检索结果-内蒙古大学图书馆

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Juncheng Mu Lin Bie Shaoyi Du Yue Gao BNRist THUIBCS School of Software Tsinghua University National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications and Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Point cloud registration is still a challenging and open problem. For example, when the overlap between two point clouds is extremely low, geo-only features may be not suf-ficient. Therefore, it is important to further explore how to utilize color data in this task. Under such circumstances, we propose ColorPCR for color point cloud registration with multi-stage geometric-color fusion. We design a Hier-archical Color Enhanced Feature Extraction module to ex-tract multi-level geometric-color features, and a GeoColor Superpoint Matching Module to encode transformation-invariant geo-color global context for robust patch corre-spondences. In this way, both geometric and color data can be used, thus leading to robust performance even under extremely challenging scenarios, such as low overlap between two point clouds. To evaluate the performance of our method, we colorize 3DMatch/3DLoMatch datasets as Color3DMatch/Color3DLoMatch and evaluations on these datasets demonstrate the effectiveness of our proposed method. Our method achieves state-of-the-art registration recall of 97.5%/88.9% on them.

关键词： Point cloud compression Computer vision Accuracy Image color analysis Feature extraction Pattern recognition Task analysis

来源：评论

学校读者我要写书评

暂无评论

Towards High-resolution 3D Anomaly Detection via Group-Level Feature Contrastive Learning 24

Towards High-resolution 3D Anomaly Detection via Group-Level...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Zhu, Hongze Xie, Guoyang Hou, Chengbin Dai, Tao Gao, Can Wang, Jinbao Shen, Linlin National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Department of Computer Science City University of Hong Kong Hong Kong Hong Kong Department of Intelligent Manufacturing CATL Ningde China Fuzhou Fuyao Institute for Advanced Study Fuyao University of Science and Technology Fuzhou China College of Computer Science and Software Engineering Shenzhen University Shenzhen China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen China Shenzhen University Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China

ISBN: (纸本)9798400706868

High-resolution point clouds (HRPCD) anomaly detection (AD) plays a critical role in precision machining and high-end equipment manufacturing. Despite considerable 3D-AD methods that have been proposed recently, they still cannot meet the requirements of the HRPCD-AD task. There are several challenges: i) It is difficult to directly capture HRPCD information due to large amounts of points at the sample level;ii) The advanced transformer-based methods usually obtain anisotropic features, leading to degradation of the representation;iii) The proportion of abnormal areas is very small, which makes it difficult to characterize. To address these challenges, we propose a novel group-level feature-based network, called Group3AD, which has a significantly efficient representation ability. First, we design an Intercluster Uniformity Network (IUN) to present the mapping of different groups in the feature space as several clusters, and obtain a more uniform distribution between clusters representing different parts of the point clouds in the feature space. Then, an Intracluster Alignment Network (IAN) is designed to encourage groups within the cluster to be distributed tightly in the feature space. In addition, we propose an Adaptive Group-Center Selection (AGCS) based on geometric information to improve the pixel density of potential anomalous regions during inference. The experimental results verify the effectiveness of our proposed Group3AD, which surpasses Reg3D-AD by the margin of 5% in terms of object-level AUROC on Real3D-AD. We provide the code and supplementary information on our website: https://***/M-3LAB/Group3AD. © 2024 ACM.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Electric Vehicle Physical Parameters Identification 48

Electric Vehicle Physical Parameters Identification

引用

48th Annual Conference of the IEEE Industrial Electronics Society, IECON 2022

作者： Maia, Ricardo Mendes, Jerome Araujo, Rui University of Coimbra Institute of Systems and Robotics Department of Electrical and Computer Engineering Pólo II CoimbraPT-3030-290 Portugal Critical Software S.A. Pq. Ind. de Taveiro Lt 49 CoimbraPT-3045-504 Portugal

ISBN: (数字)9781665480253

ISBN: (纸本)9781665480253

Electric vehicle physical parameters highly influence the modeling of its different systems. Although a simulation using data acquired from field tests can have satisfactory results, the parameters inaccuracy, due to either insufficient information or wear, can prevent a better performance. In this paper, 10 electric vehicle physical parameters are adjusted/calibrated by three metaheuristic algorithms: Particle Swarm Optimization, Genetic Algorithms, and Simulated Annealing. Moreover, tests on real short and long distance data sets were used in order to validate the proposed framework to EV model calibration. The results achieved indicate that parameter calibration is effective in the reduction of the modeling error. © 2022 IEEE.

关键词： Simulated annealing

来源：评论

学校读者我要写书评

暂无评论

PROGRESSIVE DISTRIBUTION ALIGNMENT BASED ON LABEL CORRECTION FOR UNSUPERVISED DOMAIN ADAPTATION

PROGRESSIVE DISTRIBUTION ALIGNMENT BASED ON LABEL CORRECTION...

引用

2021 IEEE International Conference on Multimedia and Expo, ICME 2021

作者： Li, Yong Li, Desheng Lu, Yuwu Gao, Can Wang, Wenjing Lu, Jianglin College of Computer Science and Software Engineering Shenzhen University SZU Branch Shenzhen Institute of Artificial Intelligence Robotics for Society Guangdong Key Laboratory of Intelligent Information Processing China

ISBN: (纸本)9781665438643

Unsupervised domain adaptation (UDA) aims to transfer knowledge between different domains. Most of the existing UDA methods try to align the conditional distribution between the source and target domains by utilizing the information of pseudo labels induced from the target domain. To tackle the negative transfer caused by inaccurate pseudo labels, we propose a novel UDA method named progressive distribution alignment based on label correction (PDALC). Specifically, PDALC uses the class discriminative information to perform subspace learning to obtain the domain invariance subspace. Furthermore, a new mechanism of pseudo label correction is introduced to measure the reliability of pseudo labels and utmostly correct the inaccurate pseudo labels. By combining subspace learning with label correction, the performance of PDALC can be continuously improved, which in turn reduces the generation of inaccurate pseudo labels. The experimental results show that the proposed method outperforms the state-of-the-art UDA methods. © 2021 IEEE

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Shift from Texture-bias to Shape-bias: Edge Deformation-based Augmentation for Robust Object Recognition

Shift from Texture-bias to Shape-bias: Edge Deformation-base...

引用

International Conference on Computer Vision (ICCV)

作者： Xilin He Qinliang Lin Cheng Luo Weicheng Xie Siyang Song Feng Liu Linlin Shen Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University Shenzhen Institue of Artificial Intelligence & Robotics for Society Guangdong Key Laboratory of Intelligent Information Processing University of Leicester

Recent studies have shown the vulnerability of CNNs under perturbation noises, which is partially caused by the reason that the well-trained CNNs are too biased toward the object texture, i.e., they make predictions mainly based on texture cues. To reduce this texture-bias, current studies resort to learning augmented samples with heavily perturbed texture to make networks be more biased toward relatively stable shape cues. However, such methods usually fail to achieve real shape-biased networks due to the insufficient diversity of the shape cues. In this paper, we propose to augment the training dataset by generating semantically meaningful shapes and samples, via a shape deformation-based online augmentation, namely as SDbOA. The samples generated by our SDbOA have two main merits. First, the augmented samples with more diverse shape variations enable networks to learn the shape cues more elaborately, which encourages the network to be shape-biased. Second, semantic-meaningful shape-augmentation samples could be produced by jointly regularizing the generator with object texture and edge-guidance soft constraint, where the edges are represented more robustly with a self information guided map to better against the noises on them. Extensive experiments under various perturbation noises demonstrate the obvious superiority of our shape-bias-motivated model over the state of the arts in terms of robustness performance. Code is available at https://***/C0notSilly/-ICCV-23-Edge-Deformation-based-Online-Augmentation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Shearlet-Based Structure-Aware Filtering for Hyperspectral and LiDAR Data Classification

引用

Journal of Remote Sensing 2021年第1期2021卷 237-261页

作者： Sen Jia Zhangwei Zhan Meng Xu College of Computer Science and Software Engineering Shenzhen UniversityShenzhenChina Key Laboratory for Geo-Environmental Monitoring of Coastal Zone of the Ministry of Natural Resources Shenzhen UniversityShenzhenChina SZU Branch Shenzhen Institute of Artificial Intelligence and Robotics for SocietyShenzhenChina

The joint interpretation of hyperspectral images(HSIs)and light detection and ranging(LiDAR)data has developed rapidly in recent years due to continuously evolving image processing ***,most feature extraction methods are carried out by convolving the raw data with fixed-size filters,whereas the structural and texture information of objects in multiple scales cannot be sufficiently *** this article,a shearlet-based structure-aware filtering approach,abbreviated as ShearSAF,is proposed for HSI and LiDAR feature extraction and ***,superpixel-guided kernel principal component analysis(KPCA)is firstly adopted on raw HSIs to reduce the ***,the KPCA-reduced HSI and LiDAR data are converted to the shearlet domain for texture and area feature *** contrast,superpixel segmentation algorithm utilizes the raw HSI data to obtain the initial oversegmentation ***,by utilizing a well-designed minimum merging cost that fully considers spectral(HSI and LiDAR data),texture,and area features,a region merging procedure is gradually conducted to produce a final merging ***,a scale map that locally indicates the filter size is achieved by calculating the edge ***,the KPCA-reduced HSI and LiDAR data are convolved with the locally adaptive filters for feature extraction,and a random forest(RF)classifier is thus adopted for *** effectiveness of our ShearSAF approach is verified on three real-world datasets,and the results show that the performance of ShearSAF can achieve an accuracy higher than that of comparison methods when exploiting small-size training sample *** codes of this work will be available at http://***/papers/for the sake of reproducibility.

关键词： LiDAR Shear utilize

来源：评论

学校读者我要写书评

暂无评论

Generalizing 6-DoF Grasp Detection via Domain Prior Knowledge

Generalizing 6-DoF Grasp Detection via Domain Prior Knowledg...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Haoxiang Ma Modi Shi Boyang Gao Di Huang State Key Laboratory of Software Development Environment Beihang University Beijing China School of Computer Science and Engineering Beihang University Beijing China School of Computer Science and Technology Harbin Institute of Technology Harbin China Geometry Robotics

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

We focus on the generalization ability of the 6-DoF grasp detection method in this paper. While learning-based grasp detection methods can predict grasp poses for unseen ob-jects using the grasp distribution learned from the training set, they often exhibit a significant performance drop when encountering objects with diverse shapes and struc-tures. To enhance the grasp detection methods' general-ization ability, we incorporate domain prior knowledge of robotic grasping, enabling better adaptation to objects with significant shape and structure differences. More specifi-cally, we employ the physical constraint regularization during the training phase to guide the model towards predicting grasps that comply with the physical rule on grasping. For the unstable grasp poses predicted on novel objects, we design a contact-score joint optimization using the pro-jection contact map to refine these poses in cluttered sce-narios. Extensive experiments conducted on the GraspNet-1 billion benchmark demonstrate a substantial performance gain on the novel object set and the real-world grasping experiments also demonstrate the effectiveness of our gen-eralizing 6-DoF grasp detection method. Code is available at https://***/mahaoxiang822/Generalizing-Grasp.

关键词： Training Computer vision Shape Grasping Benchmark testing Predictive models Performance gain

来源：评论

学校读者我要写书评

暂无评论

A Multi-stage Prediction Framework for Pest Identification

A Multi-stage Prediction Framework for Pest Identification

引用

IEEE International Conference on Cloud Computing and Intelligence Systems (CCIS)

作者： Yanan Chen Miao Chen Minghui Guo Fangfang Wang Jianji Wang National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University School of Software Engineering Xi’an Jiaotong University

With the development of computer vision technology and smart agriculture, deep learning techniques have been widely applied to crop pest identification tasks. However, existing studies do not consider the problem of large differences in pests across multiple growth stages, leading to unsatisfactory performance in pest identification in practical applications. This article proposes a simple framework for multi-stage prediction of pests, which can effectively predict the growth stage of pests and improve pest classification performance. The framework consists of a classification branch and a stage prediction branch. The stage prediction branch predicts the growth stage of pests based on feature similarity using K-Means, and guides the classification branch to classify images from different stages into different categories to avoid interfering with the performance of the classifier. In addition, to update the entire network parameters, we propose a multi-stage cross-entropy loss that optimizes feature extractors and classifiers by fusing image labels and stage prediction outputs. Experimental results show that the proposed multi-stage prediction framework for pest identification can accurately classify pest stages and improve pest classification accuracy. In addition, our work provides research ideas for pest stage prediction and identification, which is expected to help achieve more efficient pest control.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Review of Inference Time Prediction Approaches of DNN: Emphasis on Service robots with cloud-edge-device architecture

Review of Inference Time Prediction Approaches of DNN: Empha...

引用

IEEE International Conference on robotics and Biomimetics

作者： Tian Xiang Qiwei Meng Ji Zhang Beibei Zhang Wei Song Anhuan Xie Jason Gu Research Center for Intelligent Robotics Research Institute of Interdisciplinary Innovation Zhejiang Laboratory Hangzhou China Department of Mechanical and Automation Engineering T Stone Robotics Institute The Chinese University of Hong Kong HKSAR China Research Center for Intelligent Computing Software Research Institute of Intelligent Computing Zhejiang Laboratory Hangzhou China Electrical and Computer Engineering Dalhousie University Halifax Canada

In recent years, the global robot market has witnessed substantial growth, particularly in the domain of service robots. Despite their expanding presence, service robots encounter limitations when operating autonomously in unstructured environments, primarily due to their constrained computational capacities. As a solution, the fusion of cloud and edge computing resources becomes imperative to expedite task inference and enhance scenario perception capabilities. The integration of cloud-edge-device models holds significant promise in bolstering the operational efficiency of robots. This entails the dynamic partitioning of intricate robotic tasks, executed collaboratively across cloud, edge, and device resources. In this landscape, deep neural network (DNN) models play a pivotal role in facilitating a wide array of robotic tasks. The inference time for each layer of a DNN model in actual deployment, emerges as a critical determinant in the model’s partitioning strategy. It also serves as an important metric influencing the model’s suitability for a specific hardware platform. This article presents an overview of recent advancements in predicting inference and training time of DNN models, summarizes the related methods, and finally discusses the challenges in this field and the research that can be studied in the future.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards Generalizable Multi-Object Tracking

Towards Generalizable Multi-Object Tracking

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Zheng Qin Le Wang Sanping Zhou Panpan Fu Gang Hua Wei Tang National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University School of Software Engineering Xi'an Jiaotong University Wormpex AI Research University of Illinois at Chicago

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Multi-Object Tracking (MOT) encompasses various tracking scenarios, each characterized by unique traits. Ef-fective trackers should demonstrate a high degree of gen-eralizability across diverse scenarios. However, existing trackers struggle to accommodate all aspects or necessi-tate hypothesis and experimentation to customize the asso-ciation information (motion and/or appearance) for a given scenario, leading to narrowly tailored solutions with limited generalizability. In this paper, we investigate the factors that influence trackers' generalization to different scenar-ios and concretize them into a set of tracking scenario at-tributes to guide the design of more generalizable trackers. Furthermore, we propose a “point-wise to instance-wise relation” framework for MOT, i.e., GeneralTrack, which can generalize across diverse scenarios while eliminating the need to balance motion and appearance. Thanks to its supe-rior generalizability, our proposed GeneralTrack achieves state-of-the-art performance on multiple benchmarks and demonstrates the potential for domain generalization.

关键词： Computer vision Tracking Computational modeling Benchmark testing Pattern recognition

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：