检索结果-内蒙古大学图书馆

International Conference on Automatic Face and Gesture Recognition

作者： Tao Zhong Xiaole Xian Zihan Wang Weicheng Xie Linlin Shen Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University

ISBN: (数字)9798350394948

ISBN: (纸本)9798350394955

Cross-database facial expression recognition (CD-FER) has been widely studied due to its promising applicability in real-life situations, while the generalization performance is the main concern in this task. For improving cross-database generalization, current works frequently resort to masked auto encoder (MAE) to learn the expression representation in an unsupervised manner, and disentanglement of expression and domain features. (i) For MAE, current algorithms mainly employ random masking, and leverage the reconstruction of these masked regions to enable networks to learn the expression representation. However, these masked regions are expression-irrelevant, can not well reflect the characteristics of expression, thus are not efficient enough in representation learning. To this end, we propose an expression-aware masking in MAE to improve the learning efficiency of expression representation, by guiding MAE to mask out expression-aware regions during training. (ii) For disentanglement of expression and domain features, current algorithms realize it mainly in the deep layers. However, the coupling of these features in the shallow layers are rarely concerned, which may largely affect the disentanglement performance in deep layers. Thus, we propose a progressive decoupler to disentangle these features block by block, to use the feature disentanglement in shallow layers to facilitate that in deep layers. Extensive quantitative and qualitative results on multiple expression datasets show that our method can largely outperform the state of the arts in terms of cross-database generalization performance.

关键词： Training Representation learning Couplings Face recognition Gesture recognition Task analysis

来源：评论

学校读者我要写书评

暂无评论

Proposal of a parallel architecture for a motion detection algorithm

Proposal of a parallel architecture for a motion detection a...

引用

International Conference on Pattern Recognition

作者： V. Ila R. Garcia F. Charot Computer Vision and Robotics Group Institute of Informatics and Applications Girona Spain Institute de Recherche en Informatique et en Systemes Aleatoires Rennes France

This paper proposes a parallel architecture for estimation of the motion of an underwater robot. It is well known that image processing requires a huge amount of computation, mainly at low-level processing where the algorithms are dealing with a great number of data. In a motion estimation algorithm, correspondences between two images have to be solved at the low level. In the underwater imaging, normalised correlation can be a solution in the presence of non-uniform illumination. Due to its regular processing scheme, parallel implementation of the correspondence problem can be an adequate approach to reduce the computation time. Taking into consideration the complexity of the normalised correlation criteria, a new approach using parallel organisation of every processor from the architecture is proposed.

关键词： Proposals Parallel architectures Motion detection Motion estimation Image processing computer architecture computer vision Robot vision systems Cameras Application software

来源：评论

学校读者我要写书评

暂无评论

Efficient Image Super-Resolution Using Pixel Attention 16th

Efficient Image Super-Resolution Using Pixel Attention

引用

Workshops held at the 16th European Conference on computer vision, ECCV 2020

作者： Zhao, Hengyuan Kong, Xiangtao He, Jingwen Qiao, Yu Dong, Chao ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Beijing China SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9783030670696

This work aims at designing a lightweight convolutional neural network for image super resolution (SR). With simplicity bare in mind, we construct a pretty concise and effective network with a newly proposed pixel attention scheme. Pixel attention (PA) is similar as channel attention and spatial attention in formulation. The difference is that PA produces 3D attention maps instead of a 1D attention vector or a 2D map. This attention scheme introduces fewer additional parameters but generates better SR results. On the basis of PA, we propose two building blocks for the main branch and the reconstruction branch, respectively. The first one—SC-PA block has the same structure as the Self-Calibrated convolution but with our PA layer. This block is much more efficient than conventional residual/dense blocks, for its two-branch architecture and attention scheme. While the second one—U-PA block combines the nearest-neighbor upsampling, convolution and PA layers. It improves the final reconstruction quality with little parameter cost. Our final model—PAN could achieve similar performance as the lightweight networks—SRResNet and CARN, but with only 272K parameters (17.92% of SRResNet and 17.09% of CARN). The effectiveness of each proposed component is also validated by ablation study. The code is available at https://***/zhaohengyuan1/PAN. © 2020, Springer Nature Switzerland AG.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Object recognition using saliency maps and HTM learning

Object recognition using saliency maps and HTM learning

引用

2012 IEEE International Conference on Imaging Systems and Techniques, IST 2012

作者： Kostavelis, Ioannis Nalpantidis, Lazaros Gasteratos, Antonios Laboratory of Robotics and Automation Department of Production and Management Engineering Democritus University of Thrace Vas. Sofias 12 GR-67100 Xanthi Greece Computer Vision and Active Perception Lab. Centre for Autonomous Systems Royal Institute of Technology - KTH SE-100 44 Stockholm Sweden

ISBN: (纸本)9781457717741

In this paper a pattern classification and object recognition approach based on bio-inspired techniques is presented. It exploits the Hierarchical Temporal Memory (HTM) topology, which imitates human neocortex for recognition and categorization tasks. The HTM comprises a hierarchical tree structure that exploits enhanced spatiotemporal modules to memorize objects appearing in various orientations. In accordance with HTM's biological inspiration, human vision mechanisms can be used to preprocess the input images. Therefore, the input images undergo a saliency computation step, revealing the plausible information of the scene, where a human might fixate. The adoption of the saliency detection module releases the HTM network from memorizing redundant information and augments the classification accuracy. The efficiency of the proposed framework has been experimentally evaluated in the ETH-80 dataset, and the classification accuracy has been found to be greater than other HTM systems. © 2012 IEEE.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Elastic modulus imaging using optical flow and image registration

Elastic modulus imaging using optical flow and image registr...

引用

IEEE International Conference on Image Processing

作者： Robert Martí Alison Noble Computer Vision and Robotics Group Institute of Informatics and Applications University of Girona Spain Biomedical Image Analysis Laboratory Institute of Biomedical Engineering University of Oxford UK

Elastography, the imaging technique for estimating the elastic tissue properties, or more specifically elastic modulus imaging, are becoming important diagnosis tools in computer aided diagnosis system, specially focusing on ultrasound and MRI images. This technique still presents unsolved challenges in the analysis of deformations in sequences of images. The aim of this paper is twofold: to evaluate the applicability of the deformation field obtained by state of the art optical flow and image registration algorithms for elastic modulus imaging and to quantitatively evaluate two different methods for estimation of the elastic modulus distribution. Results show that optical-flow methods provide a slightly better reconstruction and that the reconstruction has been shown to be more accurate using the method proposed by Sumi et al.

关键词： Image reconstruction Optical imaging Strain Young's modulus Image registration Lesions

来源：评论

学校读者我要写书评

暂无评论

Pedestrian detection based on LIDAR-driven sliding window and relational parts-based detection

Pedestrian detection based on LIDAR-driven sliding window an...

引用

IEEE Symposium on Intelligent Vehicle

作者： Luciano Oliveira Urbano Nunes Intelligent Vision Research Laboratory Federal University Bahia Brazil Institute of Systems and Robotics Department of Electrical and Computer Engineering University of Coimbra Portugal

The most standard image object detectors are usually comprised of one or multiple feature extractors or classifiers within a sliding window framework. Nevertheless, this type of approach has demonstrated a very limited performance under datasets of cluttered scenes and real life situations. To tackle these issues, LIDAR space is exploited here in order to detect 2D objects in 3D space, avoiding all the inherent problems of regular sliding window techniques. Additionally, we propose a relational parts-based pedestrian detection in a probabilistic non-iid framework. With the proposed framework, we have achieved state-of-the-art performance in a pedestrian dataset gathered in a challenging urban scenario. The proposed system demonstrated superior performance in comparison with pure sliding-window-based image detectors.

关键词： Detectors Laser radar Feature extraction Support vector machines Training Probabilistic logic Vectors

来源：评论

学校读者我要写书评

暂无评论

A non-rigid map fusion-based rgb-depth slam method for endoscopic capsule robots

arXiv

引用

arXiv 2017年

作者： Turan, Mehmet Almalioglu, Yasin Araujo, Helder Konukoglu, Ender Sitti, Metin Max Planck Institute for Intelligent Systems Stuttgart Germany Computer Vision Laboratory ETH Zurich Switzerland Robotics Laboratory University of Coimbra Portugal

In the gastrointestinal (GI) tract endoscopy field, ingestible wireless capsule endoscopy is considered as a minimally invasive novel diagnostic technology to inspect the entire GI tract and to diagnose various diseases and pathologies. Since the development of this technology, medical device companies and many groups have made significant progress to turn such passive capsule endoscopes into robotic active capsule endoscopes to achieve almost all functions of current active flexible endoscopes. However, the use of robotic capsule endoscopy still has some challenges. One such challenge is the precise localization of such active devices in 3D world, which is essential for a precise three-dimensional (3D) mapping of the inner organ. A reliable 3D map of the explored inner organ could assist the doctors to make more intuitive and correct diagnosis. In this paper, we propose to our knowledge for the first time in literature a visual simultaneous localization and mapping (SLAM) method specifically developed for endoscopic capsule robots. The proposed RGB-Depth SLAM method is capable of capturing comprehensive dense globally consistent surfel-based maps of the inner organs explored by an endoscopic capsule robot in real time. This is achieved by using dense frame-to-model camera tracking and windowed surfel-based fusion coupled with frequent model refinement through non-rigid surface deformations. Copyright © 2017, The Authors. All rights reserved.

关键词： Endoscopy

来源：评论

学校读者我要写书评

暂无评论

A fast and accurate 3-D rangefinder using the Biris technology: the TRID sensor

A fast and accurate 3-D rangefinder using the Biris technolo...

引用

International Conference on 3D Imaging, Modeling, Processing, Visualization and Transmission (3DIMPVT)

作者： F. Loranger D. Laurendeau R. Houde Computer Vision and Systems Laboratory (CVSL) Electrical and Computer Engineering Department Laval University QUE Canada Robotics Division Hydro-Quebec Research Institute (IREQ) Varennes Canada

In many industrial applications such as autonomous vehicle guidance and robotic manipulations, reliable 3-D informations must be extracted from the scene in order to provide a robust description of the environment in which the system evolves. This paper presents the TRID sensor, a simple, fast, robust and accurate 3-D sensing device based on the Biris technology. TRID is limited to a lateral resolution of one point. Experimental results show that an accuracy better than 0.15% can be obtained for the depth component (Z) of 3-D points at a distance of 1.3 meter from a wooden black painted beam surface with an acquisition rate of 8.5 points/s.

关键词： Robot vision systems Robustness computer vision Application software Robot kinematics Layout Cameras computer industry Costs Geometrical optics

来源：评论

学校读者我要写书评

暂无评论

Rapid disparity prediction for dynamic scenes

Rapid disparity prediction for dynamic scenes

引用

9th International Symposium on Advances in Visual Computing, ISVC 2013

作者： Jiang, Jun Cheng, Jun Chen, Baowen Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China Chinese University of Hong Kong Hong Kong Hong Kong Shsenzhen Institute of Information Technology China Guangdong Provincial Key Laboratory of Robotics and Intelligent System China Shenzhen Key Laboratory of Computer Vision and Pattern Recognition China

ISBN: (纸本)9783642419133

Real-time 3D sensing plays a critical role in robotic navigation, video surveillance and human-computer interaction, etc. When computing 3D structures of dynamic scenes from stereo sequences, spatiotemporal stereo and scene flow methods can produce temporally coherent disparity. However, most existing methods do not utilize the previous disparity map sufficiently to compute the next disparity map, and the searching space of correspondences limits the speed of disparity computation for each image pair. This paper proposes an effective scheme to predict disparity maps from stereo sequences. In particular, we apply a robust 3D registration algorithm based on the angular-invariant feature to estimate the ego-motion of the stereo rig between consecutive frames, and present the transformation between consecutive disparity maps. The scheme can produce a sequence of temporally coherent disparity maps rapidly. We apply the new scheme to real outdoor scenes, and thorough empirical studies indicate the effectiveness of the new scheme for practical applications. © 2013 Springer-Verlag.

关键词： Human computer interaction

来源：评论

学校读者我要写书评

暂无评论

A vision based aerial robot solution for the Mission 7 of the International Aerial robotics Competition

A vision based aerial robot solution for the Mission 7 of th...

引用

International Conference on Unmanned Aircraft Systems (ICUAS)

作者： Jose Luis Sanchez-Lopez Jesús Pestana Jean-Franois Collumeau Ramon Suarez-Fernandez Pascual Campoy Martin Molina Computer Vision Group Centre for Automation and Robotics Spain Aerial Vision Group Graz University of Technology - TUGraz Austria Robotics Institute Delft University of Technology (TU Delft) Delft The Netherlands Department of Artificial Intelligence Technical University of Madrid (UPM) Spain

ISBN: (纸本)9781479960118

The International Aerial robotics Competition (IARC) aims at pulling forward the state of the art in UAV. The Mission's 7 challenge deals mainly with GPS/Laser denied navigation, Robot-Robot interaction and obstacle avoidance in the setting of a ground robot herding problem. We present in this paper our UAV which took part in the 2014 competition, in the China venue. This year, the mission was not completed by any participant but our team at Technical University of Madrid (UPM) were awarded with two special prizes: Best Target Detection and Best System Control. The platform, hardware and the developed software used in this top leading competition are presented in this paper. This software has three main components: the visual localization and mapping algorithm; the control algorithms; and the mission planner. A statement of the safety measures integrated in the drone and of our efforts to ensure field testing in conditions as close as possible to the challenger's are also included.

关键词： Robots computer architecture Optical sensors Vehicles computers Safety

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：