检索结果-内蒙古大学图书馆

Volumetric Instance-Level Semantic Mapping Via Multi-View 2D-to-3D Label Diffusion

IEEE ROBOTICS AND AUTOMATION LETTERS 2022年第2期7卷 3531-3538页

作者： Mascaro, Ruben Teixeira, Lucas Chli, Margarita Swiss Fed Inst Technol Vis Robot Lab Dept Mech & Proc Engn CH-8092 Zurich Switzerland

Robots operating in real-world settings often need to plan interactions with surrounding scene elements and therefore, it is crucial for them to understand their workspace at the level of individual objects. In this spirit, this work presents a novel approach to progressively build instance-level, dense 3D maps from color and depth cues acquired by either a moving RGB-D sensor or a camera-LiDAR setup, whose pose is being tracked. The proposed framework processes each input RGB image with a semantic instance segmentation neural network and uses depth information to extract a set of per-frame, semantically labeled 3D instance segments, which then get matched to object instances already identified in previous views. Following integration of these newly detected instance segments in a global volumetric map, an efficient label diffusion scheme that considers multi-view instance predictions together with the reconstructed scene geometry is used to refine 3D segmentation boundaries. Experiments on indoor benchmarking RGB-D sequences show that the proposed system achieves state-of-the-art performance in terms of 3D segmentation accuracy, while reducing the computational processing cost required at each frame. Furthermore, the applicability of the system to challenging domains outside the traditional office scenes is demonstrated by testing it on a robotic excavator equipped with a calibrated camera-LiDAR setup, with the goal of segmenting individual boulders in a highly cluttered construction scenario.

关键词： Object detection segmentation and categorization RGB-D perception mapping

来源：评论

学校读者我要写书评

暂无评论

Bridging the Gap Between Events and Frames Through Unsupervised Domain Adaptation

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2022年第2期7卷 3515-3522页

作者： Messikommer, Nico Gehrig, Daniel Gehrig, Mathias Scaramuzza, Davide Univ Zurich Robot & Percept Grp CH-8050 Zurich Switzerland Univ Zurich Dept Informat CH-8050 Zurich Switzerland Univ Zurich Dept Neuroinformat CH-8092 Zurich Switzerland ETH CH-8092 Zurich Switzerland

Reliable perception during fast motion maneuvers or in high dynamic range environments is crucial for robotic systems. Since event cameras are robust to these challenging conditions, they have great potential to increase the reliability of robot vision. However, event-based vision has been held back by the shortage of labeled datasets due to the novelty of event cameras. To overcome this drawback, we propose a task transfer method to train models directly with labeled images and unlabeled event data. Compared to previous approaches, (i) our method transfers from single images to events instead of high frame rate videos, and (ii) does not rely on paired sensor data. To achieve this, we leverage the generative event model to split event features into content and motion features. This split enables efficient matching between latent spaces for events and images, which is crucial for successful task transfer. Thus, our approach unlocks the vast amount of existing image datasets for the training of event-based neural networks. Our task transfer method consistently outperforms methods targeting Unsupervised Domain Adaptation for object detection by 0.26 mAP (increase by 93%) and classification by 2.7% accuracy.

关键词： Deep learning for visual perception object detection segmentation and categorization transfer learning

来源：评论

学校读者我要写书评

暂无评论

Proximity Perception in Human-Centered Robotics: A Survey on Sensing Systems and Applications

引用

IEEE TRANSACTIONS ON ROBOTICS 2022年第3期38卷 1599-1620页

作者： Navarro, Stefan Escaida Muhlbacher-Karrer, Stephan Alagi, Hosam Zangl, Hubert Koyama, Keisuke Hein, Bjoern Duriez, Christian Smith, Joshua R. EscaidaNavarro, Stefan Inria Lille Nord Europe F-59650 Villeneuve Dascq France JOANNEUM RES ROBOT Inst Robot & Mechatron A-9020 Klagenfurt Austria Karlsruhe Inst Technol Inst Anthropomat & Robot Intelligent Proc Automat D-76131 Karlsruhe Germany Alpen Adria Univ Klagenfurt Inst Smart Syst Technol Sensors & Actuators A-9020 Klagenfurt Austria Osaka Univ Dept Syst Innovat Grad Sch Engn Sci Osaka 5608531 Japan Univ Washington Allen Sch Comp Sci & Engn Dept Elect Engn Seattle WA 98195 USA

Proximity perception is a technology that has the potential to play an essential role in the future of robotics. It can fulfill the promise of safe, robust, and autonomous systems in industry and everyday life, alongside humans, as well as in remote locations in space and underwater. In this survey article, we cover the developments of this field from the early days up to the present, with a focus on human-centered robotics. In this domain, proximity sensors are typically deployed in two scenarios: first, on the exterior of manipulator arms to support safety and interaction functionality, and second, on the inside of grippers or hands to support grasping and exploration. Therefore, based on this observation, in the beginning of this article, we propose a categorization to organize the use cases of proximity sensors in human-centered robotics. Then, we devote effort to present the sensing technologies and different measuring principles that have been developed over the years, also providing a summary in form of a table. Following, we review the literature regarding the applications that have been proposed. Finally, we give an overview of the most important trends that will shape the future of this domain.

关键词： Robot sensing systems Robots Sensors Service robots Skin Safety Collaboration Collision avoidance object detection perception for grasping and manipulation reactive and sensor-based planning segmentation and categorization

来源：评论

学校读者我要写书评

暂无评论

Automatic Radar-Camera Dataset Generation for Sensor-Fusion Applications

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2022年第2期7卷 2875-2882页

作者： Sengupta, Arindam Yoshizawa, Atsushi Cao, Siyang Univ Arizona Dept Elect & Comp Engn Tucson AZ 85721 USA Sony Grp Corp Tokyo 1080075 Japan

With heterogeneous sensors offering complementary advantages in perception, there has been a significant growth in sensor-fusion based research and development in object perception and tracking using classical or deep neural networks based approaches. However, supervised learning requires massive labeled data-sets, that require expensive manual labor to generate. This paper presents a novel approach that leverages YOLOv3 based highly accurate object detection from camera to automatically label point cloud data obtained from a co-calibrated radar sensor to generate labeled radar-image and radar-only data-sets to aid learning algorithms for different applications. To achieve this we first co-calibrate the vision and radar sensors and obtain a radar-to-camera transformation matrix. The collected radar returns are segregated by different targets using a density based clustering scheme and the cluster centroids are projected onto the camera image using the transformation matrix. The Hungarian Algorithm is then used to associate the radar cluster centroids with the YOLOv3 generated bounding box centroids, and are labeled with the predicted class. The proposed approach is efficient, easy to implement and aims to encourage rapid development of multi-sensor data-sets, which are extremely limited currently, com pared to the optical counterparts. The calibration process, software pipeline and the data-set generation is described in detail. Furthermore preliminary results from two sample applications for object detection using the data-sets are also presented.

关键词： Calibration and identification data sets for robotic vision neural and fuzzy control object detection segmentation and categorization sensor fusion

来源：评论

学校读者我要写书评

暂无评论

APPLE MOTS: Detection, segmentation and Tracking of Homogeneous Objects Using MOTS

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2022年第4期7卷 11418-11425页

作者： de Jong, Stefan Baja, Hilmy Tamminga, Karsjen Valente, Joao Wageningen Univ & Res Informat Technol Grp NL-6706 KN Wageningen Netherlands Univ Hasanuddin Ctr Technol Makassar 90245 Indonesia

Current multi object tracking and segmentation (MOTS) methods made great progress for the simultaneous detection and tracking of heterogeneous objects like cars and pedestrians. Nevertheless, all of these scenes consisted of dissimilar objects, which are easier to track than homogeneous and smaller objects, as those are more similar in appearance. Therefore, this is the first paper that explores the implementation of MOTS algorithms for the simultaneous detection and tracking of homogeneous objects. Towards this end, video data was acquired in an apple orchard using a wearable camera and unmanned aerial vehicles (UAV). The dataset, called APPLE MOTS, contains almost 86000 manually annotated apple masks and is the first public dataset in which apple instances are temporally consistent labelled across frames. Implementation of the MOTS architectures called TrackR-CNN and PointTrack indicates that they could be suitable for the joint detection (MOTSP: 80.4) and tracking (sMOTSA: 38.7, MOTSA: 52.9) of apples. This letter exposes the challenge of tracking homogeneous objects due to their similar shape and colour while detection performance remains state-of-the-art.

关键词： Agricultural automation deep learning methods object detection robotics and automation in agriculture and forestry segmentation and categorization

来源：评论

学校读者我要写书评

暂无评论

Exploiting Playbacks in Unsupervised Domain Adaptation for 3D Object Detection in Self-Driving Cars 39

Exploiting Playbacks in Unsupervised Domain Adaptation for 3...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： You, Yurong Diaz-Ruiz, Carlos Andres Wang, Yan Chao, Wei-Lun Hariharan, Bharath Campbell, Mark Weinbergert, Kilian Q. Cornell Univ Comp Sci Dept Ithaca NY 14853 USA Cornell Univ Mech & Aerosp Engn Dept Ithaca NY 14853 USA Ohio State Univ Dept Comp Sci & Engn Columbus OH 43210 USA

ISBN: (纸本)9781728196817

Self-driving cars must detect other traffic participants like vehicles and pedestrians in 3D in order to plan safe routes and avoid collisions. State-of-the-art 3D object detectors, based on deep learning, have shown promising accuracy but are prone to over-fit domain idiosyncrasies, making them fail in new environments-a serious problem for the robustness of self-driving cars. In this paper, we propose a novel learning approach that reduces this gap by fine-tuning the detector on high-quality pseudo-labels in the target domain - pseudo-labels that are automatically generated after driving based on replays of previously recorded driving sequences. In these replays, object tracks are smoothed forward and backward in time, and detections are interpolated and extrapolated-crucially, leveraging future information to catch hard cases such as missed detections due to occlusions or far ranges. We show, across five autonomous driving datasets, that fine-tuning the object detector on these pseudo-labels substantially reduces the domain gap to new driving environments, yielding strong improvements detection reliability and accuracy.

关键词： Object Detection segmentation and categorization Computer Vision for Automation Transfer Learning Deep Learning for Visual Perception

来源：评论

学校读者我要写书评

暂无评论

Monocular 3D Detection With Geometric Constraint Embedding and Semi-Supervised Training

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2021年第3期6卷 5565-5572页

作者： Li, Peixuan Zhao, Huaici Univ Chinese Acad Sci Chinese Acad Sci Shenyang Inst Automat Inst RobotKey Lab Optoelect Informat Proc Shenyang 110016 Liaoning Peoples R China Univ Chinese Acad Sci Chinese Acad Sci Shenyang Inst Automat Inst Intelligent MfgKey Lab Optoelect Informat P Shenyang 110016 Liaoning Peoples R China Key Lab Image Understanding & Comp Vis Shenyang 110016 Liaoning Peoples R China

In this work, we propose a novel one-stage and keypoint-based framework for monocular 3D object detection using only RGB images, called KM3D-Net. 2D detection only requires a deep neural network to predict 2D properties of objects, as it is a semanticity-aware task. For image-based 3D detection, we argue that the combination of a deep neural network and geometric constraints are needed to synergistically estimate appearance-related and spatial-related information. Here, we design a fully convolutional model to predict object keypoints, dimension, and orientation, and combine these with perspective geometry constraints to compute position attributes. Further, we reformulate the geometric constraints as a differentiable version and embed this in the network to reduce running time while maintaining the consistency of model outputs in an end-to-end fashion. Benefiting from this simple structure, we propose an effective semi-supervised training strategy for settings where labeled training data are scarce. In this strategy, we enforce a consensus prediction of two shared-weights KM3D-Net for the same unlabeled image under different input augmentation conditions and network regularization. In particular, we unify the coordinate-dependent augmentations as the affine transformation for the differential recovering position of objects, and propose a keypoint-dropout module for network regularization. Our model only requires RGB images, without synthetic data, instance segmentation, CAD model, or depth generator. Extensive experiments on the popular KITTI 3D detection dataset indicate that the KM3D-Net surpasses state-of-the-art methods by a large margin in both efficiency and accuracy. And also, to the best of our knowledge, this is the first application of semi-supervised learning in monocular 3D object detection. We surpass most of the previous fully supervised methods with only 13% labeled data on KITTI.

关键词： Autonomous Vehicle Navigation computer vision for automation object detection segmentation and categorization

来源：评论

学校读者我要写书评

暂无评论

Ground-Aware Monocular 3D Object Detection for Autonomous Driving

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2021年第2期6卷 919-926页

作者： Liu, Yuxuan Yixuan, Yuan Liu, Ming Hong Kong Univ Sci & Technol Dept Elect & Comp Engn Robot & Multipercept Lab Hong Kong Peoples R China City Univ Hong Kong Dept Elect Engn Hong Kong Peoples R China

Estimating the 3D position and orientation of objects in the environment with a single RGB camera is a critical and challenging task for low-cost urban autonomous driving and mobile robots. Most of the existing algorithms are based on the geometric constraints in 2D-3D correspondence, which stems from generic 6D object pose estimation. We first identify how the ground plane provides additional clues in depth reasoning in 3D detection in driving scenes. Based on this observation, we then improve the processing of 3D anchors and introduce a novel neural network module to fully utilize such application-specific priors in the framework of deep learning. Finally, we introduce an efficient neural network embedded with the proposed module for 3D object detection. We further verify the power of the proposed module with a neural network designed for monocular depth prediction. The two proposed networks achieve state-of-the-art performances on the KITTI 3D object detection and depth prediction benchmarks, respectively.

关键词： Three-dimensional displays Cameras Object detection Two dimensional displays Feature extraction Convolution Neural networks Automation technologies for smart cities deep learning for visual perception object detection segmentation and categorization

来源：评论

学校读者我要写书评

暂无评论

Hearing What You Cannot See: Acoustic Vehicle Detection Around Corners

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2021年第2期6卷 2587-2594页

作者： Schulz, Yannick Mattar, Avinash Kini Hehn, Thomas M. Kooij, Julian F. P. Delft Univ Technol Intelligent Vehicles Grp Delft Netherlands

This work proposes to use passive acoustic perception as an additional sensing modality for intelligent vehicles. We demonstrate that approaching vehicles behind blind corners can be detected by sound before such vehicles enter in line-of-sight. We have equipped a research vehicle with a roof-mounted microphone array, and show on data collected with this sensor setup that wall reflections provide information on the presence and direction of occluded approaching vehicles. A novel method is presented to classify if and from what direction a vehicle is approaching before it is visible, using as input Direction-of-Arrival features that can be efficiently computed from the streaming microphone array data. Since the local geometry around the ego-vehicle affects the perceived patterns, we systematically study several environment types, and investigate generalization across these environments. With a static ego-vehicle, an accuracy of 0.92 is achieved on the hidden vehicle classification task. Compared to a state-of-the-art visual detector, Faster R-CNN, our pipeline achieves the same accuracy more than one second ahead, providing crucial reaction time for the situations we study. While the ego-vehicle is driving, we demonstrate positive results on acoustic detection, still achieving an accuracy of 0.84 within one environment type. We further study failure cases across environments to identify future research directions.

关键词： Intelligent transportation systems object detection robot audition segmentation and categorization

来源：评论

学校读者我要写书评

暂无评论

Real-Time Ellipse Detection for Robotics Applications

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2021年第4期6卷 7009-7016页

作者： Keipour, Azarakhsh Pereira, Guilherme A. S. Scherer, Sebastian Carnegie Mellon Univ Robot Inst Pittsburgh PA 15208 USA West Virginia Univ Dept Mech & Aerosp Engn Morgantown WV 26506 USA

We propose a new algorithm for real-time detection and tracking of elliptic patterns suitable for real-world robotics applications. The method fits ellipses to each contour in the image frame and rejects ellipses that do not yield a good fit. The resulting detection and tracking method is lightweight enough to be used on robots' resource-limited onboard computers, can deal with lighting variations and detect the pattern even when the view is partial. The method is tested on an example application of an autonomous UAV landing on a fast-moving vehicle to show its performance indoors, outdoors, and in simulation on a real-world robotics task. The comparison with other well-known ellipse detection methods shows that our proposed algorithm outperforms other methods with the F1 score of 0.981 on a dataset with over 1500 frames. The videos of experiments, the source codes, and the collected dataset are provided with the letter.

关键词： Object detection segmentation and categorization computer vision for automation data sets for robotic vision ellipse detection and tracking

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：