检索结果-内蒙古大学图书馆

Key Technologies for Machine vision for Picking robots:Review and Benchmarking

Machine Intelligence Research 2025年第1期22卷 2-16页

作者： Xu Xiao Yiming Jiang Yaonan Wang College of Electrical and Information Engineering Hunan UniversityChangsha 410082China National Engineering Research Center for Robot Vision Perception and Control Technology Hunan UniversityChangsha 410082China

The increase in precision agriculture has promoted the development of picking robot technology,and the visual recognition system at its core is crucial for improving the level of agricultural *** paper reviews the progress of visual recognition tech-nology for picking robots,including image capture technology,target detection algorithms,spatial positioning strategies and scene *** article begins with a description of the basic structure and function of the vision system of the picking robot and em-phasizes the importance of achieving high-efficiency and high-accuracy recognition in the natural agricultural ***-sequently,various image processing techniques and vision algorithms,including color image analysis,three-dimensional depth percep-tion,and automatic object recognition technology that integrates machine learning and deep learning algorithms,were *** the same time,the paper also highlights the challenges of existing technologies in dynamic lighting,occlusion problems,fruit maturity di-versity,and real-time processing *** paper further discusses multisensor information fusion technology and discusses methods for combining visual recognition with a robot control system to improve the accuracy and working rate of *** the same time,this paper also introduces innovative research,such as the application of convolutional neural networks(CNNs)for accurate fruit detection and the development of event-based vision systems to improve the response speed of the *** the end of this paper,the future development of visual recognition technology for picking robots is predicted,and new research trends are proposed,including the refinement of algorithms,hardware innovation,and the adaptability of technology to different agricultural *** purpose of this paper is to provide a comprehensive analysis of visual recognition technology for researchers and practitioners in the field of agricul-tural rob

关键词： Picking robot visual system perception technology image processing machine learning deep learning.

来源：评论

学校读者我要写书评

暂无评论

An Efficient Generative Intelligent Multiobjective Grasping Model for Kitchen Waste Sorting

引用

IEEE Transactions on Instrumentation and Measurement 2025年 74卷

作者： Deng, Songyun Pei, Ruiyuan Zhou, Li Qin, Hai Sun, Wei Liang, Qiaokang Hunan University College of Electrical and Information Engineering Changsha410082 China Hunan University National Engineering Laboratory for Robot Vision Perception and Control College of Electrical and Information Engineering Changsha410082 China

The key challenge in automated kitchen waste sorting on conveyor belts is how robots execute grasping tasks. Current methods, dependent on object detection, struggle to adopt generative architectures due to data scarcity and algorithmic inefficiency. To solve these issues, this article proposes solutions in three aspects: dataset construction, annotation data processing, and generative model lightweighting. First, we built the KWG2024 dataset, which includes 3116 RGB-D images, 18231 standard annotations, and three new evaluation metrics. Second, we proposed two novel annotation processing methods to address the issue of excessive and incorrect grasps generated by generative networks in single-attempt grasp planning of multiobjects. Third, we constructed an efficient network with classification capabilities, AMI-LiteNet, by integrating the advantages of PP-LiteSeg and AMI-NanoNet. On the public Cornell dataset, AMI-LiteNet achieved a grasping accuracy of 98.3% and an efficiency of 118 frames per second (FPS). In extensive comparative experiments on KWG2024, our model reached a leading computational efficiency compared with recent state-of-the-art methods. It acquired a grasp planning generation accuracy of 87.96% while only requiring a computational effort of 2.79 GFLOPs. Finally, our model was deployed on an edge computing device and achieved a maximum grasping accuracy of 90.91% and a classification accuracy (CA) of 97.48% in our actual robotic system. To our knowledge, this is the first time that a generative grasp method has been applied independently to kitchen waste sorting tasks on a conveyor belt. © 1963-2012 IEEE.

关键词： Belt conveyors

来源：评论

学校读者我要写书评

暂无评论

RGB-Based Category-Level Object Pose Estimation via Depth Recovery and Adaptive Refinement

引用

IEEE robotics and Automation Letters 2025年第6期10卷 5377-5384页

作者： Yang, Hui Sun, Wei Liu, Jian Zheng, Jin Zeng, Zhiwen Mian, Ajmal Hunan University National Engineering Research Center for Robot Visual Perception and Control Technology College of Electrical and Information Engineering Changsha410082 China Hunan University State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body Changsha410082 China Central South University School of Architecture and Art Changsha410082 China University of Western Australia Department of Computer Science and Software Engineering CrawleyWA6009 Australia

Category-level pose estimation methods have received widespread attention as they can be generalized to intra-class unseen objects. Although RGB-D-based category-level methods have made significant progress, reliance on depth image limits practical application. RGB-based methods offer a more practical and cost-effective solution. However, current RGB-based methods struggle with object geometry perception, leading to inaccurate pose estimation. We propose depth recovery and adaptive refinement for category-level object pose estimation from a single RGB image. We leverage DINOv2 to reconstruct the coarse scene-level depth from the input RGB image and propose an adaptive refinement network based on an encoder-decoder architecture to dynamically improve the predicted coarse depth and reduce its gap from the ground truth. We introduce a 2D–3D consistency loss to ensure correspondence between the point cloud obtained from depth projection and the objects in the 2D image. This consistency supervision enables the model to maintain alignment between the depth image and the point cloud. Finally, we extract features from the refined point cloud and feed them into two confidence-aware rotation regression branches and a translation and size prediction residual branch for end-to-end training. Decoupling the rotation matrix provides a more direct representation, which facilitates parameter optimization and gradient propagation. Extensive experiments on the REAL275 and CAMERA25 datasets demonstrate the superior performance of our method. Real-world estimation and robotic grasping experiments demonstrate our model robustness to occlusion, clutter environments, and low-textured objects. Our code and robotic grasping video are available at DA-Pose. © 2016 IEEE.

关键词： Depth perception

来源：评论

学校读者我要写书评

暂无评论

DDH-Net:A Dual Dynamic Head Network for Transmission Line Inspection

引用

IEEE Transactions on Instrumentation and Measurement 2025年

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

Transmission lines are a critical component of an electrical grid, and ensuring their effective detection is of utmost importance. However, problems such as fine-grained identification, target occlusion, and background complexity in aerial transmission line images challenge existing transmission line detection methods. This paper presents a dual dynamic head network (DDH-Net) to address the aforementioned issues. This network incorporates a dual dynamic head (DDH) composed of a multifeature fusion module (MFFM) and deformable convolution. DDH leverages deformable convolution to enhance the network's focus on the target of interest. Subsequently, the MFFM enhances the feature representation capabilities for individual targets, leading to discriminative feature extraction and improving the network's accuracy in detecting similar targets. Furthermore, we introduce the wise area intersection over union (WAIoU) loss, which reduces the network's attention on detection boxes that contain only partial target content through the adaptive allocation of loss weights to anchor boxes to mitigate occlusion-induced interference. Additionally, we incorporate area as a constraint to further enhance the network's localization accuracy. Finally, extensive experiments were conducted on a power transmission line dataset. The results demonstrated the superiority of the proposed module over other state-of-the-art (SOTA) methods. © 1963-2012 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Yin, Yufeng Liu, Xiaoyan Zhang, Zichao Hunan University National Engineering Laboratory for Robot Visual Perception and Control Technology College of Electrical and Information Engineering Changsha410082 China Innovation Institute of Industrial Design and Machine Intelligence Quanzhou-Hunan University Quanzhou362006 China

Multi-view stereo aims to recover the 3D model of a scene from a set of images. However, low-textured areas in the scene have always been a challenge in 3D reconstruction. In this work, we propose a segmentation-guided multi-scale anchor deformation patch multi-view stereo. Specifically, we use the Segment Anything Model to distinguish different instances in the scene, and propose an anchor deformation strategy guided by segmentation to adaptively generate a multi-scale anchor patch, so that the depth can be refined from coarse to fine scales. To propagate a better hypothesis for low-textured areas where photometric consistency is unreliable, we propose a non-local adaptive propagation scheme by using the segmented mask as a propagation domain. In order to reduce the interference of illumination on reconstruction completeness, we propose an outlier depth cost refinement guided by reliable points that improves the performance of depth estimation in unevenly illuminated areas. As a result, our method achieves state-of-the-art performance among traditional methods and exhibits better generalization capabilities on the ETH3D, Tanks and Temples, and DTU datasets. © 1991-2012 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

An Improved Dual Neural Network Method Based on Levy Flight for Multi-robot Cooperative Area Coverage Search in 3D Unknown Environments

引用

IEEE Transactions on Cognitive and Developmental Systems 2025年

作者： Zhang, Fangfang Wang, Yongqi Wang, Wenhao Xin, Jianbin Peng, Jinzhu Wang, Yaonan Zhengzhou University School of Electrical and Information Engineering Zhengzhou450001 China State Key Laboratory of Intelligent Agricultural Power Equipment Luoyang471039 China National Engineering Laboratory of Robot Visual Perception and Control Technology School of Robotics Hunan University Changsha410082 China

The research on multi-robot collaborative search in unknown 3D environments, based on bio-inspired neural networks, holds significant value and ***, challenges arise in 3D environments, including excessive turning and vertical movement, as well as the potential for collisions between robots. In response, we propose an improved Glasius Bio-Inspired Neural Network(GBNN) that mitigates decision conflicts among robots and considers the impact of turning and vertical movement on robot decision-making. Furthermore, to address the issue of robots getting trapped in local deadlocks during the search process, we present a dual neural network algorithm based on Levy flights. In the method Dual Glasius Bio-Inspired Neural Network based on Levy Flight(LF-DUAL-GBNN) proposed in this paper, robots obtain random target points through Levy flights and are then guided by a dual neural network to navigate to the vicinity of the target points, thus breaking free from local deadlock states. Finally, we conducted simulation experiments to validate the algorithm's effectiveness. © 2016 IEEE.

关键词： Microrobots

来源：评论

学校读者我要写书评

暂无评论

EgoEvGesture: Gesture Recognition Based on Egocentric Event Camera

arXiv

引用

arXiv 2025年

作者： Wang, Luming Shi, Hao Yin, Xiaoting Yang, Kailun Wang, Kaiwei Bai, Jian State Key Laboratory of Extreme Photonics and Instrumentation Zhejiang University China School of Robotics Hunan University China National Engineering Research Center of Robot Visual Perception and Control Technology Hunan University China

Egocentric gesture recognition is a pivotal technology for enhancing natural human-computer interaction, yet traditional RGB-based solutions suffer from motion blur and illumination variations in dynamic scenarios. While event cameras show distinct advantages in handling high dynamic range with ultra-low power consumption, existing RGB-based architectures face inherent limitations in processing asynchronous event streams due to their synchronous frame-based nature. Moreover, from an egocentric perspective, event cameras record data that includes events generated by both head movements and hand gestures, thereby increasing the complexity of gesture recognition. To address this, we propose a novel network architecture specifically designed for event data processing, incorporating (1) a lightweight CNN with asymmetric depthwise convolutions to reduce parameters while preserving spatiotemporal features, (2) a plug-and-play state-space model as context block that decouples head movement noise from gesture dynamics, and (3) a parameter-free Bins-Temporal Shift Module (BSTM) that shifts features along bins and temporal dimensions to fuse sparse events efficiently. We further establish the EgoEvGesture dataset, the first large-scale dataset for egocentric gesture recognition using event cameras. Experimental results demonstrate that our method achieves 62.7% accuracy tested on unseen subjects with only 7M parameters, 3.1% higher than state-of-the-art approaches. Notable misclassifications in freestyle motions stem from high interpersonal variability and unseen test patterns differing from training data. Moreover, our approach achieved a remarkable accuracy of 97.0% on the DVS128 Gesture, demonstrating the effectiveness and generalization capability of our method on public datasets. The dataset and models are made available at https://***/3190105222/EgoEv_Gesture. Copyright © 2025, The Authors. All rights reserved.

关键词： Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

Learning to Learn Transferable Generative Attack for Person Re-Identification

引用

IEEE Transactions on Image Processing 2025年 PP卷 PP页

作者： Bian, Yuan Liu, Min Wang, Xueping Ma, Yunfeng Wang, Yaonan Hunan University National Engineering Research Center of Robot Visual Perception and Control Technology College of Electrical and Information Engineering Hunan Changsha China Hunan Normal University Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing College of Information Science and Engineering Hunan Changsha China

Deep learning-based person re-identification (reid) models are widely employed in surveillance systems and inevitably inherit the vulnerability of deep networks to adversarial attacks. Existing attacks merely consider cross-dataset and cross-model transferability, ignoring the cross-test capability to perturb models trained in different domains. To powerfully examine the robustness of real-world re-id models, the Meta Transferable Generative Attack (MTGA) method is proposed, which adopts meta-learning optimization to promote the generative attacker producing highly transferable adversarial examples by learning comprehensively simulated transfer-based crossmodel&dataset&test black-box meta attack tasks. Specifically, cross-model&dataset black-box attack tasks are first mimicked by selecting different re-id models and datasets for meta-train and meta-test attack processes. As different models may focus on different feature regions, the Perturbation Random Erasing module is further devised to prevent the attacker from learning to only corrupt model-specific features. To boost the attacker learning to possess cross-test transferability, the Normalization Mix strategy is introduced to imitate diverse feature embedding spaces by mixing multi-domain statistics of target models. Extensive experiments show the superiority of MTGA, especially in cross-model&dataset and cross-model&dataset&test attacks, our MTGA outperforms the SOTA methods by 20.0% and 11.3% on mean mAP drop rate, respectively. © 1992-2012 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Resource-Efficient Affordance Grounding with Complementary Depth and Semantic Prompts

arXiv

引用

arXiv 2025年

作者： Huang, Yizhou Yang, Fan Zhu, Guoliang Li, Gen Shi, Hao Zuo, Yukun Chen, Wenrui Li, Zhiyong Yang, Kailun School of Robotics and the National Engineering Research Center of Robot Visual Perception and Control Technology Hunan University China School of Informatics University of Edinburgh United Kingdom State Key Laboratory of Extreme Photonics and Instrumentation Zhejiang University China

Affordance refers to the functional properties that an agent perceives and utilizes from its environment, and is key perceptual information required for robots to perform actions. This information is rich and multimodal in nature. Existing multimodal affordance methods face limitations in extracting useful information, mainly due to simple structural designs, basic fusion methods, and large model parameters, making it difficult to meet the performance requirements for practical deployment. To address these issues, this paper proposes the BiT-Align image-depth-text affordance mapping framework. The framework includes a Bypass Prompt Module (BPM) and a Text Feature Guidance (TFG) attention selection mechanism. BPM integrates the auxiliary modality depth image directly as a prompt to the primary modality RGB image, embedding it into the primary modality encoder without introducing additional encoders. This reduces the model’s parameter count and effectively improves functional region localization accuracy. The TFG mechanism guides the selection and enhancement of attention heads in the image encoder using textual features, improving the understanding of affordance characteristics. Experimental results demonstrate that the proposed method achieves significant performance improvements on public AGD20K and HICO-IIF datasets. On the AGD20K dataset, compared with the current state-of-the-art method, we achieve a 6.0% improvement in the KLD metric, while reducing model parameters by 88.8%, demonstrating practical application values. The source code will be made publicly available at https://***/DAWDSE/BiT-Align. Copyright © 2025, The Authors. All rights reserved.

关键词： Image coding

来源：评论

学校读者我要写书评

暂无评论

Modality Unified Attack for Omni-Modality Person Re-Identification

引用

IEEE Transactions on Information Forensics and Security 2025年

作者： Bian, Yuan Liu, Min Yi, Yunqi Wang, Xueping Ma, Yunfeng Wang, Yaonan Hunan University National Engineering Research Center of Robot Visual Perception and Control Technology College of Electrical and Information Engineering Hunan Changsha China Hunan Normal University Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing College of Information Science and Engineering Hunan Changsha China

Deep learning based person re-identification (re-id) models have been widely employed in surveillance systems. Recent studies have demonstrated that black-box single-modality and cross-modality re-id models are vulnerable to adversarial examples (AEs), leaving the robustness of multi-modality re-id models unexplored. Due to the lack of knowledge about the specific type of model deployed in the target black-box surveillance system, we aim to generate modality unified AEs for omni-modality (single-, cross- and multi-modality) re-id models. Specifically, we propose a novel Modality Unified Attack method to train modality-specific adversarial generators to generate AEs that effectively attack different omni-modality models. A multi-modality model is adopted as the surrogate model, wherein the features of each modality are perturbed by metric disruption loss before fusion. To collapse the common features of omnimodality models, Cross Modality Simulated Disruption approach is introduced to mimic the cross-modality feature embeddings by intentionally feeding images to non-corresponding modality-specific subnetworks of the surrogate model. Moreover, Multi Modality Collaborative Disruption strategy is devised to facilitate the attacker to comprehensively corrupt the informative content of person images by leveraging a multi modality feature collaborative metric disruption loss. Extensive experiments show that our MUA method can effectively attack the omni-modality re-id models, achieving 55.9%, 24.4%, 49.0% and 62.7% mean mAP Drop Rate, respectively. © 2005-2012 IEEE.

关键词： Modality unified attack Multi Modality Collaborative Disruption Omni-Modality re-id

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：