检索结果-内蒙古大学图书馆

arXiv 2017年

作者： Ohn-Bar, Eshed Trivedi, Mohan M. Computer Vision and Robotics Research Laboratory University of California San Diego

We aim to study the modeling limitations of the commonly employed boosted decision trees classifier. Inspired by the success of large, data-hungry visual recognition models (e.g. deep convolutional neural networks), this paper focuses on the relationship between modeling capacity of the weak learners, dataset size, and dataset properties. A set of novel experiments on the Caltech Pedestrian Detection benchmark results in the best known performance among non-CNN techniques while operating at fast run-time speed. Furthermore, the performance is on par with deep architectures (9.71% log-average miss rate), while using only HOG+LUV channels as features. The conclusions from this study are shown to generalize over different object detection domains as demonstrated on the FDDB face detection benchmark (93.37% accuracy). Despite the impressive performance, this study reveals the limited modeling capacity of the common boosted trees model, motivating a need for architectural changes in order to compete with multi-level and very deep architectures. Copyright © 2017, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Detection and localization with multi-scale models

Detection and localization with multi-scale models

引用

International Conference on Pattern Recognition

作者： Eshed Ohn-Bar Mohan M. Trivedi Computer Vision and Robotics Research Laboratory University of California San Diego

ISBN: (纸本)9781509048489

Object detection and localization in images involve a multi-scale reasoning process. First, responses of object detectors are known to vary with image scale. Second, contextual relationships on a part-level, object-level, and scene-level appear at different scales of the image. This paper studies efficient modeling of these two components by training multi-scale template models. The input to the proposed algorithm involves image features computed at varying image scales, hence operating on volumes in the feature pyramid. The approach generalizes single-scale, local-region detection approaches (e.g. sliding window or region proposals), jointly learning detection and localization cues. Extending the common single-scale detection to a multi-scale volume allows learning scale-specific models as well as analyzing the importance of contextual information at different scales. Experimental analysis on the PASCAL VOC dataset shows the method to considerably improve both detection and localization performance for different type of features, histogram of oriented gradients and deep convolutional neural network features.

关键词： Feature extraction Training Automobiles Pipelines Computational modeling Analytical models Image resolution

来源：评论

学校读者我要写书评

暂无评论

Fast and Robust Object Detection Using Visual Subcategories

Fast and Robust Object Detection Using Visual Subcategories

引用

IEEE computer Society Conference on computer vision and Pattern Recognition Workshops (CVPRW)

作者： Eshed Ohn-Bar Mohan M. Trivedi Computer Vision and Robotics Research Laboratory University of California San Diego

Object classes generally contain large intra-class variation, which poses a challenge to object detection schemes. In this work, we study visual subcategorization as a means of capturing appearance variation. First, training data is clustered using color and gradient features. Second, the clustering is used to learn an ensemble of models that capture visual variation due to varying orientation, truncation, and occlusion degree. Fast object detection is achieved with integral image features and pixel lookup features. The framework is studied in the context of vehicle detection on the challenging KITTI dataset.

关键词： Vehicles Visualization Feature extraction Vehicle detection Image color analysis Support vector machines Detectors

来源：评论

学校读者我要写书评

暂无评论

What makes an on-road object important?

What makes an on-road object important?

引用

International Conference on Pattern Recognition

作者： Eshed Ohn-Bar Mohan M. Trivedi Computer Vision and Robotics Research Laboratory University of California San Diego

ISBN: (纸本)9781509048489

Human drivers continuously attend to important scene elements in order to safely and smoothly navigate in intricate environments and under uncertainty. This paper develops a human-centric framework for object recognition by analyzing a notion of object importance, as measured in a spatio-temporal context of driving a vehicle. Given a video, a main research question in this paper is - which of the surrounding agents are most important? The answer inherently requires complex reasoning over the current driving task, object properties, scene context, intent, and possible future actions. Therefore, we find that various spatio-temporal cues are relevant for the importance classification task. Furthermore, we demonstrate the usefulness of the importance annotations in evaluating vision algorithms (specifically, for the task of object detection) in an application where trust in automation is imperative and errors are costly. Finally, we show that importance-guided training of object detection models results in improved detection performance of surrounding objects of higher importance. Hence, such models may be better suited for use in representing safety-critical situations, predicting surrounding agents' intentions, and in human-robot interactivity. The dataset and code will be made publicly available.

关键词： Context Predictive models Navigation Training Computational modeling Three-dimensional displays Visualization

来源：评论

学校读者我要写书评

暂无评论

A robust method to predict temporal aspects of actions by observation

A robust method to predict temporal aspects of actions by ob...

引用

IEEE International Conference on robotics and Automation

作者： Emmanouil Hourdakis Panos Trahanias Computational Vision and Robotics laboratory of the Foundation for Research and Technology - Hellas Computer Science in the University of Crete Computational Vision and Robotics laboratory of the Foundation for Research and Technology - Hellas

The ability to predict the duration of an activity can enable a robot to plan its behaviors ahead, interact seamlessly with other humans, by coordinating its actions, and allocate effort and resources to tasks that are time-constrained or critical. Despite its usefulness, models that examine the temporal properties of an activity remain relatively unexplored. In the current paper we present, to the best of our knowledge, the first method that can estimate temporal properties of an activity by observation. We evaluate it on three use-cases (i) wiping a table, (ii) chopping vegetables and (iii) cleaning the floor, using ground truth data from real demonstrations, and show that it can make predictions with high accuracy and little training. In addition, we investigate different methods to approximate the progress of each task, and demonstrate how a model can generalize, by reusing part of it in different activities.

关键词： Task analysis Frequency modulation Motion segmentation Predictive models Process control

来源：评论

学校读者我要写书评

暂无评论

SAVIC: A SIMULATION, VISUALIZATION AND INTERACTIVE CONTROL ENVIRONMENT FOR MOBILE ROBOTS

引用

International Journal of Pattern Recognition and Artificial Intelligence 1993年第1期7卷 123-144页

作者： CHUXIN CHEN MOHAN M. TRIVEDI Computer Vision and Robotics Research Laboratory Department of Electrical and Computer Engineering The University of Tennessee Knoxville TN 37996–2100 USA

A Simulation, Animation, Visualization and Interactive Control (SAVIC) environment has been developed for the design and operation of an integrated robotic manipulator system. This unique system possesses the abilities for (1) multi-sensor simulation, (2) kinematics and locomotion animation, (3) dynamic motion and manipulation animation, (4) transformation between real and virtual modes within the same graphics system, (5) ease in exchanging software modules and hardware devices between real and virtual world operations, and (6) interfacing with a real robotic system. This research is focused on enhancing the overall productivity of an integrated human-robot system. This paper describes a working system and illustrates the concepts by presenting the simulation, animation and control methodologies for a unique mobile robot with articulated tracks, a manipulator, and sensory modules.

关键词： Sensor-based robotics intelligent human-machine interface real-time robot simulation sensor simulation visualization virtual reality interactive control

来源：评论

学校读者我要写书评

暂无评论

Human body modelling and tracking using volumetric representation: Selected recent studies and possibilities for extensions

Human body modelling and tracking using volumetric represent...

引用

ACM/IEEE International Conference on Distributed Smart Cameras, ICDSC

作者： Cuong Tran Mohan M. Trivedi Computer Vision and Robotics Research Laboratory University of California San Diego USA

Articulated human body modeling and tracking from vision data is an attractive research area with many potential applications. There has been a tremendous amount of related research works in this area. Therefore, having a comprehensive insight into high quality existing works and awareness of the research frontier in the area is essential for follow-up research studies. With that objective, this paper provides a review of the subarea of model based methods for human body modeling and tracking using volumetric (voxel) data. We will focus on analyzing and comparing some recent techniques, especially which are in the past two years, in order to highlight trends in the domain as well as to point out limitations of the current state of the art. Based on this analysis, we will discuss our idea of combining Laplacian Eigenspace (LE) based voxel segmentation [20] and Kinematically Constrained Gaussian mixture model (KC-GMM) method [3] to have a more powerful human body pose estimation system as well as discuss other possibilities for future work.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Learning multi-lane trajectories using vehicle-based vision

Learning multi-lane trajectories using vehicle-based vision

引用

International Conference on computer vision Workshops (ICCV Workshops)

作者： Sayanan Sivaraman Brendan Morris Mohan Trivedi Computer Vision and Robotics Research Laboratory University of California San Diego USA

Safe operation of a motor vehicle requires awareness of the current traffic situation as well as the ability to predict future maneuvers. In order to provide an intelligent vehicle the ability to make predictions, this work proposes a framework for understanding the driving situation based on vehicle mounted vision sensors. Vehicles are tracked using Kalman filtering based on a vision-based system that detects and tracks using a combination of monocular and stereo-vision. The vehicles' full trajectories are recorded, and a data-driven learning framework has been applied to automatically learn surround behaviors. By learning based on observations, the ADAS system is being trained by experience. Learned trajectories have been compared between dense and free-flowing traffic conditions. Preliminary experimental results using real-world multi-lane highways show the basic promise of this approach. Future research directions are discussed.

关键词： Vehicles Trajectory Hidden Markov models Mathematical model Detectors Equations Training

来源：评论

学校读者我要写书评

暂无评论

Robust real-time detection, tracking, and pose estimation of faces in video streams

Robust real-time detection, tracking, and pose estimation of...

引用

International Conference on Pattern Recognition

作者： K.S. Huang M.M. Trivedi Computer Vision and Robotics Research Laboratory University of California San Diego USA

Robust human face analysis has been recognized as a crucial part in intelligent systems. In this paper, we present the development of a computational framework for robust detection, tracking, and pose estimation of faces captured by video arrays. We discuss the development of a multi-primitive skin-tone and edge-based detection module embedded in a tracking module for efficient and robust face detection and tracking. A continuous density HMM based pose estimation is developed for an accurate estimate of the face orientation motions. Experimental evaluations of these algorithms suggest the validity of the proposed framework and its computational modules.

关键词： Face detection Streaming media Face recognition Cameras Skin Humans Intelligent systems Noise robustness computer vision Intelligent robots

来源：评论

学校读者我要写书评

暂无评论

Maintaining the identity of multiple vehicles as they travel through a video network

Maintaining the identity of multiple vehicles as they travel...

引用

IEEE Workshop on Multi-Object Tracking

作者： G.T. Kogut M.M. Trivedi Computer Vision and Robotics Research Laboratory University of California San Diego USA

ISBN: (纸本)0769511716

Large vision infrastructures have been installed, or are under construction in many major metropolitan areas. These networks of cameras offer enormous volumes of data from large areas. However, most work in ITS computer vision is constricted to the use of either single cameras, or small numbers of cameras. There is an enormous amount of information available from the fusion of data from multiple cameras that is not available from any single sensor. This paper presents an algorithm that provides an example of such data fusion: maintaining the identity of a vehicle, or groups of vehicles as they pass through multiple cameras sites. The algorithm uses a combination of color features and the spatial organization of vehicles within platoons to minimize false positives. The algorithm could be used in an application to track individual cars as they travel long distances through a traffic system allowing the measurement of point-to-point traffic parameters, such as travel time.

关键词： Cameras Telecommunication traffic Vehicle detection Costs Sensor systems Hardware Traffic control Bandwidth Internet Fuses

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：