检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Lee, Taeyeop Lee, Byeong-Uk Kim, Myungchul Kweon, In So Robotics and Computer Vision Laboratory KAIST Daejeon Korea Republic of

Advances in deep learning recognition have led to accurate object detection with 2D images. However, these 2D perception methods are insufficient for complete 3D world information. Concurrently, advanced 3D shape estimation approaches focus on the shape itself, without considering metric scale. These methods cannot determine the accurate location and orientation of objects. To tackle this problem, we propose a framework that jointly estimates a metric scale shape and pose from a single RGB image. Our framework has two branches: the Metric Scale Object Shape branch (MSOS) and the Normalized Object Coordinate Space branch (NOCS). The MSOS branch estimates the metric scale shape observed in the camera coordinates. The NOCS branch predicts the normalized object coordinate space (NOCS) map and performs similarity transformation with the rendered depth map from a predicted metric scale mesh to obtain 6d pose and size. Additionally, we introduce the Normalized Object Center Estimation (NOCE) to estimate the geometrically aligned distance from the camera to the object center. We validated our method on both synthetic and real-world datasets to evaluate category-level object pose and shape. Copyright © 2021, The Authors. All rights reserved.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Correlate-and-excite: Real-time stereo matching via guided cost volume excitation

arXiv

引用

arXiv 2021年

作者： Bangunharcana, Antyanta Cho, Jae Won Lee, Seokju Kweon, In So Kim, Kyung-Soo Kim, Soohyun Mechatronics Systems and Control Laboratory KAIST Daejeon34141 Korea Republic of Robotics and Computer Vision Laboratory KAIST Daejeon34141 Korea Republic of

Volumetric deep learning approach towards stereo matching aggregates a cost volume computed from input left and right images using 3D convolutions. Recent works showed that utilization of extracted image features and a spatially varying cost volume aggregation complements 3D convolutions. However, existing methods with spatially varying operations are complex, cost considerable computation time, and cause memory consumption to increase. In this work, we construct Guided Cost volume Excitation (GCE) and show that simple channel excitation of cost volume guided by image can improve performance considerably. Moreover, we propose a novel method of using top-k selection prior to soft-argmin disparity regression for computing the final disparity estimate. Combining our novel contributions, we present an end-to-end network that we call Correlate-and-Excite (CoEx). Extensive experiments of our model on the SceneFlow, KITTI 2012, and KITTI 2015 datasets demonstrate the effectiveness and efficiency of our model and show that our model outperforms other speed-based algorithms while also being competitive to other state-of-the-art algorithms. © 2021, CC BY.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Understanding Adversarial Examples From the Mutual Influence of Images and Perturbations

Understanding Adversarial Examples From the Mutual Influence...

引用

Conference on computer vision and Pattern Recognition (CVPR)

作者： Chaoning Zhang Philipp Benz Tooba Imtiaz In So Kweon Robotics and Computer Vision (RCV) Laboratory Korea Advanced Institute of Science and Technology (KAIST) Daejeon Korea Korea Advanced Institute of Science and Technology Daejeon South Korea

ISBN: (数字)9781728171685

ISBN: (纸本)9781728171692

A wide variety of works have explored the reason for the existence of adversarial examples, but there is no consensus on the explanation. We propose to treat the DNN logits as a vector for feature representation, and exploit them to analyze the mutual influence of two independent inputs based on the Pearson correlation coefficient (PCC). We utilize this vector representation to understand adversarial examples by disentangling the clean images and adversarial perturbations, and analyze their influence on each other. Our results suggest a new perspective towards the relationship between images and universal perturbations: Universal perturbations contain dominant features, and images behave like noise to them. This feature perspective leads to a new method for generating targeted universal adversarial perturbations using random source images. We are the first to achieve the challenging task of a targeted universal attack without utilizing original training data. Our approach using a proxy dataset achieves comparable performance to the state-of-the-art baselines which utilize the original training dataset.

关键词： Perturbation methods Correlation Training data Feature extraction Training Task analysis Robustness

来源：评论

学校读者我要写书评

暂无评论

Camera Exposure Control for Robust Robot vision with Noise-Aware Image Quality Assessment

Camera Exposure Control for Robust Robot Vision with Noise-A...

引用

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

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

In this paper, we propose a noise-aware exposure control algorithm for robust robot vision. Our method aims to capture best-exposed images, which can boost the performance of various computer vision and robotics tasks. For this purpose, we carefully design an image quality metric that 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 the preservation of sharp edges 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 the higher qualitative and quantitative performance compared with conventional approaches.

关键词：

来源：评论

学校读者我要写书评

暂无评论

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

arXiv

引用

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

来源：评论

学校读者我要写书评

暂无评论

Learning Residual Flow as Dynamic Motion from Stereo Videos

Learning Residual Flow as Dynamic Motion from Stereo Videos

引用

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

作者： Seokju Lee Sunghoon Im Stephen Lin In So Kweon Robotics and Computer Vision Laboratory KAIST Daejeon Republic of Korea Microsoft Research Asia Beijing China

We present a method for decomposing the 3D scene flow observed from a moving stereo rig into stationary scene elements and dynamic object motion. Our unsupervised learning framework jointly reasons about the camera motion, optical flow, and 3D motion of moving objects. Three cooperating networks predict stereo matching, camera motion, and residual flow, which represents the flow component due to object motion and not from camera motion. Based on rigid projective geometry, the estimated stereo depth is used to guide the camera motion estimation, and the depth and camera motion are used to guide the residual flow estimation. We also explicitly estimate the 3D scene flow of dynamic objects based on the residual flow and scene depth. Experiments on the KITTI dataset demonstrate the effectiveness of our approach and show that our method outperforms other state-of-the-art algorithms on the optical flow and visual odometry tasks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Learning residual flow as dynamic motion from stereo videos

arXiv

引用

arXiv 2019年

作者： Lee, Seokju Im, Sunghoon Lin, Stephen Kweon, In So Robotics and Computer Vision Laboratory KAIST Daejeon34141 Korea Republic of Microsoft Research Asia Beijing100080 China

关键词： Stereo image processing

来源：评论

学校读者我要写书评

暂无评论

Robust road marking detection & recognition using density-based grouping & machine learning techniques 17

Robust road marking detection & recognition using density-ba...

引用

17th IEEE Winter Conference on Applications of computer vision, WACV 2017

作者： Bailo, Oleksandr Lee, Seokju Rameau, Francois Yoon, Jae Shin Kweon, In So KAIST Robotics and Computer Vision Laboratory United States

ISBN: (纸本)9781509048229

This paper presents a robust approach for road marking detection and recognition from images captured by an embedded camera mounted on a car. Our method is designed to cope with illumination changes, shadows, and harsh meteorological conditions. Furthermore, the algorithm can effectively group complex multi-symbol shapes into an individual road marking. For this purpose, the proposed technique relies on MSER features to obtain candidate regions which are further merged using density-based clustering. Finally, these regions of interest are recognized using machine learning approaches. Worth noting, the algorithm is versatile since it does not utilize any prior information about lane position or road space. The proposed method compares favorably to other existing works through a large number of experiments on an extensive road marking dataset. © 2017 IEEE.

关键词： Road and street markings

来源：评论

学校读者我要写书评

暂无评论

Vehicular Multi-Camera Sensor System for Automated Visual Inspection of Electric Power Distribution Equipment

Vehicular Multi-Camera Sensor System for Automated Visual In...

引用

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

作者： Jinsun Park Ukcheol Shin Gyumin Shim Kyungdon Joo Francois Rameau Junhyeok Kim Dong-Geol Choi In So Kweon Robotics and Computer Vision Laboratory School of Electrical Engineering KAIST Daejeon Republic of Korea Korea Electric Power Corporation Korea Electric Power Research Institute Daejeon Republic of Korea Department of Information and Communication Engineering Hanbat National University Daejeon Republic of Korea

In this paper, we present a multi-camera sensor system along with its control algorithm for automated visual inspection from a moving vehicle. To accomplish this task, we propose a unique hardware configuration consisting of a frontal stereo vision system, six lateral cameras motorized to tilt, and a GPS/IMU sensor mounted on the roof of a car. From the frontal stereo system, we detect electric poles and estimate their corresponding 3D positions. Based on this 3D estimation, the tilt angles of the motorized lateral cameras are controlled in real-time to capture high resolution images of the equipment - typically installed a few meters above the road surface. In addition, inertial odometry information from the GPS/IMU module is utilized for pose estimation, object localization, and re-identification among cameras. Experimental results demonstrate the efficiency and robustness of our system for automated electric equipment maintenance, which can reduce human effort significantly.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep representation of industrial components using simulated images

Deep representation of industrial components using simulated...

引用

2017 IEEE International Conference on robotics and Automation, ICRA 2017

作者： Kim, Seong-Heum Choe, Gyeongmin Ahn, Byungtae Kweon, In So Robotics and Computer Vision Laboratory School of Electrical Engineering KAIST Daejeon Korea Republic of

ISBN: (纸本)9781509046331

In this paper, we present a visual learning framework to retrieve a 3D model and estimate its pose from a single image. To increase the quantity and quality of training data, we define our simulation space in the near infrared (NIR) band, and utilize the quasi-Monte Carlo (MC) method for scalable photorealistic rendering of manufactured components. Two types of convolutional neural network (CNN) architectures are trained over these synthetic data and a relatively small amount of real data. The first CNN model seeks the most discriminative information and uses it to classify industrial components with fine-grained shape attributes. Once a 3D model is identified, one of the category-specific CNNs is tested for pose regression in the second phase. The mixed data for learning object categories is useful in domain adaptation and attention mechanism in our system. We validate our data-driven method with 88 component models, and the experimental results are qualitatively demonstrated. Also, the CNNs trained with various conditions of mixed data are quantitatively analyzed. © 2017 IEEE.

关键词： Monte Carlo methods

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：