检索结果-内蒙古大学图书馆

LDFCDet: Boosting 3D Object Detectors with Low-High level Feature Crosses Using Laplace Distribution

学校读者我要写书评

暂无评论

IEEE Transactions on Circuits and Systems for Video technology 2025年

作者： He, Zhenyu Mao, Jianxu Wang, Yaonan Yu, Junlong Tao, Ziming Yi, Junfei Zhang, Hui Wang, Shaoyuan Hunan University College of Electrical and Information Engineering Hunan Changsha410012 China Hunan University School of Robotics Changsha410082 China National Engineering Reseach Center for Robot Visual Perception and Control Technology Changsha410082 China

Highly accurate 3D object detection is critical for autonomous driving and robotic sensing system. However, some objects with few foreground points significantly affect the accuracy of 3D object detection. As the network depth increases, the low-level features of these objects are gradually lost, especially for the hard object. Due to this issue, current LiDAR-only based and multimodal methods often misclassify background as foreground. Therefore, how to leverage the low-level feature that contain information about these objects in the high layer of the network becomes the key to optimizing the issue. In this paper, we propose LDFCDet, a framework boosting 3D object detectors with low-high level feature crosses using Laplace distribution(LD). In our proposed method, we design a low-high level feature crosses module(LHFCM) to embed low-level feature into high-level feature in the deeper layer of the network, and use Laplace distribution to obtain a new low-high level feature that includes information about these objects with few foreground points. In addition, we propose a res-gated feature aggregation module(RGFAM) to fuse the mutli-scale features. Our approach is well-suited for both LiDAR-based and multimodal *** evaluate the LDFCDet on the widely used KITTI dataset, and our method outperforms almost current 3D object detection methods on the challenging KITTI test set. Moreover, we conducted comparative experiments on the ONCE dataset, and the results further demonstrate the effectiveness and superiority of our method. © 1991-2012 IEEE.

关键词： Object detection

Beyond the Field-of-View: Enhancing Scene Visibility and perception with Clip-Recurrent Transformer

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Shi, Hao Jiang, Qi Yang, Kailun Yin, Xiaoting Wang, Ze Wang, Kaiwei The State Key Laboratory of Extreme Photonics and Instrumentation the National Engineering Research Center of Optical Instrumentation Zhejiang University Hangzhou310027 China The School of Robotics The National Engineering Research Center of Robot Visual Perception and Control Technology Hunan University Changsha410082 China Shanghai SUPREMIND Technology Company Ltd Shanghai201210 China

Vision sensors are widely applied in vehicles, robots, and roadside infrastructure. However, due to limitations in hardware cost and system size, camera Field-of-View (FoV) is often restricted and may not provide sufficient coverage. Nevertheless, from a spatiotemporal perspective, it is possible to obtain information beyond the camera’s physical FoV from past video streams. In this paper, we propose the concept of online video inpainting for autonomous vehicles to expand the field of view, thereby enhancing scene visibility, perception, and system safety. To achieve this, we introduce the FlowLens architecture, which explicitly employs optical flow and implicitly incorporates a novel clip-recurrent transformer for feature propagation. FlowLens offers two key features: 1) FlowLens includes a newly designed Clip-Recurrent Hub with 3D-Decoupled Cross Attention (DDCA) to progressively process global information accumulated over time. 2) It integrates a multi-branch Mix Fusion Feed Forward Network (MixF3N) to enhance the precise spatial flow of local features. To facilitate training and evaluation, we derive the KITTI360 dataset with various FoV mask, which covers both outer- and inner FoV expansion scenarios. We also conduct both quantitative assessments and qualitative comparisons of beyond-FoV semantics and beyond-FoV object detection across different models. We illustrate that employing FlowLens to reconstruct unseen scenes even enhances perception within the field of view by providing reliable semantic context. Extensive experiments and user studies involving offline and online video inpainting, as well as beyond-FoV perception tasks, demonstrate that FlowLens achieves state-of-the-art performance. The source code and dataset are made publicly available at https://github. com/MasterHow/FlowLens. Copyright © 2022, The Authors. All rights reserved.

关键词： Optical flows

Offboard Occupancy Refinement with Hybrid Propagation for Autonomous Driving

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Shi, Hao Wang, Song Zhang, Jiaming Yin, Xiaoting Wang, Zhongdao Wang, Guangming Zhu, Jianke Yang, Kailun Wang, Kaiwei The State Key Laboratory of Extreme Photonics and Instrumentation The National Engineering Research Center of Optical Instrumentation Zhejiang University Hangzhou310027 China The School of Robotics The National Engineering Research Center of Robot Visual Perception and Control Technology Hunan University Changsha410082 China The College of Computer Science and Technology Zhejiang University Hangzhou310027 China The Institute for Anthropomatics and Robotics Karlsruhe Institute of Technology Karlsruhe76131 Germany Huawei Noah’s Ark Lab. Canada The Department of Engineering University of Cambridge CambridgeCB2 1PZ United Kingdom

Vision-based occupancy prediction, also known as 3D Semantic Scene Completion (SSC), presents a significant challenge in computer vision. Previous methods, confined to onboard processing, struggle with simultaneous geometric and semantic estimation, continuity across varying viewpoints, and single-view occlusion. Our paper introduces OccFiner, a novel offboard framework designed to enhance the accuracy of vision-based occupancy predictions. OccFiner operates in two hybrid phases: 1) a multi-to-multi local propagation network that implicitly aligns and processes multiple local frames for correcting onboard model errors and consistently enhancing occupancy accuracy across all distances. 2) the region-centric global propagation, focuses on refining labels using explicit multi-view geometry and integrating sensor bias, especially to increase the accuracy of distant occupied voxels. Extensive experiments demonstrate that OccFiner improves both geometric and semantic accuracy across various types of coarse occupancy, setting a new state-of-the-art performance on the SemanticKITTI dataset. Notably, OccFiner elevates vision-based SSC models to a level even surpassing that of LiDAR-based onboard SSC models. Furthermore, OccFiner is the first to achieve automatic annotation of SSC in a purely vision-based approach. Quantitative experiments prove that OccFiner successfully facilitates occupancy data loop-closure in autonomous driving. Additionally, we quantitatively and qualitatively validate the superiority of the offboard approach on city-level SSC static maps. The source code will be made publicly available at https://***/MasterHow/OccFiner. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantic Segmentation

Steady Tracker: Tracking a Target Stably Using a Quadrotor

学校读者我要写书评

暂无评论

Steady Tracker: Tracking a Target Stably Using a Quadrotor

IEEE International Conference on robotics and Biomimetics

作者： Hongwen Li Hang Zhong Yongsheng Lv Jianjun Sha Yu Long Yaonan Wang Harbin Engineering University Harbin Qingdao Innovation and Development Center of Harbin Engineering University Qingdao China School of Robotics National Engineering Research Center for Robot Visual Perception and Control Hunan University College of Electrical and Information Engineering Hunan University Changsha China

ISBN: (纸本)9781665481106

Maneuvering target tracking of Unmanned Aerial Vehicle(UAV) in cluttered environments is a challenging issue owing to the unknown motion intention of the target and the complex moving environments. As the complexity of the environment increases, stable and secure target tracking is increasingly difficult to guarantee. To address the issue, this paper proposes a stable quadrotor tracking solution. The proposed solution contains two parts: target motion prediction and tracking path searching. The target motion prediction method predicts the future target motion based on the obtained target observations while considering observation noise and prediction errors. The tracking path searching method utilizes a sampling-based search method, using the homotopy of paths to ensure that the tracking path and the target position are in the same space. Finally, simulations, real-world experiments and statistical analysis verify the correctness and effectiveness of the proposed approach.

关键词： Target tracking Statistical analysis Prediction methods Search problems Turning Prediction algorithms Convex functions

Design, analysis, and manufacturing of a glass-plastic hybrid minimalist aspheric panoramic annular lens

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Gao, Shaohua Jiang, Qi Liao, Yiqi Qiu, Yi Ying, Wanglei Yang, Kailun Wang, Kaiwei Zhang, Benhao Bai, Jian State Key Laboratory of Extreme Photonics and Instrumentation College of Optical Science and Engineering Zhejiang University Hangzhou310027 China Ningbo Lian Technology Co. Ltd Ningbo Lian Ningbo315500 China National Engineering Research Center of Robot Visual Perception and Control Technology Hunan University Changsha410082 China Intelligent Optics & Photonics Research Center Jiaxing Research Institute Zhejiang University Jiaxing314031 China Central Research Institue of Sunny Optical Technology Sunny Optical Technology Hangzhou311215 China

We propose a high-performance glass-plastic hybrid minimalist aspheric panoramic annular lens (ASPAL) to solve several major limitations of the traditional panoramic annular lens (PAL), such as large size, high weight, and complex system. The field of view (FoV) of the ASPAL is 360◦×(35◦∼110◦) and the imaging quality is close to the diffraction limit. This large FoV ASPAL is composed of only 4 lenses. Moreover, we establish a physical structure model of PAL using the ray tracing method and study the influence of its physical parameters on compactness ratio. In addition, for the evaluation of local tolerances of annular surfaces, we propose a tolerance analysis method suitable for ASPAL. This analytical method can effectively analyze surface irregularities on annular surfaces and provide clear guidance on manufacturing tolerances for ASPAL. Benefiting from high-precision glass molding and injection molding aspheric lens manufacturing techniques, we finally manufactured 20 ASPALs in small batches. The weight of an ASPAL prototype is only 8.5 g. Our framework provides promising insights for the application of panoramic systems in space and weight-constrained environmental sensing scenarios such as intelligent security, micro-UAVs, and micro-robots. Copyright © 2024, The Authors. All rights reserved.

关键词： Optical design

Towards Source-free Domain Adaptive Semantic Segmentation via Importance-aware and Prototype-contrast Learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Cao, Yihong Zhang, Hui Lu, Xiao Xiao, Zheng Yang, Kailun Wang, Yaonan College of Computer Science and Electronic Engineering Hunan University Changsha410082 China National Engineering Research Center of Robot Vision Perception and Control Technology School of Robotics Hunan University Changsha410082 China College of Engineering and Design Hunan Normal University Changsha410082 China

Domain adaptive semantic segmentation enables robust pixel-wise understanding in real-world driving scenes. Source-free domain adaptation, as a more practical technique, addresses the concerns of data privacy and storage limitations in typical unsupervised domain adaptation methods, making it especially relevant in the context of intelligent vehicles. It utilizes a well-trained source model and unlabeled target data to achieve adaptation in the target domain. However, in the absence of source data and target labels, current solutions cannot sufficiently reduce the impact of domain shift and fully leverage the information from the target data. In this paper, we propose an end-to-end source-free domain adaptation semantic segmentation method via Importance-Aware and Prototype-Contrast (IAPC) learning. The proposed IAPC framework effectively extracts domain-invariant knowledge from the well-trained source model and learns domain-specific knowledge from the unlabeled target domain. Specifically, considering the problem of domain shift in the prediction of the target domain by the source model, we put forward an importance-aware mechanism for the biased target prediction probability distribution to extract domain-invariant knowledge from the source model. We further introduce a prototype-contrast strategy, which includes a prototype-symmetric cross-entropy loss and a prototype-enhanced cross-entropy loss, to learn target intra-domain knowledge without relying on labels. A comprehensive variety of experiments on two domain adaptive semantic segmentation benchmarks demonstrates that the proposed end-to-end IAPC solution outperforms existing state-of-the-art methods. The source code is publicly available at https://***/yihong-97/Source-free-IAPC. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

Quantum machine learning for multiclass classification beyond kernel methods

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ding, Chao Wang, Shi Wang, Yaonan Gao, Weibo College of Electrical and Information Engineering Hunan University Changsha410082 China Division of Physics and Applied Physics School of Physical and Mathematical Sciences Nanyang Technological University Singapore637371 Singapore National Engineering Research Center of Robot Visual Perception and Control Technology Hunan University Changsha410082 China Centre for Quantum Technologies National University of Singapore Singapore117543 Singapore The Photonics Institute Centre for Disruptive Photonic Technologies Nanyang Technological University Singapore637371 Singapore

Quantum machine learning is considered one of the current research fields with great potential. In recent years, Havlíček et al. [Nature 567, 209-212 (2019)] have proposed a quantum machine learning algorithm with quantum-enhanced feature spaces, which effectively addressed a binary classification problem on a superconducting processor and offered a potential pathway to achieving quantum advantage. However, a straightforward binary classification algorithm falls short in solving multiclass classification problems. In this paper, we propose a quantum algorithm that rigorously demonstrates that quantum kernel methods enhance the efficiency of multiclass classification in real-world applications, providing quantum advantage. To demonstrate quantum advantage, we design six distinct quantum kernels within the quantum algorithm to map input data into quantum state spaces and estimate the corresponding quantum kernel matrices. The results from quantum simulations reveal that the quantum algorithm outperforms its classical counterpart in handling six real-world multiclass classification problems. Furthermore, we leverage a variety of performance metrics to comprehensively evaluate the classification and generalization performance of the quantum algorithm. The results demonstrate that the quantum algorithm achieves superior classification and better generalization performance relative to classical counterparts. Copyright © 2024, The Authors. All rights reserved.

关键词： Quantum efficiency

DANet: Density Adaptive Convolutional Network with Interactive Attention for 3D Point Clouds

学校读者我要写书评

暂无评论

arXiv 2023年

作者： He, Yong Yu, Hongshan Yang, Zhengeng Sun, Wei Feng, Mingtao Mian, Ajmal The National Engineering Laboratory for Robot Visual Perception and Control Technology College of Electrical and Information Engineering Hunan University Lushan South Rd. Yuelu Dist. Changsha410082 China The School of Computer Science and Technology Xidian University Xi’an710071 China The Department of Computer Science The University of Western Australia PerthWA6009 Australia

Local features and contextual dependencies are crucial for 3D point cloud analysis. Many works have been devoted to designing better local convolutional kernels that exploit the contextual dependencies. However, current point convolutions lack robustness to varying point cloud density. Moreover, contextual modeling is dominated by non-local or self-attention models which are computationally expensive. To solve these problems, we propose density adaptive convolution, coined DAConv. The key idea is to adaptively learn the convolutional weights from geometric connections obtained from the point density and position. To extract precise context dependencies with fewer computations, we propose an interactive attention module (IAM) that embeds spatial information into channel attention along different spatial directions. DAConv and IAM are integrated in a hierarchical network architecture to achieve local density and contextual direction-aware learning for point cloud analysis. Experiments show that DAConv is significantly more robust to point density compared to existing methods and extensive comparisons on challenging 3D point cloud datasets show that our network achieves state-of-the-art classification results of 93.6% on ModelNet40, competitive semantic segmentation results of 68.71% mIoU on S3DIS and part segmentation results of 86.7% mIoU on ShapeNet. Copyright © 2023, The Authors. All rights reserved.

关键词： Convolution

Binocular Vision System for Measuring the Height of control Rod Drive Rod in Nuclear Reactor

学校读者我要写书评

暂无评论

Binocular Vision System for Measuring the Height of Control ...

Chinese control Conference (CCC)

作者： Xianen Zhou Yingjian Wen Qing Zhu Yaonan Wang Feixiang Sun Shaonan Chen National Engineering Research Center for Robot Vision Perception and Control Technology Hunan University Jiangxi Communication Terminal Industry Technology Research Institute Co. Ltd. University of Electronic Science and Technology of China China Nuclear Power Technology Research Institute Co. Ltd.

Nuclear energy is widely recognized as an important source to meet the increasing energy demand in the future. However, since the occurrence of the Fukushima accident, its potential safety hazards have been strongly concerned by the public, and has become one of the most significant problems to be solved at this stage. In this paper, a vision inspection system with support detection scheme based on RGB-D fusion is proposed to achieve accurate detection of the control rod position for the potential danger in the decoupling process of the control rod drive mechanism. In order to separate the depth region containing the relevant information of the driving rod head, the ellipse region of the top ring of the driving rod is detected from the color image by the method based on line segment extraction and region of interest detection. Due to the smoothness and reflection of the surface of the control rod, part of the depth of the head of the control rod is lost. In order to predict the reference distance between the top value of the control rod and the camera, a center point filling method based on multi-direction linear regression in gradient stage is designed. In order to evaluate the effectiveness of the proposed method, a series of experiments are carried out on the head location and depth calculation of the drive rod. The results show that the vision inspection system in this paper can achieve high-precision positioning of the control rod.

关键词：