setups over the largest blur segmentation datasets available show that this approach achieves state of the art results in blur segmentation, even without ever observing any real blurred image.
|
A. Toet, M. Henselmans, M.P. Lucassen, & Theo Gevers. (2011). Emotional effects of dynamic textures. iPER - i-Perception, 969 – 991.
Abstract: This study explores the effects of various spatiotemporal dynamic texture characteristics on human emotions. The emotional experience of auditory (eg, music) and haptic repetitive patterns has been studied extensively. In contrast, the emotional experience of visual dynamic textures is still largely unknown, despite their natural ubiquity and increasing use in digital media. Participants watched a set of dynamic textures, representing either water or various different media, and self-reported their emotional experience. Motion complexity was found to have mildly relaxing and nondominant effects. In contrast, motion change complexity was found to be arousing and dominant. The speed of dynamics had arousing, dominant, and unpleasant effects. The amplitude of dynamics was also regarded as unpleasant. The regularity of the dynamics over the textures’ area was found to be uninteresting, nondominant, mildly relaxing, and mildly pleasant. The spatial scale of the dynamics had an unpleasant, arousing, and dominant effect, which was larger for textures with diverse content than for water textures. For water textures, the effects of spatial contrast were arousing, dominant, interesting, and mildly unpleasant. None of these effects were observed for textures of diverse content. The current findings are relevant for the design and synthesis of affective multimedia content and for affective scene indexing and retrieval.
|
Marçal Rusiñol, Lluis Pere de las Heras, & Oriol Ramos Terrades. (2014). Flowchart Recognition for Non-Textual Information Retrieval in Patent Search. IR - Information Retrieval, 17(5-6), 545–562.
Abstract: Relatively little research has been done on the topic of patent image retrieval and in general in most of the approaches the retrieval is performed in terms of a similarity measure between the query image and the images in the corpus. However, systems aimed at overcoming the semantic gap between the visual description of patent images and their conveyed concepts would be very helpful for patent professionals. In this paper we present a flowchart recognition method aimed at achieving a structured representation of flowchart images that can be further queried semantically. The proposed method was submitted to the CLEF-IP 2012 flowchart recognition task. We report the obtained results on this dataset.
Keywords: Flowchart recognition; Patent documents; Text/graphics separation; Raster-to-vector conversion; Symbol recognition
|
R. de Nijs, Sebastian Ramos, Gemma Roig, Xavier Boix, Luc Van Gool, & K. Kühnlenz. (2012). On-line Semantic Perception Using Uncertainty. In International Conference on Intelligent Robots and Systems (pp. 4185–4191).
Abstract: Visual perception capabilities are still highly unreliable in unconstrained settings, and solutions might not beaccurate in all regions of an image. Awareness of the uncertainty of perception is a fundamental requirement for proper high level decision making in a robotic system. Yet, the uncertainty measure is often sacrificed to account for dependencies between object/region classifiers. This is the case of Conditional Random Fields (CRFs), the success of which stems from their ability to infer the most likely world configuration, but they do not directly allow to estimate the uncertainty of the solution. In this paper, we consider the setting of assigning semantic labels to the pixels of an image sequence. Instead of using a CRF, we employ a Perturb-and-MAP Random Field, a recently introduced probabilistic model that allows performing fast approximate sampling from its probability density function. This allows to effectively compute the uncertainty of the solution, indicating the reliability of the most likely labeling in each region of the image. We report results on the CamVid dataset, a standard benchmark for semantic labeling of urban image sequences. In our experiments, we show the benefits of exploiting the uncertainty by putting more computational effort on the regions of the image that are less reliable, and use more efficient techniques for other regions, showing little decrease of performance
Keywords: Semantic Segmentation
|
Muhammad Anwer Rao, Fahad Shahbaz Khan, Joost Van de Weijer, Matthieu Molinier, & Jorma Laaksonen. (2018). Binary patterns encoded convolutional neural networks for texture recognition and remote sensing scene classification. ISPRS J - ISPRS Journal of Photogrammetry and Remote Sensing, 138, 74–85.
Abstract: Designing discriminative powerful texture features robust to realistic imaging conditions is a challenging computer vision problem with many applications, including material recognition and analysis of satellite or aerial imagery. In the past, most texture description approaches were based on dense orderless statistical distribution of local features. However, most recent approaches to texture recognition and remote sensing scene classification are based on Convolutional Neural Networks (CNNs). The de facto practice when learning these CNN models is to use RGB patches as input with training performed on large amounts of labeled data (ImageNet). In this paper, we show that Local Binary Patterns (LBP) encoded CNN models, codenamed TEX-Nets, trained using mapped coded images with explicit LBP based texture information provide complementary information to the standard RGB deep models. Additionally, two deep architectures, namely early and late fusion, are investigated to combine the texture and color information. To the best of our knowledge, we are the first to investigate Binary Patterns encoded CNNs and different deep network fusion architectures for texture recognition and remote sensing scene classification. We perform comprehensive experiments on four texture recognition datasets and four remote sensing scene classification benchmarks: UC-Merced with 21 scene categories, WHU-RS19 with 19 scene classes, RSSCN7 with 7 categories and the recently introduced large scale aerial image dataset (AID) with 30 aerial scene types. We demonstrate that TEX-Nets provide complementary information to standard RGB deep model of the same network architecture. Our late fusion TEX-Net architecture always improves the overall performance compared to the standard RGB network on both recognition problems. Furthermore, our final combination leads to consistent improvement over the state-of-the-art for remote sensing scene
Keywords: Remote sensing; Deep learning; Scene classification; Local Binary Patterns; Texture analysis
|
Akhil Gurram, Onay Urfalioglu, Ibrahim Halfaoui, Fahd Bouzaraa, & Antonio Lopez. (2020). Semantic Monocular Depth Estimation Based on Artificial Intelligence. ITSM - IEEE Intelligent Transportation Systems Magazine, 13(4), 99–103.
Abstract: Depth estimation provides essential information to perform autonomous driving and driver assistance. A promising line of work consists of introducing additional semantic information about the traffic scene when training CNNs for depth estimation. In practice, this means that the depth data used for CNN training is complemented with images having pixel-wise semantic labels where the same raw training data is associated with both types of ground truth, i.e., depth and semantic labels. The main contribution of this paper is to show that this hard constraint can be circumvented, i.e., that we can train CNNs for depth estimation by leveraging the depth and semantic information coming from heterogeneous datasets. In order to illustrate the benefits of our approach, we combine KITTI depth and Cityscapes semantic segmentation datasets, outperforming state-of-the-art results on monocular depth estimation.
|
Jorge Charco, Angel Sappa, Boris X. Vintimilla, & Henry Velesaca. (2021). Camera pose estimation in multi-view environments: From virtual scenarios to the real world. IVC - Image and Vision Computing, 110, 104182.
Abstract: This paper presents a domain adaptation strategy to efficiently train network architectures for estimating the relative camera pose in multi-view scenarios. The network architectures are fed by a pair of simultaneously acquired images, hence in order to improve the accuracy of the solutions, and due to the lack of large datasets with pairs of overlapped images, a domain adaptation strategy is proposed. The domain adaptation strategy consists on transferring the knowledge learned from synthetic images to real-world scenarios. For this, the networks are firstly trained using pairs of synthetic images, which are captured at the same time by a pair of cameras in a virtual environment; and then, the learned weights of the networks are transferred to the real-world case, where the networks are retrained with a few real images. Different virtual 3D scenarios are generated to evaluate the relationship between the accuracy on the result and the similarity between virtual and real scenarios—similarity on both geometry of the objects contained in the scene as well as relative pose between camera and objects in the scene. Experimental results and comparisons are provided showing that the accuracy of all the evaluated networks for estimating the camera pose improves when the proposed domain adaptation strategy is used, highlighting the importance on the similarity between virtual-real scenarios.
|
Karim Lekadir, Alfiia Galimzianova, Angels Betriu, Maria del Mar Vila, Laura Igual, Daniel L. Rubin, et al. (2017). A Convolutional Neural Network for Automatic Characterization of Plaque Composition in Carotid Ultrasound. J-BHI - IEEE Journal Biomedical and Health Informatics, 21(1), 48–55.
Abstract: Characterization of carotid plaque composition, more specifically the amount of lipid core, fibrous tissue, and calcified tissue, is an important task for the identification of plaques that are prone to rupture, and thus for early risk estimation of cardiovascular and cerebrovascular events. Due to its low costs and wide availability, carotid ultrasound has the potential to become the modality of choice for plaque characterization in clinical practice. However, its significant image noise, coupled with the small size of the plaques and their complex appearance, makes it difficult for automated techniques to discriminate between the different plaque constituents. In this paper, we propose to address this challenging problem by exploiting the unique capabilities of the emerging deep learning framework. More specifically, and unlike existing works which require a priori definition of specific imaging features or thresholding values, we propose to build a convolutional neural network (CNN) that will automatically extract from the images the information that is optimal for the identification of the different plaque constituents. We used approximately 90 000 patches extracted from a database of images and corresponding expert plaque characterizations to train and to validate the proposed CNN. The results of cross-validation experiments show a correlation of about 0.90 with the clinical assessment for the estimation of lipid core, fibrous cap, and calcified tissue areas, indicating the potential of deep learning for the challenging task of automatic characterization of plaque composition in carotid ultrasound.
|
Estefania Talavera, Maria Leyva-Vallina, Md. Mostafa Kamal Sarker, Domenec Puig, Nicolai Petkov, & Petia Radeva. (2020). Hierarchical approach to classify food scenes in egocentric photo-streams. J-BHI - IEEE Journal of Biomedical and Health Informatics, 24(3), 866–877.
Abstract: Recent studies have shown that the environment where people eat can affect their nutritional behaviour. In this work, we provide automatic tools for a personalised analysis of a person's health habits by the examination of daily recorded egocentric photo-streams. Specifically, we propose a new automatic approach for the classification of food-related environments, that is able to classify up to 15 such scenes. In this way, people can monitor the context around their food intake in order to get an objective insight into their daily eating routine. We propose a model that classifies food-related scenes organized in a semantic hierarchy. Additionally, we present and make available a new egocentric dataset composed of more than 33000 images recorded by a wearable camera, over which our proposed model has been tested. Our approach obtains an accuracy and F-score of 56\% and 65\%, respectively, clearly outperforming the baseline methods.
|
Michael Holte, Bhaskar Chakraborty, Jordi Gonzalez, & Thomas B. Moeslund. (2012). A Local 3D Motion Descriptor for Multi-View Human Action Recognition from 4D Spatio-Temporal Interest Points. J-STSP - IEEE Journal of Selected Topics in Signal Processing, 6(5), 553–565.
Abstract: In this paper, we address the problem of human action recognition in reconstructed 3-D data acquired by multi-camera systems. We contribute to this field by introducing a novel 3-D action recognition approach based on detection of 4-D (3-D space $+$ time) spatio-temporal interest points (STIPs) and local description of 3-D motion features. STIPs are detected in multi-view images and extended to 4-D using 3-D reconstructions of the actors and pixel-to-vertex correspondences of the multi-camera setup. Local 3-D motion descriptors, histogram of optical 3-D flow (HOF3D), are extracted from estimated 3-D optical flow in the neighborhood of each 4-D STIP and made view-invariant. The local HOF3D descriptors are divided using 3-D spatial pyramids to capture and improve the discrimination between arm- and leg-based actions. Based on these pyramids of HOF3D descriptors we build a bag-of-words (BoW) vocabulary of human actions, which is compressed and classified using agglomerative information bottleneck (AIB) and support vector machines (SVMs), respectively. Experiments on the publicly available i3DPost and IXMAS datasets show promising state-of-the-art results and validate the performance and view-invariance of the approach.
|
