检索结果-内蒙古大学图书馆

Restoration of video frames from a single blurred image with motion understanding

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Argaw, Dawit Mureja Kim, Junsik Rameau, Francois Zhang, Chaoning Kweon, In So Kaist Robotics and Computer Vision Lab. Daejeon Korea Republic of

We propose a novel framework to generate clean video frames from a single motion-blurred image. While a broad range of literature focuses on recovering a single image from a blurred image, in this work, we tackle a more challenging task i.e. video restoration from a blurred image. We formulate video restoration from a single blurred image as an inverse problem by setting clean image sequence and their respective motion as latent factors, and the blurred image as an observation. Our framework is based on an encoder-decoder structure with spatial transformer network modules to restore a video sequence and its underlying motion in an end-to-end manner. We design a loss function and regularizers with complementary properties to stabilize the training and analyze variant models of the proposed network. The effectiveness and transferability of our network are highlighted through a large set of experiments on two different types of datasets: camera rotation blurs generated from panorama scenes and dynamic motion blurs in high speed videos. © 2021, CC BY.

关键词： Restoration

Towards efficient human-robot cooperation for socially-aware robot navigation in human-populated environments: the SNAPE framework

学校读者我要写书评

暂无评论

Towards efficient human-robot cooperation for socially-aware...

IEEE International Conference on robotics and Automation (ICRA)

作者： A. Vega-Magro R. Gondkar L.J. Manso P. Núñez Robotics and Artificial Vision Lab. RoboLab Group University of Extremadura Spain Pune Institute of Computer Technology Pune University India College of Engineering and Physical Sciences Aston University Birmingham UK

It is widely accepted that in the future, robots will cooperate with humans in everyday tasks. Robots interacting with humans will require social awareness when performing their tasks which will require navigation. While navigating, robots should aim to avoid distressing people in order to maximize their chance of social acceptance. For instance, avoiding getting too close to people or disrupting interactions. Most research approaches these problems by planning socially accepted paths, however, in everyday situations, there are many examples where a simple path planner cannot solve all of the predicted robots’ navigation problems. For instance, requesting permission to interrupt a conversation if an alternative path cannot be determined requires deliberative skills. This article presents the Social Navigation framework for Autonomous robots in Populated Environments (SNAPE), where different software agents are integrated within a robotics cognitive architecture. SNAPE addresses action planning aimed at social-awareness navigation in realistic situations: it plans socially accepted paths and conversations to negotiate its trajectory to reach targets. In this article, the framework is evaluated in different use-cases where the robot, during its navigation, has to interact with different people in order to reach its goal. The results show that participants report that the robot’s behavior was realistic and human-like.

关键词： Navigation Conferences computer architecture Software agents Planning Trajectory Task analysis

SESAME: Semantic editing of scenes by adding, manipulating or erasing objects

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Ntavelis, Evangelos Romero, Andrés Kastanis, Iason van Gool, Luc Timofte, Radu Computer Vision Lab. ETH Zurich Switzerland Robotics and Machine Learning CSEM SA Switzerland PSI ESAT KU Leuven Belgium

Recent advances in image generation gave rise to powerful tools for semantic image editing. However, existing approaches can either operate on a single image or require an abundance of additional information. They are not capable of handling the complete set of editing operations, that is addition, manipulation or removal of semantic concepts. To address these limitations, we propose SESAME, a novel generator-discriminator pair for Semantic Editing of Scenes by Adding, Manipulating or Erasing objects. In our setup, the user provides the semantic lab.ls of the areas to be edited and the generator synthesizes the corresponding pixels. In contrast to previous methods that employ a discriminator that trivially concatenates semantics and image as an input, the SESAME discriminator is composed of two input streams that independently process the image and its semantics, using the latter to manipulate the results of the former. We evaluate our model on a diverse set of datasets and report state-of-the-art performance on two tasks: (a) image manipulation and (b) image generation conditioned on semantic lab.ls. Copyright © 2020, The Authors. All rights reserved.

关键词： Generative adversarial networks

Context-transformer: Tackling object confusion for few-shot detection

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Yang, Ze Wang, Yali Chen, Xianyu Liu, Jianzhuang Qiao, Yu ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab. Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Huawei Noah’s Ark Lab. SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society

Few-shot object detection is a challenging but realistic scenario, where only a few annotated training images are availab.e for training detectors. A popular approach to handle this problem is transfer learning, i.e., fine-tuning a detector pretrained on a source-domain benchmark. However, such transferred detector often fails to recognize new objects in the target domain, due to low data diversity of training samples. To tackle this problem, we propose a novel Context-Transformer within a concise deep transfer framework. Specifically, Context-Transformer can effectively leverage source-domain object knowledge as guidance, and automatically exploit contexts from only a few training images in the target domain. Subsequently, it can adaptively integrate these relational clues to enhance the discriminative power of detector, in order to reduce object confusion in few-shot scenarios. Moreover, Context-Transformer is flexibly embedded in the popular SSD-style detectors, which makes it a plug-and-play module for end-to-end few-shot learning. Finally, we evaluate Context-Transformer on the challenging settings of few-shot detection and incremental few-shot detection. The experimental results show that, our framework outperforms the recent state-of-the-art approaches. The codes are availab.e at https://***/Ze-Yang/ContextTransformer. Copyright © 2020, The Authors. All rights reserved.

关键词： Object detection

Learning to super resolve intensity images from events

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Mostafavi, Sayed Mohammad I. Choi, Jonghyun Yoon, Kuk-Jin Computer Vision Lab. GIST Korea Republic of Visual Intelligence Lab. KAIST Korea Republic of

An event camera detects per-pixel intensity difference and produces asynchronous event stream with low latency, high dynamic sensing range, and low power consumption. As a trade-off, the event camera has low spatial resolution. We propose an end-to-end network to reconstruct high resolution, high dynamic range (HDR) images from the event streams. The reconstructed images using the proposed method is in better quality than the combination of state-of-the-art intensity image reconstruction algorithms and the state-of-the-art super resolution schemes. We further evaluate our algorithm on multiple real-world sequences showing the ability to generate high quality images in the zero-shot cross dataset transfer setting. Copyright © 2019, The Authors. All rights reserved.

关键词： Cameras

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

DISC: A Large-scale Virtual Dataset for Simulating Disaster Scenarios

学校读者我要写书评

暂无评论

DISC: A Large-scale Virtual Dataset for Simulating Disaster ...

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

作者： Hae-Gon Jeon Sunghoon Im Byeong-Uk Lee Dong-Geol Choi Martial Hebert In So Kweon The Robotics Institute Carnegie Mellon University Pittsburgh PA USA The Robotics and Computer Vision Lab. KAIST Daejeon Republic of Korea Department of Information and Communication Engineering Hanbat National University Daejeon Republic of Korea

In this paper, we present the first large-scale synthetic dataset for visual perception in disaster scenarios, and analyze state-of-the-art methods for multiple computer vision tasks with reference baselines. We simulated before and after disaster scenarios such as fire and building collapse for fifteen different locations in realistic virtual worlds. The dataset consists of more than 300K high-resolution stereo image pairs, all annotated with ground-truth data for semantic segmentation, depth, optical flow, surface normal estimation and camera pose estimation. To create realistic disaster scenes, we manually augmented the effects with 3D models using physical-based graphics tools. We use our dataset to train state-of-the-art methods and evaluate how well these methods can recognize the disaster situations and produce reliable results on virtual scenes as well as real-world images. The results obtained from each task are then used as inputs to the proposed visual odometry network for generating 3D maps of buildings on fire. Finally, we discuss challenges for future research.

关键词：

TTPP: Temporal transformer with progressive prediction for efficient action anticipation

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Wang, Wen Peng, Xiaojiang Su, Yanzhou Qiao, Yu Cheng, Jian School of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu Sichuan611731 China 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

Video action anticipation aims to predict future action categories from observed frames. Current state-of-the-art approaches mainly resort to recurrent neural networks to encode history information into hidden states, and predict future actions from the hidden representations. It is well known that the recurrent pipeline is inefficient in capturing long-term information which may limit its performance in predication task. To address this problem, this paper proposes a simple yet efficient Temporal Transformer with Progressive Prediction (TTPP) framework, which repurposes a Transformer-style architecture to aggregate observed features, and then leverages a light-weight network to progressively predict future features and actions. Specifically, predicted features along with predicted probabilities are accumulated into the inputs of subsequent prediction. We evaluate our approach on three action datasets, namely TVSeries, THUMOS-14, and TV-Human-Interaction. Additionally we also conduct a comprehensive study for several popular aggregation and prediction strategies. Extensive results show that TTPP not only outperforms the state-of-the-art methods but also more efficient. Copyright © 2020, The Authors. All rights reserved.

关键词： Forecasting

Learning to specialize with knowledge distillation for visual question answering 18

学校读者我要写书评

暂无评论

Learning to specialize with knowledge distillation for visua...

Proceedings of the 32nd International Conference on Neural Information Processing Systems

作者： Jonghwan Mun Kimin Lee Jinwoo Shin Bohyung Han Computer Vision Lab. POSTECH Pohang Korea and Computer Vision Lab. ASRI Seoul National University Seoul Korea Algorithmic Intelligence Lab. KAIST Daejeon Korea Computer Vision Lab. ASRI Seoul National University Seoul Korea

Visual Question Answering (VQA) is a notoriously challenging problem because it involves various heterogeneous tasks defined by questions within a unified framework. Learning specialized models for individual types of tasks is intuitively attracting but surprisingly difficult; it is not straightforward to outperform naïve independent ensemble approach. We present a principled algorithm to learn specialized models with knowledge distillation under a multiple choice learning (MCL) framework, where training examples are assigned dynamically to a subset of models for updating network parameters. The assigned and non-assigned models are learned to predict ground-truth answers and imitate their own base models before specialization, respectively. Our approach alleviates the limitation of data deficiency in existing MCL frameworks, and allows each model to learn its own specialized expertise without forgetting general knowledge. The proposed framework is model-agnostic and applicable to any tasks including VQA and image classification with a large number of lab.ls but few per-class examples, which is known to be difficult under existing MCL schemes. Our experimental results indeed demonstrate that our method outperforms other baselines for VQA and image classification.

关键词：