检索结果-内蒙古大学图书馆

HD Map Update for Autonomous Driving With Crowdsourced Data

IEEE ROBOTICS AND AUTOMATION LETTERS 2021年第2期6卷 1895-1901页

作者： Kim, Kitae Cho, Soohyun Chung, Woojin Korea Univ Dept Mech Engn Seoul 07981 South Korea

Current self-driving cars can perform precise localization and generate collision-free trajectories using high definition (HD) maps which provide accurate road information. Therefore, keeping HD maps up to date is important for safe autonomous driving. In general, automotive HD maps are built by the use of expensive mapping systems. In addition, a lot of manual modifications are required in many cases. The conventional HD mapping cannot be frequently carried out due to the high cost. In this letter, we used a large amount of road data collected by crowdsourcing devices. Crowdsourcing devices consist of low-cost sensors. The devices are mounted on repeatedly traveling vehicles such as buses. Although collected data shows high uncertainty and low accuracy, a large amount of data can be obtained in a short time with low expense. We present a solution that keeps HD maps up to date by using crowdsourced data. The developed solution concentrates on landmark information among crowdsourced data and HD maps. By using uncertainty information, we chose reliable observations for map updating. Observation learner algorithms were carefully designed under the consideration of differences between discrete and continuous landmarks. The triggering condition for the map update can be adjusted by the proposed update mode selection strategy. The proposed map updating scheme has been experimentally verified by the use of crowdsourced data collected from real road environments.

关键词： Autonomous vehicle navigation mapping object detection segmentation and categorization

来源：评论

学校读者我要写书评

暂无评论

Visual Object Recognition in Indoor Environments Using Topologically Persistent Features

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2021年第4期6卷 7509-7516页

作者： Samani, Ekta U. Yang, Xingjian Banerjee, Ashis G. Univ Washington Dept Mech Engn Seattle WA 98195 USA Univ Washington Dept Ind & Syst Engn Seattle WA 98195 USA

Object recognition in unseen indoor environments remains a challenging problem for visual perception of mobile robots. In this letter, we propose the use of topologically persistent features, which rely on the objects' shape information, to address this challenge. In particular, we extract two kinds of features, namely, sparse persistence image (PI) and amplitude, by applying persistent homology to multi-directional height function-based filtrations of the cubical complexes representing the object segmentation maps. The features are then used to train a fully connected network for recognition. For performance evaluation, in addition to a benchmark dataset, we collect a new dataset, comprising scene images from two different environments, namely, a living room and a mock warehouse. The scenes are captured using varying camera poses under different illumination conditions and include up to five different objects from a given set of fourteen objects. On the benchmark dataset, sparse PI features show better recognition performance in unseen environments than the features learned using the widely used ResNetV2-56 and EfficientNet-B4 models. Further, they provide slightly higher recall and accuracy values than Faster R-CNN, an end-to-end object detection method, and its state-of-the-art variant, Domain Adaptive Faster R-CNN. The performance of our methods also remains relatively unchanged from the training environment (living room) to the unseen environment (mock warehouse) in the new dataset. In contrast, the performance of the object detection methods drops substantially. We also implement the proposed method on a real-world robot to demonstrate its usefulness.

关键词： Recognition AI-Enabled robotics object detection segmentation and categorization

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Image segmentation by Mutual Information Maximization and Adversarial Regularization

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2021年第4期6卷 6931-6938页

作者： Mirsadeghi, S. Ehsan Royat, Ali Rezatofighi, Hamid Amirkabir Univ Technol Fac Elect Engn Janat Abad Tehran *** Iran Sharif Univ Technol Fac Elect Engn Tehran Iran Monash Univ Fac Informat Technol Dept Data Sci & AI Melbourne Vic 3800 Australia

Semantic segmentation is one of the basic, yet essential scene understanding tasks for an autonomous agent. The recent developments in supervised machine learning and neural networks have enjoyed great success in enhancing the performance of the state-of-the-art techniques for this task. However, their superior performance is highly reliant on the availability of a large-scale annotated dataset. In this letter, we propose a novel fully unsupervised semantic segmentation method, the so-called Information Maximization and Adversarial Regularization segmentation (InMARS). Inspired by human perception which parses a scene into perceptual groups, rather than analyzing each pixel individually, our proposed approach first partitions an input image into meaningful regions (also known as superpixels). Next, it utilizes Mutual-Information-Maximization followed by an adversarial training strategy to cluster these regions into semantically meaningful classes. To customize an adversarial training scheme for the problem, we incorporate adversarial pixel noise along with spatial perturbations to impose photometrical and geometrical invariance on the deep neural network. Our experiments demonstrate that our method achieves the state-of-the-art performance on two commonly used unsupervised semantic segmentation datasets, COCO-Stuff, and Potsdam.

关键词： Deep learning methods object detection segmentation and categorization

来源：评论

学校读者我要写书评

暂无评论

PennSyn2Real: Training Object Recognition Models Without Human Labeling

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2021年第3期6卷 5032-5039页

作者： Nguyen, Ty Miller, Ian D. Cohen, Avi Thakur, Dinesh Guru, Arjun Prasad, Shashank Taylor, Camillo J. Chaudhari, Pratik Kumar, Vijay Univ Penn Grasp Lab Philadelphia PA 19104 USA Amazon Seattle WA USA

Scalable training data generation is a critical problem in deep learning. We propose PennSyn2Real - a photo-realistic synthetic dataset consisting of more than 100 000 4K images of more than 20 types of micro aerial vehicles (MAVs). The dataset can be used to generate arbitrary numbers of training images for high-level computer vision tasks such as MAV detection and classification. Our data generation framework bootstraps chroma-keying, a mature cinematography technique, with a motion tracking system providing artifact-free and curated annotated images. Our system, therefore, allows object orientations and lighting to be controlled. This framework is easy to set up and can be applied to a broad range of objects, reducing the gap between synthetic and real-world data. We show that synthetic data generated using this framework can be directly used to train CNN models for common object recognition tasks such as detection and segmentation. We demonstrate competitive performance in comparison with training using only real images. Furthermore, bootstrapping the generated synthetic data in few-shot learning can significantly improve the overall performance, reducing the number of required training data samples to achieve the desired accuracy.

关键词： Object detection segmentation and categorization aerial systems perception and autonomy surveillance robotic systems data sets for robotic vision

来源：评论

学校读者我要写书评

暂无评论

GEM: Glare or Gloom, I Can Still See You - End-to-End Multi-Modal Object Detection

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2021年第4期6卷 6321-6328页

作者： Mazhar, Osama Babuska, Robert Kober, Jens Delft Univ Technol Cognit Robot Dept NL-2628 CD Delft Netherlands Czech Tech Univ Czech Inst Informat Robot & Cybernet Prague 16636 Czech Republic

Deep neural networks designed for vision tasks are often prone to failure when they encounter environmental conditions not covered by the training data. Single-modal strategies are insufficient when the sensor fails to acquire information due to malfunction or its design limitations. Multi-sensor configurations are known to provide redundancy, increase reliability, and are crucial in achieving robustness against asymmetric sensor failures. To address the issue of changing lighting conditions and asymmetric sensor degradation in object detection, we develop a multi-modal 2D object detector, and propose deterministic and stochastic sensor-aware feature fusion strategies. The proposed fusion mechanisms are driven by the estimated sensor measurement reliability values/weights. Reliable object detection in harsh lighting conditions is essential for applications such as self-driving vehicles and human-robot interaction. We also propose a new "r-blended" hybrid depth modality for RGB-D sensors. Through extensive experimentation, we show that the proposed strategies outperform the existing state-of-the-art methods on the FLIR-Thermal dataset, and obtain promising results on the SUNRGB-D dataset. We additionally record a new RGB-Infra indoor dataset, namely L515-Indoors, and demonstrate that the proposed object detection methodologies are highly effective for a variety of lighting conditions.

关键词： computer vision for automation deep learning for visual perception object detection RGB-D perception segmentation and categorization sensor fusion

来源：评论

学校读者我要写书评

暂无评论

LaneAF: Robust Multi-Lane Detection With Affinity Fields

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2021年第4期6卷 7477-7484页

作者： Abualsaud, Hala Liu, Sean Lu, David B. Situ, Kenny Rangesh, Akshay Trivedi, Mohan M. Univ Calif San Diego Lab Intelligent & Safe Automobiles San Diego CA 92092 USA

This study presents an approach to lane detection involving the prediction of binary segmentation masks and per-pixel affinity fields. These affinity fields, along with the binary masks, can then be used to cluster lane pixels horizontally and vertically into corresponding lane instances in a post-processing step. This clustering is achieved through a simple row-by-row decoding process with little overhead;such an approach allows LaneAF to detect a variable number of lanes without assuming a fixed or maximum number of lanes. Moreover, this form of clustering is more interpretable in comparison to previous visual clustering approaches, and can be analyzed to identify and correct sources of error. Qualitative and quantitative results obtained on popular lane detection datasets demonstrate the model's ability to detect and cluster lanes effectively and robustly. Our proposed approach sets a new state-of-the-art on the challenging CULane dataset and the recently introduced Unsupervised LLAMAS dataset.

关键词： Object detection segmentation and categorization deep learning for visual perception

来源：评论

学校读者我要写书评

暂无评论

Target-Style-Aware Unsupervised Domain Adaptation for Object Detection

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2021年第2期6卷 3825-3832页

作者： Yun, Woo-han Han, ByungOk Lee, Jaeyeon Kim, Jaehong Kim, Junmo Korea Adv Inst Sci & Technol Robot Program Daejeon 34129 South Korea ETRI Intelligent Robot Res Div Daejeon 34129 South Korea Korea Adv Inst Sci & Technol Sch Elect Engn Daejeon 34141 South Korea

Vision modules running on mobility platforms, such as robots and cars, often face challenging situations such as a domain shift where the distributions of training (source) data and test (target) data are different. The domain shift is caused by several variation factors, such as style, camera viewpoint, object appearance, object size, backgrounds, and scene layout. In this work, we propose an object detection training framework for unsupervised domain-style adaptation. The proposed training framework transfers target-style information to source samples and simultaneously trains the detection network with these target-stylized source samples in an end-to-end manner. The detection network can learn the target domain from the target-stylized source samples. The style is extracted from object areas obtained by using pseudo-labels to reflect the style of the object areas more than that of the irrelevant backgrounds. We empirically verified that the proposed methods improve detection accuracy in diverse domain shift scenarios using the Cityscapes, FoggyCityscapes, Sim10k, BDD100k, PASCAL, and Watercolor datasets.

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

LiDARTag: A Real-Time Fiducial Tag System for Point Clouds

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2021年第3期6卷 4875-4882页

作者： Huang, Jiunn-Kai Wang, Shoutian Ghaffari, Maani Grizzle, Jessy W. Univ Michigan Robot Inst Ann Arbor MI 48109 USA

Image-based fiducial markers are useful in problems such as object tracking in cluttered or textureless environments, camera (and multi-sensor) calibration tasks, and vision-based simultaneous localization and mapping (SLAM). The state-of-the-art fiducial marker detection algorithms rely on the consistency of the ambient lighting. This article introduces LiDARTag, a novel fiducial tag design and detection algorithm suitable for light detection and ranging (LiDAR) point clouds. The proposed method runs in real-time and can process data at 100 Hz, which is faster than the currently available LiDAR sensor frequencies. Because of the LiDAR sensors' nature, rapidly changing ambient lighting will not affect the detection of a LiDARTag;hence, the proposed fiducial marker can operate in a completely dark environment. In addition, the LiDARTag nicely complements and is compatible with existing visual fiducial markers, such as AprilTags, allowing for efficient multi-sensor fusion and calibration tasks. We further propose a concept of minimizing a fitting error between a point cloud and the marker's template to estimate the marker's pose. The proposed method achieves millimeter error in translation and a few degrees in rotation. Due to LiDAR returns' sparsity, the point cloud is lifted to a continuous function in a reproducing kernel Hilbert space where the inner product can be used to determine a marker's ID. The experimental results, verified by a motion capture system, confirm that the proposed method can reliably provide a tag's pose and unique ID code. The rejection of false positives is validated on the Google Cartographer indoor dataset and the Honda H3D outdoor dataset. All implementations are coded in C++ and are available at https://***/UMich-BipedLab/LiDARTag.

关键词： Range sensing visual tracking object detection segmentation and categorization computer vision for automation

来源：评论

学校读者我要写书评

暂无评论

Hough²Map - Iterative Event-Based Hough Transform for High-Speed Railway Mapping

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2021年第2期6卷 2745-2752页

作者： Tschopp, Florian von Einem, Cornelius Cramariuc, Andrei Hug, David Palmer, Andrew William Siegwart, Roland Chli, Margarita Nieto, Juan Swiss Fed Inst Technol Autonomous Syst Lab CH-8092 Zurich Switzerland Swiss Fed Inst Technol Vis Robot Lab CH-8092 Zurich Switzerland Siemens Mobil D-12489 Berlin Germany

To cope with the growing demand for transportation on the railway system, accurate, robust, and high-frequency positioning is required to enable a safe and efficient utilization of the existing railway infrastructure. As a basis for a localization system we propose a complete on-board mapping pipeline able to map robust meaningful landmarks, such as poles from power lines, in the vicinity of the vehicle. Such poles are good candidates for reliable and long term landmarks even through difficult weather conditions or seasonal changes. To address the challenges of motion blur and illumination changes in railway scenarios we employ a Dynamic Vision Sensor, a novel event-based camera. Using a sideways oriented on-board camera, poles appear as vertical lines. To map such lines in a real-time event stream, we introduce Hough(2)Map, a novel consecutive iterative event-based Hough transform framework capable of detecting, tracking, and triangulating close-by structures. We demonstrate the mapping reliability and accuracy of Hough(2)Map on real-world data in typical usage scenarios and evaluate using surveyed infrastructure ground truth maps. Hough(2)Map achieves a detection reliability of up to 92% and a mapping root mean square error accuracy of 1.1518 m.(1)

关键词： Computer vision for transportation object detection segmentation and categorization mapping

来源：评论

学校读者我要写书评

暂无评论

Robust Data Association for Multi-Object Detection in Maritime Environments Using Camera and Radar Measurements

引用

IEEE ROBOTICS AND AUTOMATION LETTERS 2021年第3期6卷 5865-5872页

作者： Kim, Keunhwan Kim, Jonghwi Kim, Jinwhan Korea Elect Technol Inst Intelligent Robot Res Ctr Bucheon 14502 South Korea Korea Adv Inst Sci & Technol Dept Mech Engn Daejeon 34141 South Korea

This letter presents a robust data association method for fusing camera and marine radar measurements in order to automatically detect surface ships and determine their locations with respect to the observing ship. In the preprocessing step for sensor fusion, convolutional neural networks are used to perform feature extraction from camera images and semantic segmentation from radar images. The correspondences between the camera and radar image features are optimized using a pair of geometric parameters, and the positions of all the matched object features are determined. The proposed method enables robust data association even without accurate calibration and alignment between the camera and radar measurements. The feasibility and performance of the proposed method are demonstrated using an experimental dataset obtained in a real coastal environment.

关键词： Marine robotics sensor fusion object detection segmentation and categorization

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：