检索结果-内蒙古大学图书馆

IEEE Symposium on Intelligent Vehicle

作者： Diego Porres Yi Xiao Gabriel Villalonga Alexandre Levy Antonio M. López Computer Vision Center (CVC) Universitat Autònoma de Barcelona (UAB) Spain Dpt. Ciències de la Computació Universitat Autònoma de Barcelona (UAB) Spain

ISBN: (数字)9798350348811

ISBN: (纸本)9798350348828

vision-based end-to-end driving models trained by imitation learning can lead to affordable solutions for autonomous driving. However, training these well-performing models usually requires a huge amount of data, while still lacking explicit and intuitive activation maps to reveal the inner workings of these models while driving. In this paper, we study how to guide the attention of these models to improve their driving quality and obtain more intuitive activation maps by adding a loss term during training using salient semantic maps. In contrast to previous work, our method does not require these salient semantic maps to be available during testing time, as well as removing the need to modify the model’s architecture to which it is applied. We perform tests using perfect and noisy salient semantic maps with encouraging results in both, the latter of which is inspired by possible errors encountered with real data. Using CIL++ as a representative state-of-the-art model and the CARLA simulator with its standard benchmarks, we conduct experiments that show the effectiveness of our method in training better autonomous driving models, especially when data and computational resources are scarce.

关键词： Training Computational modeling Semantics Natural languages computer architecture Benchmark testing Data models

来源：评论

学校读者我要写书评

暂无评论

An augmentation strategy to mimic multi-scanner variability in MRI

arXiv

引用

arXiv 2021年

作者： Meyer, Maria Ines de la Rosa, Ezequiel Barros, Nuno Paolella, Roberto van Leemput, Koen Sima, Diana M. Health Technology Dpt. Technical University of Denmark Lyngby Denmark icometrix Leuven Belgium Dpt. of Computer Science Technical University of Munich Munich Germany imec Vision Lab University of Antwerp Antwerp Belgium Martinos Center for Biomedical Imaging MGH & Harvard Medical School BostonMA United States

Most publicly available brain MRI datasets are very homogeneous in terms of scanner and protocols, and it is difficult for models that learn from such data to generalize to multi-center and multi-scanner data. We propose a novel data augmentation approach with the aim of approximating the variability in terms of intensities and contrasts present in real world clinical data. We use a Gaussian Mixture Model based approach to change tissue intensities individually, producing new contrasts while preserving anatomical information. We train a deep learning model on a single scanner dataset and evaluate it on a multi-center and multi-scanner dataset. The proposed approach improves the generalization capability of the model to other scanners not present in the training data. © 2021, CC BY.

关键词： Scanning

来源：评论

学校读者我要写书评

暂无评论

An Augmentation Strategy to Mimic Multi-Scanner Variability in MRI

An Augmentation Strategy to Mimic Multi-Scanner Variability ...

引用

IEEE International Symposium on Biomedical Imaging

作者： Maria Ines Meyer Ezequiel de la Rosa Nuno Barros Roberto Paolella Koen Van Leemput Diana M. Sima Health Technology Dpt Technical University of Denmark Lyngby Denmark icometrix Leuven Belgium Dpt. of Computer Science Technical University of Munich Munich Germany imec Vision Lab University of Antwerp Antwerp Belgium Martinos Center for Biomedical Imaging MGH & Harvard Medical School Boston MA USA

关键词： Deep learning Protocols Magnetic resonance imaging Biological system modeling Training data Mixture models Brain modeling

来源：评论

学校读者我要写书评

暂无评论

GPU-Accelerated Real-Time Stixel Computation

GPU-Accelerated Real-Time Stixel Computation

引用

IEEE Workshop on Applications of computer vision (WACV)

作者： Daniel Hernandez-Juarez Antonio Espinosa Juan C. Moure David Vázquez Antonio M. López Computer Architecture and Operating Systems Dpt. UAB Computer Vision Center and Computer Science Dpt. UAB

ISBN: (纸本)9781509048236

The Stixel World is a medium-level, compact representation of road scenes that abstracts millions of disparity pixels into hundreds or thousands of stixels. The goal of this work is to implement and evaluate a complete multistixel estimation pipeline on an embedded, energy-efficient, GPU-accelerated device. This work presents a full GPUaccelerated implementation of stixel estimation that produces reliable results at 26 frames per second (real-time) on the Tegra X1 for disparity images of 1024×440 pixels and stixel widths of 5 pixels, and achieves more than 400 frames per second on a high-end Titan X GPU card.

关键词： Dynamic programming Image segmentation Estimation Computational modeling Real-time systems Optimization Roads

来源：评论

学校读者我要写书评

暂无评论

Color spaces emerging from deep convolutional networks 24

Color spaces emerging from deep convolutional networks

引用

24th Color and Imaging Conference: Color science and Engineering Systems, Technologies, and Applications, CIC 2016

作者： Rafegas, Ivet Vanrell, Maria C. Sc. Dpt. UAB Computer Vision Center Bellaterra Barcelona Spain

ISBN: (纸本)9780892083244

Defining color spaces that provide a good encoding of spatio-chromatic properties of color surfaces is an open problem in color science [8, 22]. Related to this, in computer vision the fusion of color with local image features has been studied and evaluated [16]. In human vision research, the cells which are selective to specific color hues along the visual pathway are also a focus of attention [7, 14]. In line with these research aims, in this paper we study how color is encoded in a deep Convolutional Neural Network (CNN) that has been trained on more than one million natural images for object recognition. These convolutional nets achieve impressive performance in computer vision, and rival the representations in human brain. In this paper we explore how color is represented in a CNN architecture that can give some intuition about efficient spatio-chromatic representations. In convolutional layers the activation of a neuron is related to a spatial filter, that combines spatio-chromatic representations. We use an inverted version of it to explore the properties. Using a series of unsupervised methods we classify different type of neurons depending on the color axes they define and we propose an index of color-selectivity of a neuron. We estimate the main color axes that emerge from this trained net and we prove that colorselectivity of neurons decreases from early to deeper layers. © Society for Imaging science and Technology 2016.

关键词： Color

来源：评论

学校读者我要写书评

暂无评论

LGHD: A feature descriptor for matching across non-linear intensity variations

LGHD: A feature descriptor for matching across non-linear in...

引用

IEEE International Conference on Image Processing

作者： Cristhian A. Aguilera Angel D. Sappa Ricardo Toledo Computer Science Dpt. Universitat Autònoma de Barcelona Bellaterra Spain Campus Gustavo Galindo Escuela Superior Politécnica del Litoral Guayaquil Ecuador Campus UAB Computer Vision Center Bellaterra Spain

This paper presents a new feature descriptor suitable to the task of matching features points between images with nonlinear intensity variations. This includes image pairs with significant illuminations changes, multi-modal image pairs and multi-spectral image pairs. The proposed method describes the neighbourhood of feature points combining frequency and spatial information using multi-scale and multi-oriented Log-Gabor filters. Experimental results show the validity of the proposed approach and also the improvements with respect to the state of the art.

关键词： Histograms Feature extraction Robustness Detectors computer vision Three-dimensional displays

来源：评论

学校读者我要写书评

暂无评论

Articulated Particle Filter for hand tracking

Articulated Particle Filter for hand tracking

引用

21st International Conference on Pattern Recognition, ICPR 2012

作者： Ros, German Del Rincón, Jesús Martinez Mateos, Ginés García Computer Vision Center and Computer Science Dpt. UAB Spain Digital Imaging Research Centre Kingston University London United Kingdom Dpt. Informática y Sistemas University of Murcia Spain

ISBN: (纸本)9784990644109

This paper proposes a new version of Particle Filter, called Articulated Particle Filter - ArPF -, which has been specifically designed for an efficient sampling of hierarchical spaces, generated by articulated objects. Our approach decomposes the articulated motion into layers for efficiency purposes, making use of a careful modeling of the diffusion noise along with its propagation through the articulations. This produces an increase of accuracy and prevent for divergences. The algorithm is tested on hand tracking due to its complex hierarchical articulated nature. With this purpose, a new dataset generation tool for quantitative evaluation is also presented in this paper. © 2012 ICPR Org Committee.

关键词： Monte Carlo methods

来源：评论

学校读者我要写书评

暂无评论

Virtual worlds and active learning for human detection 11

Virtual worlds and active learning for human detection

引用

2011 ACM International Conference on Multimodal Interaction, ICMI'11

作者： Vázquez, David López, Antonio M. Ponsa, Daniel Marín, Javier Computer Vision Center Computer Science Dpt. UAB Campus UAB Bellaterra Spain Computer Vision Center Campus UAB Bellaterra Spain

ISBN: (纸本)9781450306416

Image based human detection is of paramount interest due to its potential applications in fields such as advanced driving assistance, surveillance and media analysis. However, even detecting non-occluded standing humans remains a challenge of intensive research. The most promising human detectors rely on classifiers developed in the discriminative paradigm, i.e. trained with labelled samples. However, labelling is a manual intensive step, especially in cases like human detection where it is necessary to provide at least bounding boxes framing the humans for training. To overcome such problem, some authors have proposed the use of a virtual world where the labels of the different objects are obtained automatically. This means that the human models (classifiers) are learnt using the appearance of rendered images, i.e. using realistic computer graphics. Later, these models are used for human detection in images of the real world. The results of this technique are surprisingly good. However, these are not always as good as the classical approach of training and testing with data coming from the same camera, or similar ones. Accordingly, in this paper we address the challenge of using a virtual world for gathering (while playing a videogame) a large amount of automatically labelled samples (virtual humans and background) and then training a classifier that performs equal, in real-world images, than the one obtained by equally training from manually labelled real-world samples. For doing that, we cast the problem as one of domain adaptation. In doing so, we assume that a small amount of manually labelled samples from real-world images is required. To collect these labelled samples we propose a non-standard active learning technique. Therefore, ultimately our human model is learnt by the combination of virtual and real world labelled samples, which has not been done before. © 2011 ACM.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Color contribution to part-based person detection in different types of scenarios

引用

Lecture Notes in computer science

作者： Rao, Muhammad Anwer Vázquez, David López, Antonio M. Computer Vision Center Computer Science Dpt. Universitat Autònoma de Barcelona 08193 Barcelona Spain

ISBN: (纸本)9783642236778

Camera-based person detection is of paramount interest due to its potential applications. The task is difficult because the great variety of backgrounds (scenarios, illumination) in which persons are present, as well as their intra-class variability (pose, clothe, occlusion). In fact, the class person is one of the included in the popular PASCAL visual object classes (VOC) challenge. A breakthrough for this challenge, regarding person detection, is due to Felzenszwalb et al These authors proposed a part-based detector that relies on histograms of oriented gradients (HOG) and latent support vector machines (LatSVM) to learn a model of the whole human body and its constitutive parts, as well as their relative position. Since the approach of Felzenszwalb et al appeared new variants have been proposed, usually giving rise to more complex models. In this paper, we focus on an issue that has not attracted sufficient interest up to now. In particular, we refer to the fact that HOG is usually computed from RGB color space, but other possibilities exist and deserve the corresponding investigation. In this paper we challenge RGB space with the opponent color space (OPP), which is inspired in the human vision system. We will compute the HOG on top of OPP, then we train and test the part-based human classifier by Felzenszwalb et al. using PASCAL VOC challenge protocols and person database. Our experiments demonstrate that OPP outperforms RGB. We also investigate possible differences among types of scenarios: indoor, urban and countryside. Interestingly, our experiments suggest that the benefits of OPP with respect to RGB mainly come for indoor and countryside scenarios, those in which the human visual system was designed by evolution. © 2011 Springer-Verlag.

关键词： RGB color model

来源：评论

学校读者我要写书评

暂无评论

Opponent colors for human detection

Opponent colors for human detection

引用

Lecture Notes in computer science

作者： Muhammad Anwer, Rao Vázquez, David López, Antonio M. Computer Vision Center Computer Science Dpt. Universitat Autònoma de Barcelona 08193 Bellaterra Barcelona Spain

ISBN: (纸本)9783642212567

Human detection is a key component in fields such as advanced driving assistance and video surveillance. However, even detecting non-occluded standing humans remains a challenge of intensive research. Finding good features to build human models for further detection is probably one of the most important issues to face. Currently, shape, texture and motion features have deserve extensive attention in the literature. However, color-based features, which are important in other domains (e.g., image categorization), have received much less attention. In fact, the use of RGB color space has become a kind of choice by default. The focus has been put in developing first and second order features on top of RGB space (e.g., HOG and co-occurrence matrices, resp.). In this paper we evaluate the opponent colors (OPP) space as a biologically inspired alternative for human detection. In particular, by feeding OPP space in the baseline framework of Dalal et al. for human detection (based on RGB, HOG and linear SVM), we will obtain better detection performance than by using RGB space. This is a relevant result since, up to the best of our knowledge, OPP space has not been previously used for human detection. This suggests that in the future it could be worth to compute co-occurrence matrices, self-similarity features, etc., also on top of OPP space, i.e., as we have done with HOG in this paper. © 2011 Springer-Verlag.

关键词： Security systems

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：