检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Shahbazi, Mohamad Ntavelis, Evangelos Tonioni, Alessio Collins, Edo Paudel, Danda Pani Danelljan, Martin Van Gool, Luc Computer Vision Lab ETH Zürich Switzerland Google Zürich Switzerland ML & Robotics CSEM Switzerland

Pose-conditioned convolutional generative models struggle with high-quality 3D-consistent image generation from single-view datasets, due to their lack of sufficient 3D priors. Recently, the integration of Neural Radiance Fields (NeRFs) and generative models, such as Generative Adversarial Networks (GANs), has transformed 3D-aware generation from single-view images. NeRF-GANs exploit the strong inductive bias of neural 3D representations and volumetric rendering at the cost of higher computational complexity. This study aims at revisiting pose-conditioned 2D GANs for efficient 3D-aware generation at inference time by distilling 3D knowledge from pretrained NeRF-GANs. We propose a simple and effective method, based on re-using the well-disentangled latent space of a pre-trained NeRF-GAN in a pose-conditioned convolutional network to directly generate 3D-consistent images corresponding to the underlying 3D representations. Experiments on several datasets demonstrate that the proposed method obtains results comparable with volumetric rendering in terms of quality and 3D consistency while benefiting from the computational advantage of convolutional networks. The code will be available at: https://***/mshahbazi72/NeRF-GAN-Distillation © 2023, CC BY.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Enhancement for face video from omni-directional video camera

Enhancement for face video from omni-directional video camer...

引用

Asilomar Conference on Signals, Systems & computers

作者： Junwen Wu M.M. Trivedi Computer Vision and Robotics Research lab ECE Department University of California San Diego La Jolla CA USA

In this paper we propose a novel algorithm to enhance the face video from omni-directional video camera. A two-stage strategy is used. First stage is the noise elimination, realized by iterative MAP update. Naive Bayesian criterion is used to model the posterior. The predominant salt and pepper noise introduced by the omni-to-perspective transformation can be removed effectively, while the image details are well preserved. The high frequency component compensation (HFCC) super-resolution algorithm is applied thereafter to remove the blocky effect. Experimental results show that the video quality has a marked improvement.

关键词： Cameras Iterative algorithms Statistics Robot vision systems Bayesian methods Face detection Image resolution Image enhancement Streaming media Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Real-time tracking of recreational boats in coastal areas using deep learning

引用

Ocean and Coastal Management 2025年 267.0卷

作者： Signaroli, Marco Lana, Arancha Cutolo, Eugenio Alós, Josep Gonzalez-Cid, Yolanda Institut Mediterrani d'Estudis Avançats IMEDEA (CSIC-UIB) Marine Research in Ecological and Social Systems Group (MARES) C/. Miquel Marquès 21 Illes Balears Esporles 07190 Spain AtalaIA Detection Technologies Av. Gabriel Alomar I Villalonga 22 Illes Balears Palma 07006 Spain Institut Mediterrani d'Estudis Avançats IMEDEA (CSIC-UIB) DataLab Service C/. Miquel Marquès 21 Illes Balears Esporles 07190 Spain IMT Atlantique Lab-STICC UMR CNRS 6285 and Odyssey Inria/IMT Technopôle Brest-Iroise 655 Avenue du Technopôle Plouzané 29280 France Universitat de les Illes Balears (UIB) Department of Mathematics and Computer Science Systems Robotics and Vision Group (SRV) Cra. de Valldemossa km 7.5 Illes Balears Palma 07122 Spain

To effectively manage and conserve coastal ecosystems, accurate spatial data on marine recreational activities are crucial. This study introduces a deep-learning-based system designed for real-time detection and tracking of recreational vessels in coastal environments using cameras. We fine-tuned and evaluated two object detection and classification algorithms, YOLOv5 and YOLOv7, for automated, real-time vessel detection, classification and positioning within Marine Protected Areas (MPAs). Additionally, we optimized two multiple object tracking algorithms, StrongSORT and ByteTrack, for tracking the movements of the detected vessels in sequential timeframes. We implemented the best combination (YOLOv5 and ByteTrack) on an NVIDIA Jetson platform, an edge computing device specifically designed for AI applications, conducting thorough benchmarking across various simulated hardware configurations to determine its minimal computational and power needs. Then, we conducted field tests by positioning the system on a coastal cliff overlooking a recreational fishery located in a partial MPA. These tests aimed to validate the system's real-time operational viability and to acquire precise vessel trajectories. The results confirmed the system's efficacy and its data collection capabilities within a real marine environment. Finally, we evaluated two camera calibration techniques for converting image trajectories to geographic coordinates: a projective transformation with homography for accurate perspective adjustment, and an innovative neural network-based approach. The system we have developed could markedly enhance the monitoring and surveillance capabilities within MPAs, generating spatial-temporal data of recreational fishing effort that can be easily transferred to other case studies. © 2025 The Authors

关键词： Artificial intelligence Boat detection Deep learning Fishing effort Marine protected areas Multiple object tracking Recreational fishing

来源：评论

学校读者我要写书评

暂无评论

Global Localization: Utilizing Relative Spatio-Temporal Geometric Constraints from Adjacent and Distant Cameras

arXiv

引用

arXiv 2023年

作者： Altillawi, Mohammad Pataki, Zador Li, Shile Liu, Ziyuan AI Robotics & Simulation Huawei Munich Research Center Germany Computer Vision Center Universitat Autònoma de Barcelona Spain Computer Vision and Geometry Lab ETH Zurich Switzerland

Re-localizing a camera from a single image in a previously mapped area is vital for many computer vision applications in robotics and augmented/virtual reality. In this work, we address the problem of estimating the 6 DoF camera pose relative to a global frame from a single image. We propose to leverage a novel network of relative spatial and temporal geometric constraints to guide the training of a Deep Network for localization. We employ simultaneously spatial and temporal relative pose constraints that are obtained not only from adjacent camera frames but also from camera frames that are distant in the spatio-temporal space of the scene. We show that our method, through these constraints, is capable of learning to localize when little or very sparse ground-truth 3D coordinates are available. In our experiments, this is less than 1% of available ground-truth data. We evaluate our method on 3 common visual localization datasets and show that it outperforms other direct pose estimation methods. © 2023, CC BY-NC-SA.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Towards a generic diver-following algorithm: Balancing robustness and efficiency in deep visual detection

arXiv

引用

arXiv 2018年

作者： Islam, Md Jahidul Fulton, Michael Sattar, Junaed Interactive Robotics and Vision Lab-oratory Department of Computer Science and Engineering University of Minnesota-Twin Cities United States

This paper explores the design and development of a class of robust diver-following algorithms for autonomous underwater robots. By considering the operational challenges for underwater visual tracking in diverse real-world settings, we formulate a set of desired features of a generic diver following algorithm. We attempt to accommodate these features and maximize general tracking performance by exploiting the state-of-the-art deep object detection models. We fine-tune the building blocks of these models with a goal of balancing the trade-off between robustness and efficiency in an on-board setting under real-time constraints. Subsequently, we design an architecturally simple Convolutional Neural Network (CNN)-based diver-detection model that is much faster than the state-of-the-art deep models yet provides comparable detection performances. In addition, we validate the performance and effectiveness of the proposed diver-following modules through a number of field experiments in closed-water and open-water environments. Copyright © 2018, The Authors. All rights reserved.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Robust text line detection in equipment nameplate images

Robust text line detection in equipment nameplate images

引用

2019 IEEE International Conference on robotics and Biomimetics, ROBIO 2019

作者： Lai, Jiangyu Guo, Lanqing Qiao, Yu Chen, Xiaolong Zhang, Zhengfu Liu, Canping Li, Ying Fu, Bin Guangzhou Power Supply Bureau Co. Ltd. Guangzhou China ShenZhen Key Lab of Computer Vision and Pattern Recognition SIATSenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society China

ISBN: (纸本)9781728163215

Scene text detection for equipment nameplates in the wild is important for equipment inspection robot since it enables inspection robot to take specific actions for different equipment's. Although text detection in images has achieved great progress in recent years, the detection for equipment nameplates faces several challenges such as extreme illumination and distortion which significantly decrease the detection performance. In this paper, we propose a deep text detection model Robust Text Line Detection (RTLD) for locating word level text instances in equipment cards. Specifically, the proposed model first employs a corner detection module to determine the four corner points of each nameplate, and then a carefully designed image transformed module transforms the irregular nameplate region into a rectangular region. Finally, text detection module is introduced to locate every word level text instance in the transformed images. We conduct extensive experiments to examine our proposed methods on real equipment nameplate images. Our model achieves 91.2% precision and 92.6% recall on Equipment Nameplate Dataset. The experimental results demonstrate the effectiveness of our models. © 2019 IEEE.

关键词： Nameplates

来源：评论

学校读者我要写书评

暂无评论

Viewpoint independent human motion analysis in man-made environments

Viewpoint independent human motion analysis in man-made envi...

引用

2006 17th British Machine vision Conference, BMVC 2006

作者： Rogez, G. Guerrero, J.J. Martínez, J. Orrite, C. Computer Vision Lab. I3A - University of Zaragoza Maria de Luna 1 50018 Zaragoza Spain Robotics Perception and Real Time Group I3A - University of Zaragoza Maria de Luna 1 50018 Zaragoza Spain

ISBN: (纸本)1904410146

This work addresses the problem of human motion analysis in video sequences of a scene observed by a single fixed camera with high perspective effect. The goal of this work is to make a 2D-Model (made of Shape and Stick figure) viewpoint-insensitive and preprocess the input image for removing the perspective effect. We focus our methodology on using the 3D principal directions of man-made environments and also the direction of motion to transform both 2D-Model and input images to a common frontal view (parallel or orthogonal to the direction of motion) before the fitting process. The inverse transformation is then performed on the resulting human features obtaining a segmented silhouette and a pose estimation in the original input image. Preliminary results are very promising since the proposed algorithm is able to locate head and feet with a better precision than previous one.

关键词： Motion analysis

来源：评论

学校读者我要写书评

暂无评论

Integrating mission, logistics, and task planning for skills-based robot control in industrial kitting applications 34

Integrating mission, logistics, and task planning for skills...

引用

34th Workshop of the UK Planning and Scheduling Special Interest Group, PlanSIG 2016

作者： Crosby, Matthew Petrick, Ronald P. A. Toscano, César Dias, Rui Correia Rovida, Francesco Krüger, Volker Department of Computer Science Heriot-Watt University EdinburghEH14 4AS United Kingdom INESC TEC Technology and Science Porto4200 - 465 Portugal Robotics Vision and Machine Intelligence Lab. Aalborg University Copenhagen2450 Denmark

This paper presents an integrated cognitive robotics system for industrial kitting operations in a modern factory setting. The robot system combines low-level robot control and execution monitoring with automated mission and task planning, and a logistics planner which communicates with the factory's manufacturing execution system. The system has been implemented and tested on a series of automotive kitting problems, where collections of parts are picked from a warehouse and delivered to the production line. The system has been empirically evaluated and the complete framework shown to be successful at assembling kits in a small factory environment. © 2017, CEUR-WS. All rights reserved.

关键词： Robot programming

来源：评论

学校读者我要写书评

暂无评论

A Real Time and Robust Facial Expression Recognition and Imitation approach for Affective Human-Robot Interaction Using Gabor filtering

A Real Time and Robust Facial Expression Recognition and Imi...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems

作者： Felipe Cid Jose Augusto Prado Pablo Bustos Pedro Nunez Robotics and Artificial Vision Lab. Robolab Group University of Extremadura Spain Institute of Systems and Robotics Dept. Electrical and Computer Engineering University of Coimbra Portugal

ISBN: (纸本)9781467363563

Facial expressions are a rich source of communicative information about human behavior and emotion. This paper presents a real-time system for recognition and imitation of facial expressions in the context of affective Human Robot Interaction. The proposed method achieves a fast and robust facial feature extraction based on consecutively applying filters to the gradient image. An efficient Gabor filter is used, along with a set of morphological and convolutional filters to reduce the noise and the light dependence of the image acquired by the robot. Then, a set of invariant edge-based features are extracted and used as input to a Dynamic Bayesian Network classifier in order to estimate a human emotion. The output of this classifier updates a geometric robotic head model, which is used as a bridge between the human expressiveness and the robotic head. Experimental results demonstrate the accuracy and robustness of the proposed approach compared to similar systems.

关键词： Imitation approach emotion context of affective Human Robot Interaction

来源：评论

学校读者我要写书评

暂无评论

Orientation robust scene text recognition in natural scene

Orientation robust scene text recognition in natural scene

引用

2019 IEEE International Conference on robotics and Biomimetics, ROBIO 2019

作者： Chen, Xiaolong Zhang, Zhengfu Qiao, Yu Lai, Jiangyu Jiang, Jian Zhang, Zeyu Fu, Bin Guangzhou Power Supply Bureau Co. Ltd. Guangzhou China ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society China

ISBN: (纸本)9781728163215

In recent years, scene text recognition has achieved significant improvement and various state-of-the-art recognition approaches have been proposed. This paper focused on recognizing text in natural photos of equipment nameplates, which has wide applications in industrial automations. This task only receives little attentions in previous works. The challenge of this problem comes from multi-orientation, curved, noisy and blurry text patches in equipment nameplates. To address this problem, we propose a deep model for text recognition in multi-oriented nameplates, namely, Orientation Robust Scene Text Recognition (ORSTR). Specifically, our model employs a rectification module to transform curved, distorted or multi-orientation text to near-horizontal text with a carefully designed rectification module. Once the near-horizontal text has been generated, recognition network will output the predictions of text patches. Our scene text recognition model achieves 90.8% recognition accuracy on equipment nameplate dataset which outperforms previous scene text recognition model (CRNN) about 0.8%. Several extensive experiments have been conducted to verify the effectiveness of our model. © 2019 IEEE.

关键词： Nameplates

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：