检索结果-内蒙古大学图书馆

Domain and View-Point Agnostic Hand Action Recognition

IEEE ROBOTICS AND AUTOMATION LETTERS 2021年第4期6卷 7823-7830页

作者： Sabater, Alberto Alonso, Inigo Montesano, Luis Murillo, Ana Cristina Univ Zaragoza DIIS I3A Zaragoza 50018 Spain Bitbrain Technol Zaragoza 50008 Spain

Hand action recognition is a special case of action recognition with applications in human-robot interaction, virtual reality or life-logging systems. Building action classifiers able to work for such heterogeneous action domains is very challenging. There are very subtle changes across different actions from a given application but also large variations across domains (e.g. virtual reality vs life-logging). This work introduces a novel skeleton-based hand motion representation model that tackles this problem. The framework we propose is agnostic to the application domain or camera recording view-point. When working on a single domain (intra-domain action classification) our approach performs better or similar to current state-of-the-art methods on well-known hand action recognition benchmarks. And, more importantly, when performing hand action recognition for action domains and camera perspectives which our approach has not been trained for (cross-domain action classification), our proposed framework achieves comparable performance to intra-domain state-of-the-art methods. These experiments show the robustness and generalization capabilities of our framework.

关键词： Human and humanoid motion analysis and synthesis gesture posture and facial expressions deep learning for visual perception

来源：评论

学校读者我要写书评

暂无评论

Uncertainty-Aware Self-Supervised learning of Spatial perception Tasks

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2021年第4期6卷 6693-6700页

作者： Nava, Mirko Paolillo, Antonio Guzzi, Jerome Gambardella, Luca Maria Giusti, Alessandro USI SUPSI Dalle Molle Inst Artificial Intelligence IDSIA CH-6928 Lugano Switzerland

We propose a general self-supervised learning approach for spatial perception tasks, such as estimating the pose of an object relative to the robot, from onboard sensor readings. The model is learned from training episodes, by relying on: A continuous state estimate, possibly inaccurate and affected by odometry drift;and a detector, that sporadically provides supervision about the target pose. We demonstrate the general approach in three different concrete scenarios: a simulated robot arm that visually estimates the pose of an object of interest;a small differential drive robot using 7 infrared sensors to localize a nearby wall;an omnidirectionalmobile robot that localizes itself in an environment from camera images. Quantitative results show that the approach works well in all three scenarios, and that explicitly accounting for uncertainty yields statistically significant performance improvements. Videos, datasets, and code to reproduce our results are available at: https://***/idsia-robotics/uncertainty-awaressl-spatial- perception.

关键词： deep learning for visual perception deep learning methods

来源：评论

学校读者我要写书评

暂无评论

PVStereo: Pyramid Voting Module for End-to-End Self-Supervised Stereo Matching

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2021年第3期6卷 4353-4360页

作者： Wang, Hengli Fan, Rui Cai, Peide Liu, Ming Hong Kong Univ Sci & Technol Dept Elect & Comp Engn Kowloon Hong Kong 999077 Peoples R China Univ Calif San Diego Dept Comp Sci & Engn & Dept Ophthalmol La Jolla CA 92093 USA

Supervised learning with deep convolutional neural networks (DCNNs) has seen huge adoption in stereo matching. However, the acquisition of large-scale datasets with well-labeled ground truth is cumbersome and labor-intensive, making supervised learning-based approaches often hard to implement in practice. To overcome this drawback, we propose a robust and effective self-supervised stereo matching approach, consisting of a pyramid voting module (PVM) and a novel DCNN architecture, referred to as OptStereo. Specifically, our OptStereo first builds multi-scale cost volumes, and then adopts a recurrent unit to iteratively update disparity estimations at high resolution;while our PVM can generate reliable semi-dense disparity images, which can be employed to supervise OptStereo training. Furthermore, we publish the HKUST-Drive dataset, a large-scale synthetic stereo dataset, collected under different illumination and weather conditions for research purposes. Extensive experimental results demonstrate the effectiveness and efficiency of our self-supervised stereo matching approach on the KITTI Stereo benchmarks and our HKUST-Drive dataset. PVStereo, our best-performing implementation, greatly outperforms all other state-of-the-art self-supervised stereo matching approaches. Our project page is available at ***/view/pvstereo.

关键词： Computer vision for automation data sets for robotic vision deep learning for visual perception

来源：评论

学校读者我要写书评

暂无评论

FoV-Net: Field-of-View Extrapolation Using Self-Attention and Uncertainty

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2021年第3期6卷 4321-4328页

作者： Ma, Liqian Georgoulis, Stamatios Jia, Xu Van Gool, Luc Katholieke Univ Leuven Dept Elect Engn B-3001 Leuven Belgium Swiss Fed Inst Technol Dept Informat Technol & Elect Engn CH-8092 Zurich Switzerland Dalian Univ Technol Sch Artificial Intelligence Dalian 116024 Peoples R China ETH Zilch Dept Informat Technol & Elect Engn CH-8092 Zurich Switzerland

The ability to make educated predictions about their surroundings, and associate them with certain confidence, is important for intelligent systems, like autonomous vehicles and robots. It allows them to plan early and decide accordingly. Motivated by this observation, in this letter we utilize information from a video sequence with a narrow field-of-view to infer the scene at a wider field-of-view. To this end, we propose a temporally consistent field-of-view extrapolation framework, namely FoV-Net, that: (1) leverages 3D information to propagate the observed scene parts from past frames;(2) aggregates the propagated multi-frame information using an attention-based feature aggregation module and a gated self-attention module, simultaneously hallucinating any unobserved scene parts;and (3) assigns an interpretable uncertainty value at each pixel. Extensive experiments show that FoV-Net does not only extrapolate the temporally consistent wide field-of-view scene better than existing alternatives, but also provides the associated uncertainty which may benefit critical decision-making downstream applications. Project page is at http://***/RAL21_FoV.

关键词： Computer vision for automation deep learning for visual perception visual learning

来源：评论

学校读者我要写书评

暂无评论

Joint Plant Instance Detection and Leaf Count Estimation for In-Field Plant Phenotyping

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2021年第2期6卷 3599-3606页

作者： Weyler, Jan Milioto, Andres Falck, Tillmann Behley, Jens Stachniss, Cyrill Univ Bonn Photogrammetry & Robot D-53115 Bonn Germany Robert Bosch GmbH Bosch Res Autonomous Syst D-71272 Renningen Germany

Precision management of agricultural fields as well as plant breeding are central factors for keeping yields high and to provide food, feed, and fiber for our society. A key element in breeding trials but also for targeted management actions is to analyze the growth state of individual plants objectively and at a large scale. In this letter, we address the problem of analyzing crops in real agricultural fields based on camera data recorded with mobile robots and to derive information about the plant development, e.g., to monitor phenotypic traits such as growth stage. We propose a novel single-stage object detection approach that localizes crops and weeds in the field. At the same time, it detects plant-specific leaf keypoints intending to estimate leaf count at a plant level, which is a key trait for classifying the growth stage. We implemented and thoroughly tested our approach on real sugar beet fields. As our experiments show, it performs the required detections and shows superior performance with respect to a state-of-the-art two-stage approach based on Mask R-CNN.

关键词： deep learning for visual perception robotics and automation in agriculture and forestry

来源：评论

学校读者我要写书评

暂无评论

Reconstructing Spatial Aspects of Motion by Image-to-Path deep Neural Networks

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2021年第1期6卷 255-262页

作者： Pahic, Rok Gams, Andrej Ude, Ales Jozef Stefan Inst Dept Automat Biocybernet & Robot Humanoid & Cognit Robot Lab Ljubljana 2318 Slovenia Jozef Stefan Int Postgrad Sch Ljubljana Slovenia Univ Ljubljana Fac Elect Engn Ljubljana 1000 Slovenia

The choice of an appropriate representation is important when reconstructing motion from images. In this letter we propose a new type of deep neural network (DNN) that maps images to spatial paths represented by a recently introduced motion representation called arc-length dynamic movement primitive (AL-DMP). This representation separates the spatial from temporal aspects of motion and is therefore suitable for processing data that do not contain temporal information. We propose a physically meaningful loss function for training of AL-DMPs, which improves the performance of the trained DNN, and derive its gradients, which are needed to apply the backpropagation algorithm. Moreover, the proposed DNN architecture supports the processing of variable-size input images and images with cluttered background. The developed approach was applied to the reproduction of handwritten digits from single images that do not contain temporal aspects of motion. Our experiments also show that the proposed network can be applied to input images of sizes that are different from the size of training images. Finally, the proposed approach was successfully applied for reproducing real handwritten digits with a humanoid robot.

关键词： deep learning for visual perception novel deep learning methods perception-action coupling

来源：评论

学校读者我要写书评

暂无评论

SeqNet: learning Descriptors for Sequence-Based Hierarchical Place Recognition

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2021年第3期6卷 4305-4312页

作者： Garg, Sourav Milford, Michael Queensland Univ Technol Sch Elect Engn & Robot Brisbane Qld 4000 Australia

visual Place Recognition (VPR) is the task of matching current visual imagery from a camera to images stored in a reference map of the environment. While initial VPR systems used simple direct image methods or hand-crafted visual features, recent work has focused on learning more powerful visual features and further improving performance through either some form of sequential matcher / filter or a hierarchical matching process. In both cases the performance of the initial single-image based system is still far from perfect, putting significant pressure on the sequence matching or (in the case of hierarchical systems) pose refinement stages. In this paper we present a novel hybrid system that creates a high performance initial match hypothesis generator using short learnt sequential descriptors, which enable selective control sequential score aggregation using single image learnt descriptors. Sequential descriptors are generated using a temporal convolutional network dubbed SeqNet, encoding short image sequences using 1-D convolutions, which are then matched against the corresponding temporal descriptors from the reference dataset to provide an ordered list of place match hypotheses. We then perform selective sequential score aggregation using shortlisted single image learnt descriptors from a separate pipeline to produce an overall place match hypothesis. Comprehensive experiments on challenging benchmark datasets demonstrate the proposed method outperforming recent state-of-the-art methods using the same amount of sequential information. Source code and supplementary material can be found online.(1)

关键词： Autonomous vehicle navigation computer vision for automation deep learning for visual perception localization recognition

来源：评论

学校读者我要写书评

暂无评论

A Probabilistic Next Best View Planner for Depth Cameras Based on deep learning

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2021年第2期6卷 3529-3536页

作者： Monica, Riccardo Aleotti, Jacopo Univ Parma Dept Engn & Architecture RIMLab Parco Area Sci 181A I-43124 Parma Italy

In this work we present a novel method to plan the next best view of a depth camera by leveraging on a Convolutional Neural Network (CNN), and on a probabilistic occupancy map of the environment for ray casting operations. In particular, a hybrid approach is introduced that exploits the convolutional encoder-decoder to perform object completion, and an algorithm based on ray casting to evaluate the information gain of possible sensor view poses. Automatic object completion consists of inferring the occupancy probability of the regions of space that have not been observed. A comparison against several methods, including City-CNN, was carried out in 2D and 3D environments on publicly available datasets. In particular, to enable comparison, the original City-CNN algorithm was modified to work with depth cameras. Experiments indicate that the proposed method achieves the best results in terms of exploration accuracy. Results on a real robot are also presented.

关键词： deep learning for visual perception RGB-D perception view planning for SLAM

来源：评论

学校读者我要写书评

暂无评论

Efficient and accurate stereo matching via guided deformable aggregation

引用

JOURNAL OF ELECTRONIC IMAGING 2025年第2期34卷

作者： Li, Jie Li, Xinjia Chang, Mingyuan Wang, Lin Du, Shuangli Zhou, Jie Liu, Yiguang Shanxi Univ Finance & Econ Sch Informat Taiyuan Peoples R China Xian Univ Technol Sch Comp Sci & Engn Xian Peoples R China Sichuan Univ Sch Math Chengdu Peoples R China Sichuan Univ Sch Comp Sci Chengdu Peoples R China

In stereo vision, depth information relies on the dense registration accuracy of binocular stereo images, and its real-time performance is also significant in many automation applications. Recently, it is still a challenge to balance efficiency and accuracy. Motivated by this problem, we propose a lightweight two-dimensional (2D) guided deformable aggregation (GDA) module. It uses color prior information to learn the aggregation sampling points for fitting the irregular window, and it enables the fast recovery of lost high-frequency detail information from a coarse cost volume. Furthermore, we propose a guided deformable aggregation-based stereo matching network (GDANet) for balancing the efficiency and accuracy. It builds a fast three-dimensional network to obtain the cost volume of low-frequency non-detail regions and then uses the lightweight 2D GDA module to recover high-frequency detail regions. Experiments show that GDANet achieves better results than current high-efficiency methods in the Scene Flow and KITTI datasets. Especially, in edge regions and thin structures, our method shows better qualitative and quantitative results.

关键词： computer vision for automation deep learning for visual perception guided deformable aggregation

来源：评论

学校读者我要写书评

暂无评论

Sensing Anomalies as Potential Hazards: Datasets and Benchmarks 23rd

Sensing Anomalies as Potential Hazards: Datasets and Benchma...

引用

23rd Conference on Towards Autonomous Robotic Systems (TAROS)

作者： Mantegazza, Dario Redondo, Carlos Espada, Fran Gambardella, Luca M. Giusti, Alessandro Guzzi, Jerome USI SUPSI Dalle Molle Inst Artificial Intelligence IDSIA Lugano Switzerland Hovering Solut Ltd Madrid Spain

ISBN: (纸本)9783031159084;9783031159077

We consider the problem of detecting, in the visual sensing data stream of an autonomous mobile robot, semantic patterns that are unusual (i.e., anomalous) with respect to the robot's previous experience in similar environments. These anomalies might indicate unforeseen hazards and, in scenarios where failure is costly, can be used to trigger an avoidance behavior. We contribute three novel image-based datasets acquired in robot exploration scenarios, comprising a total of more than 200k labeled frames, spanning various types of anomalies. On these datasets, we study the performance of an anomaly detection approach based on autoencoders operating at different scales.

关键词： visual anomaly detection Dataset for robotic vision deep learning for visual perception Robotic perception

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：