检索结果-内蒙古大学图书馆

Smallbignet: Integrating core and contextual views for video classification

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Li, Xianhang Wang, Yali Zhou, Zhipeng Qiao, Yu ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society

Temporal convolution has been widely used for video classification. However, it is performed on spatio-temporal contexts in a limited view, which often weakens its capacity of learning video representation. To alleviate this problem, we propose a concise and novel SmallBig network, with the cooperation of small and big views. For the current time step, the small view branch is used to learn the core semantics, while the big view branch is used to capture the contextual semantics. Unlike traditional temporal convolution, the big view branch can provide the small view branch with the most activated video features from a broader 3D receptive field. Via aggregating such big-view contexts, the small view branch can learn more robust and discriminative spatio-temporal representations for video classification. Furthermore, we propose to share convolution in the small and big view branch, which improves model compactness as well as alleviates overfitting. As a result, our SmallBigNet achieves a comparable model size like 2D CNNs, while boosting accuracy like 3D CNNs. We conduct extensive experiments on the large-scale video benchmarks, e.g., Kinetics400, Something-Something V1 and V2. Our SmallBig network outperforms a number of recent state-of-the-art approaches, in terms of accuracy and/or efficiency. The codes and models will be available on https://***/xhl-video/SmallBigNet. Copyright © 2020, The Authors. All rights reserved.

关键词： Convolution

6D pose estimation with combined deep learning and 3D vision techniques for a fast and accurate object grasping

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Le, Tuan-Tang Le, Trung-Son Chen, Yu-Ru Vidal, Joel Lin, Chyi-Yeu Department of Mechanical Engineering National Taiwan University of Science and Technology Taipei106 Taiwan Computer Vision and Robotics Institute University of Girona Girona17003 Spain Taiwan Building Technology Center National Taiwan University of Science and Technology Taipei106 Taiwan Center for Cyber-Physical System National Taiwan University of Science and Technology Taipei106 Taiwan

Real-time robotic grasping, supporting a subsequent precise object-in-hand operation task, is a priority target towards highly advanced autonomous systems. However, such an algorithm which can perform sufficiently-accurate grasping with time efficiency is yet to be found. This paper proposes a novel method with a 2-stage approach that combines a fast 2D object recognition using a deep neural network and a subsequent accurate and fast 6D pose estimation based on Point Pair Feature framework to form a real-time 3D object recognition and grasping solution capable of multi-object class scenes. The proposed solution has a potential to perform robustly on real-time applications, requiring both efficiency and accuracy. In order to validate our method, we conducted extensive and thorough experiments involving laborious preparation of our own dataset. The experiment results show that the proposed method scores 97.37% accuracy in 5cm5deg metric and 99.37% in Average Distance metric. Experiment results have shown an overall 62% relative improvement (5cm5deg metric) and 52.48% (Average Distance metric) by using the proposed method. Moreover, the pose estimation execution also showed an average improvement of 47.6% in running time. Finally, to illustrate the overall efficiency of the system in real-time operations, a pick-and-place robotic experiment is conducted and has shown a convincing success rate with 90% of accuracy. This experiment video is available at https://***/view/dl-ppf6dpose/. © 2021, CC BY.

关键词： Real time systems

Learning Attentive Pairwise Interaction for Fine-Grained Classification

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Zhuang, Peiqin Wang, Yali Qiao, Yu ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society

Fine-grained classification is a challenging problem, due to subtle differences among highly-confused categories. Most approaches address this difficulty by learning discriminative representation of individual input image. On the other hand, humans can effectively identify contrastive clues by comparing image pairs. Inspired by this fact, this paper proposes a simple but effective Attentive Pairwise Interaction Network (API-Net), which can progressively recognize a pair of fine-grained images by interaction. Specifically, API-Net first learns a mutual feature vector to capture semantic differences in the input pair. It then compares this mutual vector with individual vectors to generate gates for each input image. These distinct gate vectors inherit mutual context on semantic differences, which allow API-Net to attentively capture contrastive clues by pairwise interaction between two images. Additionally, we train API-Net in an end-to-end manner with a score ranking regularization, which can further generalize API-Net by taking feature priorities into account. We conduct extensive experiments on five popular benchmarks in fine-grained classification. API-Net outperforms the recent SOTA methods, i.e., CUB-200-2011 (90.0%), Aircraft (93.9%), Stanford Cars (95.3%), Stanford Dogs (90.3%), and NABirds (88.1%). Copyright © 2020, The Authors. All rights reserved.

关键词： Vectors

OTE: Optimal Trustworthy EdgeAI solutions for smart cities

学校读者我要写书评

暂无评论

OTE: Optimal Trustworthy EdgeAI solutions for smart cities

IEEE/ACM International Symposium on Cluster Computing and the Grid (CCGRID)

作者： Vasileios Mygdalis Lorenzo Carnevale Jose Ramiro Martí nez-De-Dios Dmitriy Shutin Giovanni Aiello Massimo Villari Ioannis Pitas Department of Informatics Aristotle University of Thessaloniki Thessaloniki Greece Department of Mathematical and Computer Science Physics and Hearth Sciences University of Messina Messina Italy Gruppo Nazionale per il Calcolo Scientifico (GNCS) Istituto Nazionale di Alta Matematica (INdAM) &#x201C F. Severi&#x201D Rome Italy Robotics Vision and Control Group University of Seville Seville Spain Institute of Communications and Navigation German Aerospace Center (DLR) Wessling Germany Research and Development Lab. Engineering Ingegneria Informatica S.p.A Rome Italy

This work studies and defines the problem of providing extensive and opportunistic Edge AI-based area coverage in smart city application scenarios, by researching and determining the optimal configuration of sensing and computational resources for minimizing the environmental/technology footprint of the solution. A typical smart city computing continuum consists of statically installed multimodal sensing Internet-of-Things (IoT) nodes at various city locations, accompanied by interconnected computational Cloud/Edge/IoT nodes. This paper presents Optimal Trustworthy EdgeAI (OTE), an entirely novel research pipeline, that complements existing smart city infrastructure with intelligent drone Edge/IoT nodes (in the form of modularly equipped unmanned aerial vehicles), capable of autonomous repositioning according to individual/collective sensing and coverage criteria. Thereby, we envisage the emerging cutting-edge technologies of trustworthy sensing, perceiving, modelling technologies for predicting the behavior of moving targets (e.g., citizens/vehicles/objects), understanding natural phenomena (e.g., sea wave motion, urban flora/fauna, biodiversity) in order to anticipate events (people's bad habits, environmental changes), by exploiting novel continuous data processing services across the whole span of the enhanced Cloud-Edge-IoT computing continuum.

关键词： Cloud computing Privacy Smart cities Pipelines Semantics Robot sensing systems Software

Bitcoin Price Forecasting: A Comparative Study Between Statistical and Machine Learning Methods

学校读者我要写书评

暂无评论

Bitcoin Price Forecasting: A Comparative Study Between Stati...

International Conference on computer & Information Science (ICCIS)

作者： Waddah Waheeb Habib Shah Mohammed Jabreel Domenec Puig School of Computing Asia Pacific University of Technology & Innovation Kuala Lumpur Bukit Jalil Malaysia College of Computer Science King Khalid University Abha Saudi Arabia IRCV - Intelligent Robotics and Computer Vision Group Universitat Rovira i Virgili Tarragona Spain

ISBN: (数字)9781728154671

ISBN: (纸本)9781728154688

This paper presents a comparative study between statistical and machine learning methods in forecasting Bitcoin's closing prices. Thirteen forecasting methods namely average, naive, drift, auto-regressive integrated moving-average, simple exponential smoothing (SES), Holt, and damped exponential smoothing, the average of SES, Holt and damped methods, exponential smoothing (ETS), bagged ETS, Theta, multilayer perceptron, and extreme learning machines (ELM) were used to forecast the closing prices for the next 14 days. The findings of this study are three folds. First, there are seven forecasting methods outperformed the naive method namely MLP, ELM, damped exponential smoothing, simple exponential smoothing, Theta, ETS, and ARIMA. Second, MLP and ELM showed better forecasting accuracy on both validation and out-of-sample data among the forecasting methods used in this study. Third, the size of the training data is essential factor that should be considered when training forecasting methods.

关键词： Forecasting Bitcoin Training data Smoothing methods Training Time series analysis Support vector machines

Are You With Me? Determining the Association of Individuals and the Collective Social Space

学校读者我要写书评

暂无评论

Are You With Me? Determining the Association of Individuals ...

2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Alan D. G. Silva Douglas G. Macharet Computer Vision and Robotics Laboratory (VeRLab) Universidade Federal de Minas Gerais MG Brazil

The increasing use of autonomous mobile robots in different parts of society, and not restricted only to industrial environments, makes it important to propose techniques that will allow them to behave in the most socially acceptable way as possible. In most real-world scenarios, individuals in the environment are interacting with each other and are arranged into groups. Therefore, it is paramount the proposition of techniques to efficiently and correctly identify and represent such groups. This information can be useful in different tasks such as approaching and initiating an interaction, escorting, and the navigation itself. In this work, we propose a novel graph-based approach to evaluate the possible association of individuals in the environment based on their position and body orientation. Next, based on this association, we propose a representation of the combined social space of individuals in the same group. The methodology was evaluated using synthetic and real-world datasets, showing that it achieves results comparable to or better than the state-of-the-art.

关键词：

Camera exposure control for robust robot vision with noise-aware image quality assessment

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Shin, Ukcheol Park, Jinsun Shim, Gyumin Rameau, Francois Kweon, In So Robotics and Computer Vision Laboratory School of Electrical Engineering KAIST Daejeon34141 Korea Republic of

In this paper, we propose a noise-aware exposure control algorithm for robust robot vision. Our method aims to capture the best-exposed image which can boost the performance of various computer vision and robotics tasks. For this purpose, we carefully design an image quality metric which captures complementary quality attributes and ensures light-weight computation. Specifically, our metric consists of a combination of image gradient, entropy, and noise metrics. The synergy of these measures allows preserving sharp edge and rich texture in the image while maintaining a low noise level. Using this novel metric, we propose a real-time and fully automatic exposure and gain control technique based on the Nelder-Mead method. To illustrate the effectiveness of our technique, a large set of experimental results demonstrates higher qualitative and quantitative performances when compared with conventional approaches. Copyright © 2019, The Authors. All rights reserved.

关键词： computer vision

Underwater image super-resolution using deep residual multipliers

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Islam, Md Jahidul Enan, Sadman Sakib Luo, Peigen Sattar, Junaed Interactive Robotics and Vision Laboratory Department of Computer Science and Engineering Minnesota Robotics Institute University of Minnesota Twin Cities United States

We present a deep residual network-based generative model for single image super-resolution (SISR) of underwater imagery for use by autonomous underwater robots. We also provide an adversarial training pipeline for learning SISR from paired data. In order to supervise the training, we formulate an objective function that evaluates the perceptual quality of an image based on its global content, color, and local style information. Additionally, we present USR-248, a large-scale dataset of three sets of underwater images of ‘high’ (640 × 480) and ‘low’ (80 × 60, 160 × 120, and 320 × 240) resolution. USR-248 contains over 7K paired instances in each set of data for supervised training of 2×, 4×, or 8× SISR models. Furthermore, we validate the effectiveness of our proposed model through qualitative and quantitative experiments and compare the results with several state-of-the-art models’ performances. We also analyze its practical feasibility for applications such as scene understanding and attention modeling in noisy visual conditions. Copyright © 2019, The Authors. All rights reserved.

关键词： Large dataset

Stonefish: An Advanced Open-Source Simulation Tool Designed for Marine robotics, With a ROS Interface

学校读者我要写书评

暂无评论

Stonefish: An Advanced Open-Source Simulation Tool Designed ...

OCEANS - Europe

作者： Patryk Cieślak Computer Vision and Robotics Research Institute Scientific and Technological Park of the University of Girona Girona Spain

The marine robotics community is lacking a high quality simulator for doing scientific research, especially when it comes to testing control and vision algorithms in realistic underwater intervention tasks. All of the solutions used today are either outdated or try to combine different software tools, which often results in bad performance, stability issues and lack of important features. This paper presents a new software tool, focused on, but not limited to, simulation of intervention autonomous underwater vehicles (I-AUV). It delivers advanced hydrodynamics based on actual geometry, simulation of underwater sensors and actuators, as well as realistic rendering of underwater environment and ocean surface. It consists of a library written in C++ and a Robot Operating System (ROS) package.

关键词： Atmospheric modeling Libraries Robot sensing systems Actuators Rendering (computer graphics)