Alejandro Gonzalez Alzate, David Vazquez, Antonio Lopez, & Jaume Amores. (2017). On-Board Object Detection: Multicue, Multimodal, and Multiview Random Forest of Local Experts. Cyber - IEEE Transactions on cybernetics, 47(11), 3980–3990.
Abstract: Despite recent significant advances, object 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 multiview (MV) classifier that accounts for different object views and poses. In this paper, we provide an extensive evaluation that gives insight into how each of these aspects (multicue, multimodality, and strong MV classifier) affect accuracy both individually and when integrated together. In the multimodality component, we explore the fusion of RGB and depth maps obtained by high-definition light detection and ranging, a type of modality that is starting to receive increasing attention. As our analysis reveals, although all the aforementioned aspects significantly help in improving the accuracy, 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.
Keywords: Multicue; multimodal; multiview; object detection
|
Xavier Otazu, Maria Vanrell, & C. Alejandro Parraga. (2008). Multiresolution Wavelet Framework Models Brightness Induction Effects. VR - Vision Research, 733–751.
|
Ernest Valveny, Oriol Ramos Terrades, Joan Mas, & Marçal Rusiñol. (2013). Interactive Document Retrieval and Classification. In Angel Sappa, & Jordi Vitria (Eds.), Multimodal Interaction in Image and Video Applications (Vol. 48, pp. 17–30). Springer Berlin Heidelberg.
Abstract: In this chapter we describe a system for document retrieval and classification following the interactive-predictive framework. In particular, the system addresses two different scenarios of document analysis: document classification based on visual appearance and logo detection. These two classical problems of document analysis are formulated following the interactive-predictive model, taking the user interaction into account to make easier the process of annotating and labelling the documents. A system implementing this model in a real scenario is presented and analyzed. This system also takes advantage of active learning techniques to speed up the task of labelling the documents.
|
Joost Van de Weijer, Fahad Shahbaz Khan, & Marc Masana. (2013). Interactive Visual and Semantic Image Retrieval. In Angel Sappa, & Jordi Vitria (Eds.), Multimodal Interaction in Image and Video Applications (Vol. 48, pp. 31–35). Springer Berlin Heidelberg.
Abstract: One direct consequence of recent advances in digital visual data generation and the direct availability of this information through the World-Wide Web, is a urgent demand for efficient image retrieval systems. The objective of image retrieval is to allow users to efficiently browse through this abundance of images. Due to the non-expert nature of the majority of the internet users, such systems should be user friendly, and therefore avoid complex user interfaces. In this chapter we investigate how high-level information provided by recently developed object recognition techniques can improve interactive image retrieval. Wel apply a bagof- word based image representation method to automatically classify images in a number of categories. These additional labels are then applied to improve the image retrieval system. Next to these high-level semantic labels, we also apply a low-level image description to describe the composition and color scheme of the scene. Both descriptions are incorporated in a user feedback image retrieval setting. The main objective is to show that automatic labeling of images with semantic labels can improve image retrieval results.
|
Abel Gonzalez-Garcia, Robert Benavente, Olivier Penacchio, Javier Vazquez, Maria Vanrell, & C. Alejandro Parraga. (2013). Coloresia: An Interactive Colour Perception Device for the Visually Impaired. In Multimodal Interaction in Image and Video Applications (Vol. 48, pp. 47–66). Springer Berlin Heidelberg.
Abstract: A significative percentage of the human population suffer from impairments in their capacity to distinguish or even see colours. For them, everyday tasks like navigating through a train or metro network map becomes demanding. We present a novel technique for extracting colour information from everyday natural stimuli and presenting it to visually impaired users as pleasant, non-invasive sound. This technique was implemented inside a Personal Digital Assistant (PDA) portable device. In this implementation, colour information is extracted from the input image and categorised according to how human observers segment the colour space. This information is subsequently converted into sound and sent to the user via speakers or headphones. In the original implementation, it is possible for the user to send its feedback to reconfigure the system, however several features such as these were not implemented because the current technology is limited.We are confident that the full implementation will be possible in the near future as PDA technology improves.
|
Michal Drozdzal, Santiago Segui, Petia Radeva, Carolina Malagelada, Fernando Azpiroz, & Jordi Vitria. (2013). An Application for Efficient Error-Free Labeling of Medical Images. In Multimodal Interaction in Image and Video Applications (Vol. 48, pp. 1–16). Springer Berlin Heidelberg.
Abstract: In this chapter we describe an application for efficient error-free labeling of medical images. In this scenario, the compilation of a complete training set for building a realistic model of a given class of samples is not an easy task, making the process tedious and time consuming. For this reason, there is a need for interactive labeling applications that minimize the effort of the user while providing error-free labeling. We propose a new algorithm that is based on data similarity in feature space. This method actively explores data in order to find the best label-aligned clustering and exploits it to reduce the labeler effort, that is measured by the number of “clicks. Moreover, error-free labeling is guaranteed by the fact that all data and their labels proposals are visually revised by en expert.
|
Marc Castello, Jordi Gonzalez, Ariel Amato, Pau Baiget, Carles Fernandez, Josep M. Gonfaus, et al. (2013). Exploiting Multimodal Interaction Techniques for Video-Surveillance. In Multimodal Interaction in Image and Video Applications Intelligent Systems Reference Library (Vol. 48, pp. 135–151). Springer Berlin Heidelberg.
Abstract: In this paper we present an example of a video surveillance application that exploits Multimodal Interactive (MI) technologies. The main objective of the so-called VID-Hum prototype was to develop a cognitive artificial system for both the detection and description of a particular set of human behaviours arising from real-world events. The main procedure of the prototype described in this chapter entails: (i) adaptation, since the system adapts itself to the most common behaviours (qualitative data) inferred from tracking (quantitative data) thus being able to recognize abnormal behaviors; (ii) feedback, since an advanced interface based on Natural Language understanding allows end-users the communicationwith the prototype by means of conceptual sentences; and (iii) multimodality, since a virtual avatar has been designed to describe what is happening in the scene, based on those textual interpretations generated by the prototype. Thus, the MI methodology has provided an adequate framework for all these cooperating processes.
|
David Vazquez, Antonio Lopez, Daniel Ponsa, & David Geronimo. (2013). Interactive Training of Human Detectors. In Multiodal Interaction in Image and Video Applications (Vol. 48, pp. 169–182). Springer Berlin Heidelberg.
Abstract: Image based human detection remains as a challenging problem. Most promising detectors rely on classifiers trained with labelled samples. However, labelling is a manual labor intensive step. To overcome this problem we propose to collect images of pedestrians from a virtual city, i.e., with automatic labels, and train a pedestrian detector with them, which works fine when such virtual-world data are similar to testing one, i.e., real-world pedestrians in urban areas. When testing data is acquired in different conditions than training one, e.g., human detection in personal photo albums, dataset shift appears. In previous work, we cast this problem as one of domain adaptation and solve it with an active learning procedure. In this work, we focus on the same problem but evaluating a different set of faster to compute features, i.e., Haar, EOH and their combination. In particular, we train a classifier with virtual-world data, using such features and Real AdaBoost as learning machine. This classifier is applied to real-world training images. Then, a human oracle interactively corrects the wrong detections, i.e., few miss detections are manually annotated and some false ones are pointed out too. A low amount of manual annotation is fixed as restriction. Real- and virtual-world difficult samples are combined within what we call cool world and we retrain the classifier with this data. Our experiments show that this adapted classifier is equivalent to the one trained with only real-world data but requiring 90% less manual annotations.
Keywords: Pedestrian Detection; Virtual World; AdaBoost; Domain Adaptation
|
Angel Sappa, & Jordi Vitria. (2013). Multimodal Interaction in Image and Video Applications (Vol. 48). Springer Berlin Heidelberg.
Abstract: Book Series Intelligent Systems Reference Library
|
Marçal Rusiñol, David Aldavert, Ricardo Toledo, & Josep Llados. (2015). Efficient segmentation-free keyword spotting in historical document collections. PR - Pattern Recognition, 48(2), 545–555.
Abstract: In this paper we present an efficient segmentation-free word spotting method, applied in the context of historical document collections, that follows the query-by-example paradigm. We use a patch-based framework where local patches are described by a bag-of-visual-words model powered by SIFT descriptors. By projecting the patch descriptors to a topic space with the latent semantic analysis technique and compressing the descriptors with the product quantization method, we are able to efficiently index the document information both in terms of memory and time. The proposed method is evaluated using four different collections of historical documents achieving good performances on both handwritten and typewritten scenarios. The yielded performances outperform the recent state-of-the-art keyword spotting approaches.
Keywords: Historical documents; Keyword spotting; Segmentation-free; Dense SIFT features; Latent semantic analysis; Product quantization
|
Ivan Huerta, Marco Pedersoli, Jordi Gonzalez, & Alberto Sanfeliu. (2015). Combining where and what in change detection for unsupervised foreground learning in surveillance. PR - Pattern Recognition, 48(3), 709–719.
Abstract: Change detection is the most important task for video surveillance analytics such as foreground and anomaly detection. Current foreground detectors learn models from annotated images since the goal is to generate a robust foreground model able to detect changes in all possible scenarios. Unfortunately, manual labelling is very expensive. Most advanced supervised learning techniques based on generic object detection datasets currently exhibit very poor performance when applied to surveillance datasets because of the unconstrained nature of such environments in terms of types and appearances of objects. In this paper, we take advantage of change detection for training multiple foreground detectors in an unsupervised manner. We use statistical learning techniques which exploit the use of latent parameters for selecting the best foreground model parameters for a given scenario. In essence, the main novelty of our proposed approach is to combine the where (motion segmentation) and what (learning procedure) in change detection in an unsupervised way for improving the specificity and generalization power of foreground detectors at the same time. We propose a framework based on latent support vector machines that, given a noisy initialization based on motion cues, learns the correct position, aspect ratio, and appearance of all moving objects in a particular scene. Specificity is achieved by learning the particular change detections of a given scenario, and generalization is guaranteed since our method can be applied to any possible scene and foreground object, as demonstrated in the experimental results outperforming the state-of-the-art.
Keywords: Object detection; Unsupervised learning; Motion segmentation; Latent variables; Support vector machine; Multiple appearance models; Video surveillance
|
Marco Pedersoli, Andrea Vedaldi, Jordi Gonzalez, & Xavier Roca. (2015). A coarse-to-fine approach for fast deformable object detection. PR - Pattern Recognition, 48(5), 1844–1853.
Abstract: We present a method that can dramatically accelerate object detection with part based models. The method is based on the observation that the cost of detection is likely to be dominated by the cost of matching each part to the image, and not by the cost of computing the optimal configuration of the parts as commonly assumed. Therefore accelerating detection requires minimizing the number of
part-to-image comparisons. To this end we propose a multiple-resolutions hierarchical part based model and a corresponding coarse-to-fine inference procedure that recursively eliminates from the search space unpromising part
placements. The method yields a ten-fold speedup over the standard dynamic programming approach and is complementary to the cascade-of-parts approach of [9]. Compared to the latter, our method does not have parameters to be determined empirically, which simplifies its use during the training of the model. Most importantly, the two techniques can be combined to obtain a very significant speedup, of two orders of magnitude in some cases. We evaluate our method extensively on the PASCAL VOC and INRIA datasets, demonstrating a very high increase in the detection speed with little degradation of the accuracy.
|
Gloria Fernandez Esparrach, Jorge Bernal, Maria Lopez Ceron, Henry Cordova, Cristina Sanchez Montes, Cristina Rodriguez de Miguel, et al. (2016). Exploring the clinical potential of an automatic colonic polyp detection method based on the creation of energy maps. END - Endoscopy, 48(9), 837–842.
Abstract: Background and aims: Polyp miss-rate is a drawback of colonoscopy that increases significantly in small polyps. We explored the efficacy of an automatic computer vision method for polyp detection.
Methods: Our method relies on a model that defines polyp boundaries as valleys of image intensity. Valley information is integrated into energy maps which represent the likelihood of polyp presence.
Results: In 24 videos containing polyps from routine colonoscopies, all polyps were detected in at least one frame. Mean values of the maximum of energy map were higher in frames with polyps than without (p<0.001). Performance improved in high quality frames (AUC= 0.79, 95%CI: 0.70-0.87 vs 0.75, 95%CI: 0.66-0.83). Using 3.75 as maximum threshold value, sensitivity and specificity for detection of polyps were 70.4% (95%CI: 60.3-80.8) and 72.4% (95%CI: 61.6-84.6), respectively.
Conclusion: Energy maps showed a good performance for colonic polyp detection. This indicates a potential applicability in clinical practice.
|
David Berga, Xavier Otazu, Xose R. Fernandez-Vidal, Victor Leboran, & Xose M. Pardo. (2019). Generating Synthetic Images for Visual Attention Modeling. PER - Perception, 48, 99.
|
Antonio Hernandez, Miguel Angel Bautista, Xavier Perez Sala, Victor Ponce, Sergio Escalera, Xavier Baro, et al. (2014). Probability-based Dynamic Time Warping and Bag-of-Visual-and-Depth-Words for Human Gesture Recognition in RGB-D. PRL - Pattern Recognition Letters, 50(1), 112–121.
Abstract: PATREC5825
We present a methodology to address the problem of human gesture segmentation and recognition in video and depth image sequences. A Bag-of-Visual-and-Depth-Words (BoVDW) model is introduced as an extension of the Bag-of-Visual-Words (BoVW) model. State-of-the-art RGB and depth features, including a newly proposed depth descriptor, are analysed and combined in a late fusion form. The method is integrated in a Human Gesture Recognition pipeline, together with a novel probability-based Dynamic Time Warping (PDTW) algorithm which is used to perform prior segmentation of idle gestures. The proposed DTW variant uses samples of the same gesture category to build a Gaussian Mixture Model driven probabilistic model of that gesture class. Results of the whole Human Gesture Recognition pipeline in a public data set show better performance in comparison to both standard BoVW model and DTW approach.
Keywords: RGB-D; Bag-of-Words; Dynamic Time Warping; Human Gesture Recognition
|