|
Cesar de Souza, Adrien Gaidon, Yohann Cabon, Naila Murray and Antonio Lopez. 2020. Generating Human Action Videos by Coupling 3D Game Engines and Probabilistic Graphical Models. IJCV, 128, 1505–1536.
Abstract: Deep video action recognition models have been highly successful in recent years but require large quantities of manually-annotated data, which are expensive and laborious to obtain. In this work, we investigate the generation of synthetic training data for video action recognition, as synthetic data have been successfully used to supervise models for a variety of other computer vision tasks. We propose an interpretable parametric generative model of human action videos that relies on procedural generation, physics models and other components of modern game engines. With this model we generate a diverse, realistic, and physically plausible dataset of human action videos, called PHAV for “Procedural Human Action Videos”. PHAV contains a total of 39,982 videos, with more than 1000 examples for each of 35 action categories. Our video generation approach is not limited to existing motion capture sequences: 14 of these 35 categories are procedurally-defined synthetic actions. In addition, each video is represented with 6 different data modalities, including RGB, optical flow and pixel-level semantic labels. These modalities are generated almost simultaneously using the Multiple Render Targets feature of modern GPUs. In order to leverage PHAV, we introduce a deep multi-task (i.e. that considers action classes from multiple datasets) representation learning architecture that is able to simultaneously learn from synthetic and real video datasets, even when their action categories differ. Our experiments on the UCF-101 and HMDB-51 benchmarks suggest that combining our large set of synthetic videos with small real-world datasets can boost recognition performance. Our approach also significantly outperforms video representations produced by fine-tuning state-of-the-art unsupervised generative models of videos.
Keywords: Procedural generation; Human action recognition; Synthetic data; Physics
|
|
|
Daniel Hernandez and 8 others. 2019. Slanted Stixels: A way to represent steep streets. IJCV, 127, 1643–1658.
Abstract: This work presents and evaluates a novel compact scene representation based on Stixels that infers geometric and semantic information. Our approach overcomes the previous rather restrictive geometric assumptions for Stixels by introducing a novel depth model to account for non-flat roads and slanted objects. Both semantic and depth cues are used jointly to infer the scene representation in a sound global energy minimization formulation. Furthermore, a novel approximation scheme is introduced in order to significantly reduce the computational complexity of the Stixel algorithm, and then achieve real-time computation capabilities. The idea is to first perform an over-segmentation of the image, discarding the unlikely Stixel cuts, and apply the algorithm only on the remaining Stixel cuts. This work presents a novel over-segmentation strategy based on a fully convolutional network, which outperforms an approach based on using local extrema of the disparity map. We evaluate the proposed methods in terms of semantic and geometric accuracy as well as run-time on four publicly available benchmark datasets. Our approach maintains accuracy on flat road scene datasets while improving substantially on a novel non-flat road dataset.
|
|
|
Lluis Pere de las Heras, Ahmed Sheraz, Marcus Liwicki, Ernest Valveny and Gemma Sanchez. 2014. Statistical Segmentation and Structural Recognition for Floor Plan Interpretation. IJDAR, 17(3), 221–237.
Abstract: A generic method for floor plan analysis and interpretation is presented in this article. The method, which is mainly inspired by the way engineers draw and interpret floor plans, applies two recognition steps in a bottom-up manner. First, basic building blocks, i.e., walls, doors, and windows are detected using a statistical patch-based segmentation approach. Second, a graph is generated, and structural pattern recognition techniques are applied to further locate the main entities, i.e., rooms of the building. The proposed approach is able to analyze any type of floor plan regardless of the notation used. We have evaluated our method on different publicly available datasets of real architectural floor plans with different notations. The overall detection and recognition accuracy is about 95 %, which is significantly better than any other state-of-the-art method. Our approach is generic enough such that it could be easily adopted to the recognition and interpretation of any other printed machine-generated structured documents.
|
|
|
Lluis Pere de las Heras, Oriol Ramos Terrades, Sergi Robles and Gemma Sanchez. 2015. CVC-FP and SGT: a new database for structural floor plan analysis and its groundtruthing tool. IJDAR, 18(1), 15–30.
Abstract: Recent results on structured learning methods have shown the impact of structural information in a wide range of pattern recognition tasks. In the field of document image analysis, there is a long experience on structural methods for the analysis and information extraction of multiple types of documents. Yet, the lack of conveniently annotated and free access databases has not benefited the progress in some areas such as technical drawing understanding. In this paper, we present a floor plan database, named CVC-FP, that is annotated for the architectural objects and their structural relations. To construct this database, we have implemented a groundtruthing tool, the SGT tool, that allows to make specific this sort of information in a natural manner. This tool has been made for general purpose groundtruthing: It allows to define own object classes and properties, multiple labeling options are possible, grants the cooperative work, and provides user and version control. We finally have collected some of the recent work on floor plan interpretation and present a quantitative benchmark for this database. Both CVC-FP database and the SGT tool are freely released to the research community to ease comparisons between methods and boost reproducible research.
|
|
|
David Aldavert, Marçal Rusiñol, Ricardo Toledo and Josep Llados. 2015. A Study of Bag-of-Visual-Words Representations for Handwritten Keyword Spotting. IJDAR, 18(3), 223–234.
Abstract: The Bag-of-Visual-Words (BoVW) framework has gained popularity among the document image analysis community, specifically as a representation of handwritten words for recognition or spotting purposes. Although in the computer vision field the BoVW method has been greatly improved, most of the approaches in the document image analysis domain still rely on the basic implementation of the BoVW method disregarding such latest refinements. In this paper, we present a review of those improvements and its application to the keyword spotting task. We thoroughly evaluate their impact against a baseline system in the well-known George Washington dataset and compare the obtained results against nine state-of-the-art keyword spotting methods. In addition, we also compare both the baseline and improved systems with the methods presented at the Handwritten Keyword Spotting Competition 2014.
Keywords: Bag-of-Visual-Words; Keyword spotting; Handwritten documents; Performance evaluation
|
|
|
Carme Julia, Felipe Lumbreras and Angel Sappa. 2011. A Factorization-based Approach to Photometric Stereo. IJIST, 21(1), 115–119.
Abstract: This article presents an adaptation of a factorization technique to tackle the photometric stereo problem. That is to recover the surface normals and reflectance of an object from a set of images obtained under different lighting conditions. The main contribution of the proposed approach is to consider pixels in shadow and saturated regions as missing data, in order to reduce their influence to the result. Concretely, an adapted Alternation technique is used to deal with missing data. Experimental results considering both synthetic and real images show the viability of the proposed factorization-based strategy. © 2011 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 21, 115–119, 2011.
|
|
|
Aura Hernandez-Sabate, Meritxell Joanpere, Nuria Gorgorio and Lluis Albarracin. 2015. Mathematics learning opportunities when playing a Tower Defense Game.
Abstract: A qualitative research study is presented herein with the purpose of identifying mathematics learning opportunities in students between 10 and 12 years old while playing a commercial version of a Tower Defense game. These learning opportunities are understood as mathematicisable moments of the game and involve the establishment of relationships between the game and mathematical problem solving. Based on the analysis of these mathematicisable moments, we conclude that the game can promote problem-solving processes and learning opportunities that can be associated with different mathematical contents that appears in mathematics curricula, thought it seems that teacher or new game elements might be needed to facilitate the processes.
Keywords: Tower Defense game; learning opportunities; mathematics; problem solving; game design
|
|
|
Fadi Dornaika and Angel Sappa. 2009. A Featureless and Stochastic Approach to On-board Stereo Vision System Pose. IMAVIS, 27(9), 1382–1393.
Abstract: This paper presents a direct and stochastic technique for real-time estimation of on-board stereo head’s position and orientation. Unlike existing works which rely on feature extraction either in the image domain or in 3D space, our proposed approach directly estimates the unknown parameters from the stream of stereo pairs’ brightness. The pose parameters are tracked using the particle filtering framework which implicitly enforces the smoothness constraints on the estimated parameters. The proposed technique can be used with a driver assistance applications as well as with augmented reality applications. Extended experiments on urban environments with different road geometries are presented. Comparisons with a 3D data-based approach are presented. Moreover, we provide a performance study aiming at evaluating the accuracy of the proposed approach.
Keywords: On-board stereo vision system; Pose estimation; Featureless approach; Particle filtering; Image warping
|
|
|
Carme Julia, Angel Sappa, Felipe Lumbreras, Joan Serrat and Antonio Lopez. 2010. An Iterative Multiresolution Scheme for SFM with Missing Data: single and multiple object scenes. IMAVIS, 28(1), 164–176.
Abstract: Most of the techniques proposed for tackling the Structure from Motion problem (SFM) cannot deal with high percentages of missing data in the matrix of trajectories. Furthermore, an additional problem should be faced up when working with multiple object scenes: the rank of the matrix of trajectories should be estimated. This paper presents an iterative multiresolution scheme for SFM with missing data to be used in both the single and multiple object cases. The proposed scheme aims at recovering missing entries in the original input matrix. The objective is to improve the results by applying a factorization technique to the partially or totally filled in matrix instead of to the original input one. Experimental results obtained with synthetic and real data sequences, containing single and multiple objects, are presented to show the viability of the proposed approach.
|
|
|
Antonio Lopez and 7 others. 2017. Training my car to see using virtual worlds. IMAVIS, 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.
|
|