检索结果-内蒙古大学图书馆

Edge-guided Representation Learning for Underwater Object Detection

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Dai, Linhui Liu, Hong Song, Pinhao Tang, Hao Ding, Runwei Li, Shengquan Key Laboratory of Machine Perception Shenzhen Graduate School Peking University Shenzhen China Robotics Research Group KU Leuven Leuven Belgium Computer Vision Lab ETH Zurich Zurich Switzerland Peng Cheng Laboratory Shenzhen China

Underwater object detection (UOD) is crucial for marine economic development, environmental protection, and the planet’s sustainable development. The main challenges of this task arise from low-contrast, small objects, and mimicry of aquatic organisms. The key to addressing these challenges is to focus the model on obtaining more discriminative information. We observe that the edges of underwater objects are highly unique and can be distinguished from low-contrast or mimicry environments based on their edges. Motivated by this observation, we propose an Edge-guided Representation Learning Network, termed ERL-Net, that aims to achieve discriminative representation learning and aggregation under the guidance of edge cues. Firstly, we introduce an edge-guided attention module to model the explicit boundary information, which generates more discriminative features. Secondly, a feature aggregation module is proposed to aggregate the multi-scale discriminative features by regrouping them into three levels, effectively aggregating global and local information for locating and recognizing underwater objects. Finally, we propose a wide and asymmetric receptive field block to enable features to have a wider receptive field, allowing the model to focus on more small object information. Comprehensive experiments on three challenging underwater datasets show that our method achieves superior performance on the UOD task. Copyright © 2023, The Authors. All rights reserved.

关键词： Object detection

Task-Oriented Grasp Prediction with Visual-Language Inputs

学校读者我要写书评

暂无评论

Task-Oriented Grasp Prediction with Visual-Language Inputs

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

作者： Chao Tang Dehao Huang Lingxiao Meng Weiyu Liu Hong Zhang Shenzhen Key Laboratory of Robotics and Computer Vision Southern University of Science and Technology Shenzhen China Department of Electronic and Electrical Engineering Southern University of Science and Technology Shenzhen China Stanford University United States

To perform household tasks, assistive robots receive commands in the form of user language instructions for tool manipulation. The initial stage involves selecting the intended tool (i.e., object grounding) and grasping it in a task-oriented manner (i.e., task grounding). Nevertheless, prior researches on visual-language grasping (VLG) focus on object grounding, while disregarding the fine-grained impact of tasks on object grasping. Task-incompatible grasping of a tool will inevitably limit the success of subsequent manipulation steps. Motivated by this problem, this paper proposes GraspCLIP, which addresses the challenge of task grounding in addition to object grounding to enable task-oriented grasp prediction with visual-language inputs. Evaluation on a custom dataset demonstrates that GraspCLIP achieves superior performance over established baselines with object grounding only. The effectiveness of the proposed method is further validated on an assistive robotic arm for grasping previously unseen kitchen tools given the task specification. Our presentation video is available at: https://***/watch?v=e1wfYQPeAXU.

关键词：

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Lin, Zhenchao He, Li Yang, Hongqiang Sun, Xiaoqun Zhang, Guojin Chen, Weinan Guan, Yisheng Zhang, Hong School of Electromechanical Engineering Guangdong University of Technology Guangzhou China Department of Electronic and Electrical Engineering Southern University of Science and Technology China Shenzhen Key Laboratory of Robotics and Computer Vision China Meituan Technology Co. Ltd Shenzhen China

Large-scale point cloud consists of a multitude of individual objects, thereby encompassing rich structural and underlying semantic contextual information, resulting in a challenging problem in efficiently segmenting a point cloud. Most existing researches mainly focus on capturing intricate local features without giving due consideration to global ones, thus failing to leverage semantic context. In this paper, we propose a Similarity-Weighted Convolution and local-global Fusion Network, named SWCF-Net, which takes into account both local and global features. We propose a Similarity-Weighted Convolution (SWConv) to effectively extract local features, where similarity weights are incorporated into the convolution operation to enhance the generalization capabilities. Then, we employ a downsampling operation on the K and V channels within the attention module, thereby reducing the quadratic complexity to linear, enabling Transformer to deal with large-scale point cloud. At last, orthogonal components are extracted in the global features and then aggregated with local features, thereby eliminating redundant information between local and global features and consequently promoting efficiency. We evaluate SWCF-Net on large-scale outdoor datasets SemanticKITTI and Toronto3D. Our experimental results demonstrate the effectiveness of the proposed network. Our method achieves a competitive result with less computational cost, and is able to handle large-scale point clouds efficiently. The code is available at https://***/Sylva-Lin/SWCF-Net Copyright © 2024, The Authors. All rights reserved.

关键词： Convolution

A Single 2D Pose with Context is Worth Hundreds for 3D Human Pose Estimation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhao, Qitao Zheng, Ce Liu, Mengyuan Chen, Chen Robotics Institute Carnegie Mellon University United States Center for Research in Computer Vision University of Central Florida United States Key Laboratory of Machine Perception Peking University Shenzhen Graduate School China

The dominant paradigm in 3D human pose estimation that lifts a 2D pose sequence to 3D heavily relies on long-term temporal clues (i.e., using a daunting number of video frames) for improved accuracy, which incurs performance saturation, intractable computation and the non-causal problem. This can be attributed to their inherent inability to perceive spatial context as plain 2D joint coordinates carry no visual cues. To address this issue, we propose a straightforward yet powerful solution: leveraging the readily available intermediate visual representations produced by off-the-shelf (pre-trained) 2D pose detectors - no finetuning on the 3D task is even needed. The key observation is that, while the pose detector learns to localize 2D joints, such representations (e.g., feature maps) implicitly encode the joint-centric spatial context thanks to the regional operations in backbone networks. We design a simple baseline named Context-Aware PoseFormer to showcase its effectiveness. Without access to any temporal information, the proposed method significantly outperforms its context-agnostic counterpart, PoseFormer [77], and other state-of-the-art methods using up to hundreds of video frames regarding both speed and precision. Project page: ***/ContextAware-PoseFormer. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Goswami, Dipam Liu, Yuyang Twardowski, Bartlomiej van de Weijer, Joost Department of Computer Science Universitat Autònoma de Barcelona Spain Computer Vision Center Barcelona Spain University of Chinese Academy of Sciences China State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences China IDEAS-NCBR

Exemplar-free class-incremental learning (CIL) poses several challenges since it prohibits the rehearsal of data from previous tasks and thus suffers from catastrophic forgetting. Recent approaches to incrementally learning the classifier by freezing the feature extractor after the first task have gained much attention. In this paper, we explore prototypical networks for CIL, which generate new class prototypes using the frozen feature extractor and classify the features based on the Euclidean distance to the prototypes. In an analysis of the feature distributions of classes, we show that classification based on Euclidean metrics is successful for jointly trained features. However, when learning from non-stationary data, we observe that the Euclidean metric is suboptimal and that feature distributions are heterogeneous. To address this challenge, we revisit the anisotropic Mahalanobis distance for CIL. In addition, we empirically show that modeling the feature covariance relations is better than previous attempts at sampling features from normal distributions and training a linear classifier. Unlike existing methods, our approach generalizes to both many- and few-shot CIL settings, as well as to domain-incremental settings. Interestingly, without updating the backbone network, our method obtains state-of-the-art results on several standard continual learning benchmarks. Code is available at https://***/dipamgoswami/FeCAM. © 2023, CC BY.

关键词： Normal distribution

Adaptive Generalized Social Space Delimitation for Human-Robot Interaction Tasks

学校读者我要写书评

暂无评论

Adaptive Generalized Social Space Delimitation for Human-Rob...

IEEE Latin American robotics Symposium, LARS

作者： Manuela M. F. Silva Aline F. F. Silva Douglas G. Macharet Department of Computer Science Computer Vision and Robotics Laboratory (VeRLab) Universidade Federal de Minas Gerais Belo Horizonte MG Brazil Laboratório de Inteligência Computacional e Robótica (LICRo) Instituto Federal do Triângulo Mineiro (IFTM) Campus Patrocínio Brazil

ISBN: (数字)9798331508807

ISBN: (纸本)9798331508814

Human-Robot Interaction (HRI) research is of paramount importance as it addresses the rapidly evolving landscape where robots are increasingly integrated into everyday life. Social spaces refer to the invisible zones that individuals maintain around themselves, dictating appropriate distances for various types of interactions. This concept is pivotal in HRI, as it ensures that robots engage with humans in ways that are both comfortable and respectful of personal boundaries. In this paper, we propose a novel social space delimitation approach based on deformable elastic bands. Our method leverages the flexibility and adaptability of elastic band theory to dynamically define and adjust social spaces around individuals and groups. The results, based on both static and dynamic cases as well as a real-world dataset, show that our approach achieves a responsive and accurate representation of social spaces, that can accommodate varying group configurations and environmental conditions.

关键词： Accuracy Human-robot interaction Robots

Fast Candidate Region Extraction for SAR Ship Target 37

学校读者我要写书评

暂无评论

Fast Candidate Region Extraction for SAR Ship Target

37th Youth Academic Annual Conference of Chinese Association of Automation, YAC 2022

作者： Zhang, Panpan Luo, Haibo Xu, Zheng He, Miao Shenyang Institute of Automation Shenyang110016 China Institutes for Robotics and Intelligent Manufacturing Shenyang110016 China University of Chinese Academy of Sciences Beijing100049 China Key Laboratory of Opto-Electronic Information Processing Shenyang110016 China The Key Lab of Image Understanding and Computer Vision Shenyang110016 China

ISBN: (纸本)9781665465366

At present, deep learning technology is widely used in ship target detection in synthetic aperture radar (SAR) images. However, high-resolution remote sensing SAR images cover a larger area and have larger image sizes. To be able to use the deep learning model for training and testing, the image needs to be cropped to the appropriate size. In a high-resolution SAR ship image, the ship target usually takes only a small part of the whole image. As a result, only part of the cropped image contains the target, and most of the rest are background regions. This will cause a lot of computational redundancy in the model inference stage. To solve this problem, a fast candidate region extraction algorithm is proposed in this paper for ship target extraction. The algorithm consists of three parts: firstly, extract the saliency map of the SAR ship image, secondly, perform median filtering on the segmented image, and thirdly, extract candidate regions. The superiority of the algorithm was demonstrated by experiments on the AIR-SARShip-1.0 dataset. © 2022 IEEE.

关键词： Synthetic aperture radar

CSSL-MHTR: Continual Self-Supervised Learning for Scalable Multi-script Handwritten Text Recognition

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Dhiaf, Marwa Souibgui, Mohamed Ali Wang, Kai Liu, Yuyang Kessentini, Yousri Fornés, Alicia Rouhou, Ahmed Cheikh InstaDeep United Kingdom Computer Vision Center UAB Spain Digital Research Center of Sfax SM@RTS Tunisia State Key Laboratory of Robotics China Shenyang Institute of Automation Chinese Academy of Sciences China

Self-supervised learning has recently emerged as a strong alternative in document analysis. These approaches are now capable of learning high-quality image representations and overcoming the limitations of supervised methods, which require a large amount of labeled data. However, these methods are unable to capture new knowledge in an incremental fashion, i.e. when data is presented to the model sequentially, which is closer to the realistic scenario. In this paper, we explore the potential of continual self-supervised learning to alleviate the catastrophic forgetting problem in handwritten text recognition, as an example of sequence recognition. Our method consists in adding intermediate layers called adapters for each task, and efficiently distilling knowledge from the previous model while learning the current task. Our proposed framework is efficient in both computation and memory complexity. To demonstrate its effectiveness, we evaluate our method by transferring the learned model to diverse text recognition downstream tasks, including Latin and non-Latin scripts. As far as we know, this is the first application of continual self-supervised learning for handwritten text recognition. We attain state-of-the-art performance in English, Italian, and Russian, whilst adding only a few parameters per task. The code and trained models will be publicly available1 © 2023, CC BY.

关键词： Supervised learning

A vision Based Hardware-Software Real-Time Control System for the Autonomous Landing of an UAV 1

学校读者我要写书评

暂无评论

International Conference on computer vision and Graphics, ICCVG 2020

作者： Blachut, Krzysztof Szolc, Hubert Wasala, Mateusz Kryjak, Tomasz Gorgon, Marek Embedded Vision Systems Group Computer Vision Laboratory Department of Automatic Control and Robotics AGH University of Science and Technology Krakow Poland

ISBN: (数字)9783030590062

ISBN: (纸本)9783030590055

In this paper we present a vision based hardware-software control system enabling the autonomous landing of a multirotor unmanned aerial vehicle (UAV). It allows for the detection of a marked landing pad in real-time for a 1280 720 @ 60 fps video stream. In addition, a LiDAR sensor is used to measure the altitude above ground. A heterogeneous Zynq SoC device is used as the computing platform. The solution was tested on a number of sequences and the landing pad was detected with 96% accuracy. This research shows that a reprogrammable heterogeneous computing system is a good solution for UAVs because it enables real-time data stream processing with relatively low energy consumption. © 2020, Springer Nature Switzerland AG.

关键词： System-on-chip