检索结果-内蒙古大学图书馆

Risk Identification Method for Smuggled Frozen Meat in Urban Public Safety Awareness and Early Warning

学校读者我要写书评

暂无评论

Risk Identification Method for Smuggled Frozen Meat in Urban...

2023 International Conference on Intelligent Communication and Networking, ICN 2023

作者： Li, Xueru Zhang, Yan Liu, Lingjie Tian, Ye Zhang, Yue Harbin Engineering University College of Computer Science and Technology Harbin China China Industrial Control Systems Cyber Emergency Response Team Beijing China Environment and Food and Drug Crime Investigation Detachment of Hangzhou Public Security Bureau Hangzhou China Xidian University Hangzhou Institute of Technology Hangzhou China Key Laboratory of Peace-Building Big Data of Zhejiang Province Zhejiang China

ISBN: (纸本)9798350357677

With the continuous growth in demand for meat and frozen products in the cold chain market, illegally smuggled frozen goods have quickly entered the market due to their low prices, leading to a series of food safety issues. This article proposes a method for identifying the risks of smuggled frozen meat for urban public safety awareness using the YOLOv7 model. The YOLOv7 model is used to detect data captured at various traffic checkpoints, obtaining spatiotemporal information of frozen goods vehicles. This information is then combined with map data to generate vehicle trajectory information. The trajectory similarity between the frozen vehicle trajectories and the specialized database of frozen transportation routes is analyzed using the EDwP distance algorithm. The EDwP algorithm employs a threshold-free approach, dynamically interpolating using the concept of projection, and automatically adapting to non-uniform sampling rates to address the issue of inconsistent trajectory data sampling rates. The experimental results of the YOLOv7-EDwP algorithm were verified by verifying the alerts generated in the recent period through on-site verification by a third-party inspection agency, with a recognition accuracy of 90.77%. This holds significant significance in the detection and warning of smuggled frozen meat. © 2023 IEEE.

关键词： Transportation routes

NF-Atlas: Multi-Volume Neural Feature Fields for Large Scale LiDAR Mapping

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Yu, Xuan Liu, Yili Mao, Sitong Zhou, Shunbo Xiong, Rong Liao, Yiyi Wang, Yue The State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control Zhejiang University Hangzhou China College of Information Science and Electronic Engineering Zhejiang University Hangzhou China Huawei Cloud Computing Technologies Co. Ltd. Shenzhen China

LiDAR Mapping has been a long-standing problem in robotics. Recent progress in neural implicit representation has brought new opportunities to robotic mapping. In this paper, we propose the multi-volume neural feature fields, called NF-Atlas, which bridge the neural feature volumes with pose graph optimization. By regarding the neural feature volume as pose graph nodes and the relative pose between volumes as pose graph edges, the entire neural feature field becomes both locally rigid and globally elastic. Locally, the neural feature volume employs a sparse feature Octree and a small MLP to encode the signed distance function (SDF) of the submap with an option of semantics. Learning the map using this structure allows for end-to-end solving of maximum a posteriori (MAP) based probabilistic mapping. Globally, the map is built volume by volume independently, avoiding catastrophic forgetting when mapping incrementally. Furthermore, when a loop closure occurs, with the elastic pose graph based representation, only updating the origin of neural volumes is required without remapping. Finally, these functionalities of NF-Atlas are validated. Thanks to the sparsity and the optimization based formulation, NF-Atlas shows competitive performance in terms of accuracy, efficiency and memory usage on both simulation and real-world datasets. The project page is: https://***/NFAtlas/ Copyright © 2023, The Authors. All rights reserved.

关键词： Mapping

ImmFusion: Robust mmWave-RGB Fusion for 3D Human Body Reconstruction in All Weather Conditions

学校读者我要写书评

暂无评论

ImmFusion: Robust mmWave-RGB Fusion for 3D Human Body Recons...

IEEE International Conference on Robotics and Automation (ICRA)

作者： Anjun Chen Xiangyu Wang Kun Shi Shaohao Zhu Bin Fang Yingfeng Chen Jiming Chen Yuchi Huo Qi Ye State Key Laboratory of Industrial Control Technology Zhejiang University Hangzhou China Tsinghua University Beijing China Fuxi AI Lab NetEase Hangzhou China State Key Lab of CAD&CG Zhejiang Lab Zhejiang University Hangzhou China State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Zhejiang University Key Laboratory of Collaborative Sensing and Autonomous Unmanned Systems of Zhejiang Province

3D human reconstruction from RGB images achieves decent results in good weather conditions but degrades dramatically in rough weather. Complementary, mmWave radars have been employed to reconstruct 3D human joints and meshes in rough weather. However, combining RGB and mmWave signals for robust all-weather 3D human reconstruction is still an open challenge, given the sparse nature of mmWave and the vulnerability of RGB images. In this paper, we present ImmFusion, the first mmWave-RGB fusion solution to reconstruct 3D human bodies in all weather conditions robustly. Specifically, our ImmFusion consists of image and point backbones for token feature extraction and a Transformer module for token fusion. The image and point backbones refine global and local features from original data, and the Fusion Transformer Module aims for effective information fusion of two modalities by dynamically selecting informative tokens. Extensive experiments on a large-scale dataset, mmBody, captured in various environments demonstrate that ImmFusion can efficiently utilize the information of two modalities to achieve a robust 3D human body reconstruction in all weather conditions. In addition, our method's accuracy is significantly superior to that of state-of-the-art Transformer-based LiDAR-camera fusion methods.

关键词：

UGNA-VPR: A Novel Training Paradigm for Visual Place Recognition Based on Uncertainty-Guided NeRF Augmentation

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Shen, Yehui Zhang, Lei Li, Qingqiu Zhao, Xiongwei Wang, Yue Lu, Huimin Chen, Xieyuanli College of Intelligence Science and Technology National University of Defense Technology China Faculty of Robot Science and Engineering Northeastern University China School of Electronic and Information Engineering Harbin Institute of Technology Shenzhen China State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control Zhejiang University China SIASUN Robot& Automation Co. Ltd China School of Computer Science Fudan University China

Visual place recognition (VPR) is crucial for robots to identify previously visited locations, playing an important role in autonomous navigation in both indoor and outdoor environments. However, most existing VPR datasets are limited to single-viewpoint scenarios, leading to reduced recognition accuracy, particularly in multi-directional driving or feature-sparse scenes. Moreover, obtaining additional data to mitigate these limitations is often expensive. This paper introduces a novel training paradigm to improve the performance of existing VPR networks by enhancing multi-view diversity within current datasets through uncertainty estimation and NeRF-based data augmentation. Specifically, we initially train NeRF using the existing VPR dataset. Then, our devised self-supervised uncertainty estimation network identifies places with high uncertainty. The poses of these uncertain places are input into NeRF to generate new synthetic observations for further training of VPR networks. Additionally, we propose an improved storage method for efficient organization of augmented and original training data. We conducted extensive experiments on three datasets and tested three different VPR backbone networks. The results demonstrate that our proposed training paradigm significantly improves VPR performance by fully utilizing existing data, outperforming other training approaches. We further validated the effectiveness of our approach on self-recorded indoor and outdoor datasets, consistently demonstrating superior results. Our dataset and code have been released at https://***/nubot-nudt/UGNA-VPR. Copyright © 2025, The Authors. All rights reserved.

关键词：

Ordered mesoporous carbon as an efficient heterogeneous catalyst to activate peroxydisulfate for degradation of sulfadiazine

学校读者我要写书评

暂无评论

Chinese Chemical Letters 2022年第5期33卷 2747-2752页

作者： Zhi-Ling Li Di Cao Hao Cheng Fan Chen Jun Nan Bin Liang Kai Sun Cong Huang Ai-Jie Wang State Key Laboratory of Urban Water Resource and Environment School of EnvironmentHarbin Institute of TechnologyHarbin 150090China School of Civil&Environmental Engineering Harbin Institute of Technology(Shenzhen)Shenzhen 518055China School of Ecology and Environment Northwestern Polytechnical UniversityXi’an 710129China Key Lab of Structures Dynamic Behavior and Control of China Ministry of Education School of Civil EngineeringHarbin Institute of TechnologyHarbin 150090China National Technology Innovation Center of Synthetic Biology Tianjin Institute of Industrial BiotechnologyChinese Academy of SciencesTianjin 300308China

Catalytic potential of carbon nanomaterials in peroxydisulfate(PDS)advanced oxidation systems for degradation of antibiotics remains poorly *** study revealed ordered mesoporous carbon(type CMK)acted as a superior catalyst for heterogeneous degradation of sulfadiazine(SDZ)in PDS sys-tem,with a first-order reaction kinetic constant(k)and total organic carbon(TOC)mineralization efficiency of 0.06 min^(–1) and 59.67%±3.4%within 60min,*** catalyzed PDS system exhibited high degradation efficiencies of five other sulfonamides and three other types of antibiotics,verifying the broad-degradation capacity of *** neutral pH conditions,the optimal catalytic parameters were an initial SDZ concentration of 44.0mg/L,CMK dosage of 0.07g/L,and PDS dosage of 5.44mmol/L,respectively.X-ray photoelectron spectroscopy and Raman spectrum analysis confirmed that the defect structure at edge of CMK and oxygen-containing functional groups on surface of CMK were major active sites,contributing to the high catalytic *** radical quenching analysis revealed that both SO_(4)•−and•OH were generated and participated in catalytic *** addition,direct electron transfer by CMK to activate PDS also occurred,further promoting catalytic *** of SDZ molecule was optimized using density functional theory,and the possible reaction sites in SDZ molecule were calculated using Fukui *** ultra-high-performance liquid chromatography(UPLC)–mass spectrometry(MS)/MS analysis,three potential degradation pathways were proposed,including the direct removal of SO_(2)molecules,the 14S-17N fracture,and the 19C-20N and 19C-27N cleavage of the SDZ *** study demonstrated that ordered mesoporous carbon could work as a feasible catalytic material for PDS advanced oxidation during removal of antibiotics from wastewater.

关键词： Ordered mesoporous carbon CMK Sulfadiazine Peroxydisulfate Degradation pathway Density functional theory Physicochemical properties

Efficient Object Manipulation to an Arbitrary Goal Pose: Learning-based Anytime Prioritized Planning

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Xu, Kechun Yu, Hongxiang Huang, Renlang Guo, Dashun Wang, Yue Xiong, Rong The State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control Zhejiang University Hangzhou China

We focus on the task of object manipulation to an arbitrary goal pose, in which a robot is supposed to pick an assigned object to place at the goal position with a specific orientation. However, limited by the execution space of the manipulator with gripper, one-step picking, moving and releasing might be failed, where a reorientation object pose is required as a transition. In this paper, we propose a learningdriven anytime prioritized search-based solver to find a feasible solution with low path cost in a short time. In our work, the problem is formulated as a hierarchical learning problem, with the high level finding a reorientation object pose, and the low level planning paths between adjacent grasps. We learn an offline-training path cost estimator to predict approximate path planning costs, which serve as pseudo rewards to allow for pre-training the high-level planner without interacting with the simulator. To deal with the problem of distribution mismatch of the cost net and the actual execution cost space, a refined training stage is conducted with simulation interaction. A series of experiments carried out in simulation and real world indicate that our system can achieve better performances in the object manipulation task with less time and less cost. Copyright © 2021, The Authors. All rights reserved.

关键词： Cost estimating

A new flexible multi-AGVs scheduling model with pre-waiting time in an intelligent manufacturing system

学校读者我要写书评

暂无评论

A new flexible multi-AGVs scheduling model with pre-waiting ...

IEEE International Conference on Networking, Sensing and control

作者： Haoyi Niu Zichao Xing Xingkai Wang Weimin Wu Tao Zhang State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control Zhejiang University Hangzhou China

ISBN: (纸本)9781665440493

This paper studies a flexible flow-shop scheduling problem with limited resources (FFSP-LR) which is based on an actual air-conditioning production line in an intelligent manufacturing system. It extends the classical flexible flow-shop scheduling problem by considering practical constraints of the number of the AGVs (automated guided vehicles) on the transportation resources. The problem aims to determine the optimal scheduling results that minimizes the idle waiting time and pick-up waiting time of the workstations. To solve this problem, a pre-waiting scheduling model (PWSM) is proposed by taking into account the advance waiting time of AGVs. The experimental results show that the proposed PWSM is able to reduce idle waiting time and pick-up waiting time up to 425.01 and 414.25 comparing to traditional FCFS (First Come First Serve) strategy respectively. Correspondingly, these two types of time could be saved up to 87.01% and 98.57%. Finally, the overall efficiency of the intelligent manufacturing system is improved since the PWSM is able to effectively reduce the idle waiting time and pick-up waiting time of the workstations under the condition of limited transportation resources.

关键词： Job shop scheduling Transportation Optimal scheduling Production Workstations Numerical models Sensors

A Novel Searching Method of Fringe Blocks for AGV Deadlock Avoidance

学校读者我要写书评

暂无评论

A Novel Searching Method of Fringe Blocks for AGV Deadlock A...

IEEE International Conference on Networking, Sensing and control

作者： Xinyu Chen Tingqi Zhang Weimin Wu Ruifen Hu State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control Zhejiang University Hangzhou China

ISBN: (纸本)9781665440493

With the increasing development of automated logistics systems, automated guided vehicles (AGVs) have been gradually deployed in various logistics systems. AGVs are mainly used to transport materials and products, which promote the efficiency greatly and provide profound flexibility and safety. The strategy to prevent AGVs from forming deadlocks is one of the fundamental and vital issues in applications. In this paper, a common type of deadlock that usually occurs in warehouses and a typical attribute of map called fringe blocks are studied thoroughly. To solve the deadlock, it’s crucial to identify fringe blocks. We first use traditional depth first search algorithm (DFS) to find out all the fringe blocks in the map. Then, confronted with the huge time complexity, we combine the DFS procedure with a high-efficiency trimming method. Finally, we run a simulation and make a comparison of both methods. The simulation results have shown that the proposed strategy will reduce computational time significantly without making false judgements.

关键词： Remotely guided vehicles Simulation Computational modeling Conferences System recovery Search problems Sensors

Learn to differ: Sim2Real small defection segmentation network

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Chen, Zexi Huang, Zheyuan Wang, Yunkai Xu, Xuecheng Wang, Yue Xiong, Rong The State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and Control Zhejiang University Zhejiang China

Recent studies on deep-learning-based small defection segmentation approaches are trained in specific settings and tend to be limited by fixed context. Throughout the training, the network inevitably learns the representation of the background of the training data before figuring out the defection. They underperform in the inference stage once the context changed and can only be solved by training in every new settings. This eventually leads to the limitation in practical robotic applications where contexts keep varying. To cope with this, instead of training a network context by context and hoping it to generalize, why not stop misleading it with any limited context and start training it with pure simulation? In this paper, we propose the network SSDS that learns a way of distinguishing small defections between two images regardless of the context, so that the network can be trained once for all. A small defection detection layer utilizing the pose sensitivity of phase correlation between images is introduced and is followed by an outlier masking layer. The network is trained on randomly generated simulated data with simple shapes and is generalized across the real world. Finally, SSDS is validated on real-world collected data and demonstrates the ability that even when trained in cheap simulation, SSDS can still find small defections in the real world showing the effectiveness and its potential for practical applications. © 2021, CC BY.

关键词： Deep learning