检索结果-内蒙古大学图书馆

2017 International Conference on Watermarking and Image Processing, ICWIP 2017

作者： Lee, Kevin Moloney, David Computer Vision and Machine Learning Group Intel/Movidius United States

ISBN: (纸本)9781450353076

Stereo vision is a very active field in the realm of computer vision and in recent years Convolutional Neural Networks (CNNs) have proven to be very competitive against the state-of-the-art. However, the performance of these networks are limited by the quality of the data that is used when training the CNNs. Data acquisition of high quality labeled images is a time-consuming and expensive process. By exploiting the power of modern-day powerful GPUs, we present a synthetic data-set with fully rectified stereo image pairs and accompanying accurate ground truth information that can be used for training and testing stereo algorithms. We provide validation of the quality of our dataset by performing quantitative experiments that suggest pre-training deep learning algorithms on synthetic data can perform competitively against networks trained on real life data. Testing on a real-world data-set, we found the accuracy performance difference between the real and synthetically trained networks was within a margin of 1.8%. We also illustrate the functionality synthetic data can provide, by conducting a key performance index on a selection of conventional and deep learning stereo algorithms available on embedded platforms and compared them under common metrics. © 2017 Association for Computing machinery.

关键词： Stereo vision

来源：评论

学校读者我要写书评

暂无评论

Cross-dimensional weighting for aggregated deep convolutional features 14

Cross-dimensional weighting for aggregated deep convolutiona...

引用

computer vision - ECCV 2016 Workshops, Proceedings

作者： Kalantidis, Yannis Mellina, Clayton Osindero, Simon Computer Vision and Machine Learning Group Flickr Yahoo San Francisco United States

ISBN: (纸本)9783319466033

We propose a simple and straightforward way of creating powerful image representations via cross-dimensional weighting and aggregation of deep convolutional neural network layer outputs. We first present a generalized framework that encompasses a broad family of approaches and includes cross-dimensional pooling and weighting steps. We then propose specific non-parametric schemes for both spatial-and channel-wise weighting that boost the effect of highly active spatial responses and at the same time regulate burstiness effects. We experiment on different public datasets for image search and show that our approach outperforms the current state-of-the-art for approaches based on pre-trained networks. We also provide an easy-to-use, open source implementation that reproduces our results. © Springer International Publishing Switzerland 2016.

关键词： Network layers

来源：评论

学校读者我要写书评

暂无评论

On the Implementation of Baselines and Lightweight Conditional Model Extrapolation (LIMES) Under Class-Prior Shift 4th

On the Implementation of Baselines and Lightweight Condit...

引用

Fourth International Workshop on Reproducible Research in Pattern Recognition, RRPR 2022

作者： Tomaszewska, Paulina Lampert, Christoph H. Warsaw University of Technology Faculty of Mathematics and Information Science Warsaw Poland Machine Learning and Computer Vision Group Klosterneuburg Austria

ISBN: (纸本)9783031407727

This paper focuses on the implementation details of the baseline methods and a recent lightweight conditional model extrapolation algorithm LIMES [5] for streaming data under class-prior shift. LIMES achieves superior performance over the baseline methods, especially concerning the minimum-across-day accuracy, which is important for the users of the system. In this work, the key measures to facilitate reproducibility and enhance the credibility of the results are described. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Lime

来源：评论

学校读者我要写书评

暂无评论

Applications of the VOLA Format for 3D Data Knowledge Discovery.

Applications of the VOLA Format for 3D Data Knowledge Discov...

引用

International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery

作者： Jonathan Byrne Sam Caulfield Léonie Buckley Xiaofan Xu Dexmont Pena Gary Baugh David Moloney Computer Vision and Machine Learning Group Movidius / Intel

VOLA is a compact data structure that unifies computer vision and 3D rendering and allows for the rapid calculation of connected components, per-voxel census/accounting, CNN inference, path planning and obstacle avoidance. Using a hierarchical bit array format allows it to run efficiently on embedded systems and maximize the level of data compression. The proposed format allows massive scale volumetric data to be used in embedded applications where it would be inconceivable to utilize point-clouds due to memory constraints. Furthermore, geographical and qualitative data is embedded in the file structure to allow it to be used in place of standard point cloud formats. This work examines the reduction in file size when encoding 3D data using the VOLA format and finds that it is an order of magnitude smaller than the current binary standard for point cloud data.

关键词： Point Clouds Embedded Systems Auralisation Deep learning GIS

来源：评论

学校读者我要写书评

暂无评论

Robust Autonomous Vehicle Pursuit Without Expert Steering Labels

引用

IEEE Robotics and Automation Letters 2023年第10期8卷 6595-6602页

作者： Pan, Jiaxin Zhou, Changyao Gladkova, Mariia Khan, Qadeer Cremers, Daniel Technical University of Munich Computer Vision Group Garching85748 Germany Munich Data Science Institute Garching85748 Germany Munich Center for Machine Learning Munchen80333 Germany University of Oxford OxfordOX1 3AZ United Kingdom

In this work, we present a learning method for both lateral and longitudinal motion control of an ego-vehicle for the task of vehicle pursuit. The car being controlled does not have a pre-defined route, rather it reactively adapts to follow a target vehicle while maintaining a safety distance. To train our model, we do not rely on steering labels recorded from an expert driver, but effectively leverage a classical controller as an offline label generation tool. In addition, we account for the errors in the predicted control values, which can lead to a loss of tracking and catastrophic crashes of the controlled vehicle. To this end, we propose an effective data augmentation approach, which allows to train a network that is capable of handling different views of the target vehicle. During the pursuit, the target vehicle is firstly localized using a Convolutional Neural Network. The network takes a single RGB image along with cars' velocities and estimates target vehicle's pose with respect to the ego-vehicle. This information is then fed to a Multi-Layer Perceptron, which regresses the control commands for the ego-vehicle, namely throttle and steering angle. We extensively validate our approach using the CARLA simulator on a wide range of terrains. Our method demonstrates real-time performance, robustness to different scenarios including unseen trajectories and high route completion. © 2016 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

LOH and behold: Web-scale visual search, recommendation and clustering using locally optimized hashing 14

LOH and behold: Web-scale visual search, recommendation and ...

引用

computer vision - ECCV 2016 Workshops, Proceedings

作者： Kalantidis, Yannis Kennedy, Lyndon Nguyen, Huy Mellina, Clayton Shamma, David A. Computer Vision and Machine Learning Group Flickr Yahoo San Francisco United States Futurewei Technologies Inc Santa Clara United States CWI: Centrum Wiskunde and Informatica Amsterdam Netherlands

ISBN: (纸本)9783319466033

We propose a novel hashing-based matching scheme, called Locally Optimized Hashing (LOH), based on a state-of-the-art quantization algorithm that can be used for efficient, large-scale search, recommendation, clustering, and deduplication. We show that matching with LOH only requires set intersections and summations to compute and so is easily implemented in generic distributed computing systems. We further show application of LOH to: (a) large-scale search tasks where performance is on par with other state-of-the-art hashing approaches (b) large-scale recommendation where queries consisting of thousands of images can be used to generate accurate recommendations from collections of hundreds of millions of images;and (c) efficient clustering with a graph-based algorithm that can be scaled to massive collections in a distributed environment or can be used for deduplication for small collections, like search results, performing better than traditional hashing approaches while only requiring a few milliseconds to run. In this paper we experiment on datasets of up to 100 million images, but in practice our system can scale to larger collections and can be used for other types of data that have a vector representation in a Euclidean space. © Springer International Publishing Switzerland 2016.

关键词： Vector spaces

来源：评论

学校读者我要写书评

暂无评论

A survey of historical document image datasets

A survey of historical document image datasets

引用

作者： Nikolaidou, Konstantina Seuret, Mathias Mokayed, Hamam Liwicki, Marcus EISLAB Machine Learning Group Luleå University of Technology Aurorum 1 Norrbotten Luleå97187 Sweden Pattern Recognition Lab Computer Vision Group Friedrich-Alexander-Universität Martensstr. 3 Bavaria Erlangen91058 Germany

This paper presents a systematic literature review of image datasets for document image analysis, focusing on historical documents, such as handwritten manuscripts and early prints. Finding appropriate datasets for historical document analysis is a crucial prerequisite to facilitate research using different machine learning algorithms. However, because of the very large variety of the actual data (e.g., scripts, tasks, dates, support systems, and amount of deterioration), the different formats for data and label representation, and the different evaluation processes and benchmarks, finding appropriate datasets is a difficult task. This work fills this gap, presenting a meta-study on existing datasets. After a systematic selection process (according to PRISMA guidelines), we select 65 studies that are chosen based on different factors, such as the year of publication, number of methods implemented in the article, reliability of the chosen algorithms, dataset size, and journal outlet. We summarize each study by assigning it to one of three pre-defined tasks: document classification, layout structure, or content analysis. We present the statistics, document type, language, tasks, input visual aspects, and ground truth information for every dataset. In addition, we provide the benchmark tasks and results from these papers or recent competitions. We further discuss gaps and challenges in this domain. We advocate for providing conversion tools to common formats (e.g., COCO format for computer vision tasks) and always providing a set of evaluation metrics, instead of just one, to make results comparable across studies. © 2022, The Author(s).

关键词： Deterioration

来源：评论

学校读者我要写书评

暂无评论

Click-Free, Video-Based Document Capture - Methodology and Evaluation

Click-Free, Video-Based Document Capture - Methodology and E...

引用

International Conference on Document Analysis and Recognition

作者： Waqas Tariq Nazar Khan Computer Vision & Machine Learning Group Punjab University College of Information Technology Lahore Pakistan

We propose a click-free method for video-based digitization of multi-page documents. The work is targeted at the non-commercial, low-volume, home user. The document is viewed through a mounted camera and the user is only required to turn pages manually while the system automatically extracts the video frames representing stationary document pages. This is in contrast to traditional document conversion approaches such as photocopying and scanning which can be time-consuming, repetitive, redundant and can lead to document deterioration. Main contributions of our work are i) a 3-step method for automatic extraction of unique, stable and clear document pages from video, ii) a manually annotated data set of 37 videos consisting of 763 page turn events covering a large variety of documents, and iii) a soft, quantitative evaluation criterion that is highly correlated with the hard F 1 -measure. The criterion is motivated by the need to counter the subjectivity in human marked ground truth for videos. On our data set, we report an F 1 -measure of 0.91 and a soft score of 0.94 for the page extraction task.

关键词： Cameras Task analysis Standards Detectors Text analysis Optical distortion

来源：评论

学校读者我要写书评

暂无评论

Multi-Vehicle Trajectory Prediction at Intersections using State and Intention Information

arXiv

引用

arXiv 2023年

作者： Zhu, Dekai Khan, Qadeer Cremers, Daniel Computer Vision Group CIT Technical University of Munich This work was funded by the Munich Center for Machine Learning Germany

Traditional approaches to prediction of future trajectory of road agents rely on knowing information about their past trajectory. This work rather relies only on having knowledge of the current state and intended direction to make predictions for multiple vehicles at intersections. Furthermore, message passing of this information between the vehicles provides each one of them a more holistic overview of the environment allowing for a more informed prediction. This is done by training a neural network which takes the state and intent of the multiple vehicles to predict their future trajectory. Using the intention as an input allows our approach to be extended to additionally control the multiple vehicles to drive towards desired paths. Experimental results demonstrate the robustness of our approach both in terms of trajectory prediction and vehicle control at intersections. The complete training and evaluation code for this work is available here: https:// ***/Dekai21/Multi_Agent_Intersection. Copyright © 2023, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Constrained parametric min-cuts for automatic object segmentation

Constrained parametric min-cuts for automatic object segment...

引用

Conference on computer vision and Pattern Recognition (CVPR)

作者： Joao Carreira Cristian Sminchisescu Computer Vision and Machine Learning Group Institute for Numerical Simulation Faculty of Mathematics and Natural Sciences University of Bonn Germany

We present a novel framework for generating and ranking plausible objects hypotheses in an image using bottom-up processes and mid-level cues. The object hypotheses are represented as figure-ground segmentations, and are extracted automatically, without prior knowledge about properties of individual object classes, by solving a sequence of constrained parametric min-cut problems (CPMC) on a regular image grid. We then learn to rank the object hypotheses by training a continuous model to predict how plausible the segments are, given their mid-level region properties. We show that this algorithm significantly outperforms the state of the art for low-level segmentation in the VOC09 segmentation dataset. It achieves the same average best segmentation covering as the best performing technique to date, 0.61 when using just the top 7 ranked segments, instead of the full hierarchy in. Our method achieves 0.78 average best covering using 154 segments. In a companion paper, we also show that the algorithm achieves state-of-the art results when used in a segmentation-based recognition pipeline.

关键词： Object segmentation Image segmentation machine learning Art Humans machine learning algorithms computer vision Numerical simulation Mathematics Predictive models

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：