检索结果-内蒙古大学图书馆

Size-invariance matters: rethinking metrics and losses for imbalanced multi-object salient object detection 24

学校读者我要写书评

暂无评论

Size-invariance matters: rethinking metrics and losses for i...

Proceedings of the 41st International Conference on machine Learning

作者： Feiran Li Qianqian Xu Shilong Bao Zhiyong Yang Runmin Cong Xiaochun Cao Qingming Huang Institute of Information Engineering Chinese Academy of Sciences Beijing China and School of Cyber Security University of Chinese Academy of Sciences Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Institute of Information Science Beijing Jiaotong University Beijing China and School of Control Science and Engineering Shandong University Jinan China and Key Laboratory of Machine Intelligence and System Control Ministry of Education Jinan China School of Cyber Science and Tech. Shenzhen Campus Sun Yat-sen University School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China and Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China and Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China

This paper explores the size-invariance of evaluation metrics in Salient Object Detection (SOD), especially when multiple targets of diverse sizes co-exist in the same image. We observe that current metrics are size-sensitive, where larger objects are focused, and smaller ones tend to be ignored. We argue that the evaluation should be size-invariant because bias based on size is unjustified without additional semantic information. In pursuit of this, we propose a generic approach that evaluates each salient object separately and then combines the results, effectively alleviating the imbalance. We further develop an optimization framework tailored to this goal, achieving considerable improvements in detecting objects of different sizes. Theoretically, we provide evidence supporting the validity of our new metrics and present the generalization analysis of SOD. Extensive experiments demonstrate the effectiveness of our method. The code is available at https://***/Ferry-Li/SI-SOD.

关键词：

A moving target detection and localization strategy based on optical flow and pin-hole imaging methods using monocular vision

学校读者我要写书评

暂无评论

A moving target detection and localization strategy based on...

2021 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2021

作者： Wang, Shun Guo, Qingqiang Xu, Sheng Su, Dan School of Control Science and Engineering Shandong University Shandong Jinan250061 China Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institute of Advanced Technology Chinese Academy of Sciences CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institute of Advanced Technology Shenzhen518055 China Shandong Institute of Advanced Technology Chinese Academy of Sciences Shandong Jinan250102 China Orbbec Inc. Shenzhen518057 China

ISBN: (纸本)9781665436786

This paper proposes a new strategy for moving target detection and localization based on monocular vision. Firstly, to detect a moving target with large displacement and high speed accurately, two consecutive video images captured by a monocular camera are preprocessed using the enhancement and denoising methods. Then, the optical flow representing motion information is calculated iteratively by the modified Lucas-Kanade optical flow method. Secondly, a new interest region extraction method is developed to overcome the negative impacts caused by the noises in the background. Specifically, this proposed method combines a two-level image segmentation strategy from coarse to fine, including median filtering, two-direction dynamic threshold segmentation, the Otsu method, and morphological processing. Thirdly, a low computational cost target localization algorithm is proposed based on pin-hole imaging theory. Besides, it only uses two-dimensional image and camera parameters to obtain the moving target's position in the three-dimensional space. Finally, experimental results show that the proposed strategy can effectively eliminate noise interferences and realize moving target detection, extraction, and localization. © 2021 IEEE.

关键词： Image segmentation

Enabling Eco-Approach Where Signal Timing is Unknown

学校读者我要写书评

暂无评论

Enabling Eco-Approach Where Signal Timing is Unknown

International Conference on Intelligent Transportation

作者： Shuoyuan Li Guan Wang Xiao Xiao Zhenghao Xu Jia Hu Haoran Wang Key Laboratory of Road and Traffic Engineering of the Ministry of Education Tongji University Shanghai China Shanghai motor vehicle inspection technology research center Shanghai China Air system Dept Intelligent Driving Business Group Baidu Control Department of Intelligence Driving Center Shanghai Utopilot Technology Shanghai China

This research proposed an optimal control based eco-approach controller with the consideration of the uncertainty of the actuated traffic signal timing. Simulation demonstrates that the proposed controller could reduce 4.55% fuel-consumptions, reduce 8.74 % travel time and predict the actuated signal switching time with only 2.3 seconds of average prediction error.

关键词：

Emission Evaluation for Diesel Vehicles Under Typical Operating Conditions

学校读者我要写书评

暂无评论

Emission Evaluation for Diesel Vehicles Under Typical Operat...

International Conference on Advanced Robotics and Mechatronics (ICARM)

作者： Jiaren Li Zhenyi Xu Yang Cao Xiushan Xia Yu Kang AHU-IAI AI Joint Laboratory Anhui University Hefei China Key Laboratory of System Control and Information Processing Ministry of Education Shanghai Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei China Department of Automation University of Science and Technology of China Hefei China Institute of Advanced Technology University of Science and Technology of China Hefei China

China‘s ambient air quality has improved significantly as a result of the formulation and implementation of the Action Plan for the Prevention and control of Air Pollution and the Three-Year Action Plan for Winning the Blue Sky Defense War, but the air pollution problem in key regions remains severe, diesel truck pollution has not been effectively addressed, and mobile sources are an important source of nitrogen oxide emissions. The existing diesel vehicle emission model is primarily divided based on average vehicle speed and VSP binning methods, and it lacks an instantaneous vehicle speed model. This paper collected data from 10 diesel vehicles in order to accurately evaluate driving conditions and promote energy saving and emission reduction of heavy-duty diesel vehicles. Then we extracted 51,925 kinematic fragment data after cleaning abnormal data and built a kinematic feature evaluation system of diesel vehicles closely related to NOx emission. The sample data of kinematic segments were clustered into two groups of low-speed conditions and medium-speed conditions using the standardized mutual information to extract the characteristics with strong correlation with NOx and the vehicle driving conditions assessment model of cluster analysis. From the clustering results, the high NOx emission is completely classified into the low-speed working condition, which matches the conclusion that the high NOx emission region appears in the low-speed acceleration region reached by previous researchers through experimental studies, indicating that the kinematic feature evaluation model of diesel vehicles established in this paper is reasonable and effective.

关键词：

Ultrasensitive Ammonia Gas Sensor Based on Ti3c2tx/Ti3alc2 Planar Composite at Room Temperature

学校读者我要写书评

暂无评论

SSRN 2022年

作者： Liu, Zhihua Han, Dan Liu, Lulu Li, Donghui Han, Xiaomei Chen, Yi Liu, Xiaoru Zhuo, Kai Cheng, Yongqiang Sang, Shengbo Shanxi Key Laboratory of Micro Nano Sensors & Artificial Intelligence Perception College of Information and Computer Taiyuan University of Technology Taiyuan030024 China Key Lab of Advanced Transducers and Intelligent Control System of the Ministry of Education Taiyuan University of Technology Taiyuan030024 China

Two-dimensional (2D) transition metal carbides (MXene) have attracted great attention for device applications due to their unique structures and excellent properties, such as high electrical conductivity and abundant functional groups on the surface. However, gas sensors based on Ti3C2Tx MXene have the problems of high detection limit and poor long-term stability. Herein, we report a simple method to prepare Ti3C2Tx/Ti3AlC2 planar composite gas sensing materials using high molar ratio of HCl and LiF with Ti3AlC2 as a framework. The Ti3C2Tx/Ti3AlC2 planar composite gas sensor has a high sensitivity, good selectivity and low detection limit for NH3, which can detect 50 ppb (1.2%) at room temperature (25°C). Furthermore, the gas sensor has good repeatability and long-term stability. After 120 days, the response of the gas sensor to 500 ppb of NH3 fluctuated little due to the Ti3AlC2 as a framework. The superior performances can be attributed to the special heterojunction between Ti3C2Tx and Ti3AlC2 and the high proportion of -O and -OH functional groups on the surface of Ti3C2Tx/Ti3AlC2 composite. This study provides an important reference for the realization of high performance NH3 sensing by Ti3C2Tx. © 2022, The Authors. All rights reserved.

关键词： Chemical detection

Bearing Fault Diagnosis Based on Dual-Data Input Convolutional Neural Network

学校读者我要写书评

暂无评论

SSRN 2022年

作者： He, Chaoqian Hao, Runfang Yang, Kun Yuan, Zhongyun Shang, Shengbo Wang, Xiaorui Shanxi Key Laboratory of Micro Nano Sensors & Artificial Intelligence Perception College of Information and Computer Taiyuan University of Technology Taiyuan030024 China Key Lab of Advanced Transducers and Intelligent Control System Ministry of Education Taiyuan University of Technology Taiyuan030024 China

Previous bearing fault diagnosis models show low accuracy and unstable performance in strong noise environment, which are not suitable for the actual complex industrial scenarios. In this paper, the dual-channel convolution model (DDCNN) based on dual-data inputs is established. The model used the reconstructed two-dimensional data as inputs. In one channel, convolution with small kernel is used to extract details of FE data, and large kernel obtain global information of DE data in the other. The output is classified through the full connection layer after the data features of both channels are fused. Besides, data are mixed from different loads to avoid cross-load effects as much as possible. The results demonstrate that the proposed model has good accuracy and anti-noise performance. The accuracy is as high as 92.65% when the SNR is -10. © 2022, The Authors. All rights reserved.

关键词： Failure analysis

Study on Sensitization Mechanism of Novel Magnetorheological Composite Pdms Thin Film Based on Enhanced Magneto-Mechanical Effect

学校读者我要写书评

暂无评论

SSRN 2023年

作者： Sang, Shengbo Tan, Qiuyun Jiang, Jiaolin Wu, Kaile Xiao, Pengli Zhao, Dong Guo, Xing Yang, Zhuoqing Dong, Xiushan Ge, Yang Shanxi Key Laboratory of Micro Nano Sensors & Artificial Intelligence Perception College of Information and Computer Taiyuan University of Technology Taiyuan030024 China Key Lab of Advanced Transducers and Intelligent Control System Ministry of Education Taiyuan University of Technology Taiyuan030024 China Shanghai200240 China Shanxi Academy of Medical Sciences China Shanxi Research Institute of 6D Artificial Intelligence Biomedical Science Taiyuan030024 China

High sensitivity is key to expand the range of bio-detection, especially in realizing biological detection on single molecular level. Herein, we introduce a novel magnetorheological membrane with enhanced magneto-mechanical effect into the biosensor. Specifically, we made the magnetorheological composite PDMS film (MREF) strengthened by magnetostrictive particles (MSP), and the anisotropic TbDyFe-PDMS can be magnetically deformed to 90 °with 5.8 emu/g, which possesses an initial tensile modulus 55% higher than isotropic. In particular, the modified MR effect equations were proposed considering magnetic dipole interaction and nonlinear magnetostrictive pre-strain of MSP. Such formulae indicate that the enhanced MR effect of MSP-MREF is greatly determined by Ms, remanence, and the flux linkage-like structure. In addition, finite element simulations were carried out to validate and complementarily demonstrate the nonlinear magneto-mechanical behaviors of MSP-MREF theoretically. Finally, the biosensor based on MSP-MREF was fabricated to detect the low concentrations of human serum albumin (HSA), and its sensitivity is around 4 times that of the conventional biosensor. Furthermore, it exhibits high reliability in detecting HSA in real human urine samples, making it the ideal candidate as a practical and effective way for the detection of biomolecules at low concentrations in the future. © 2023, The Authors. All rights reserved.

关键词： Finite element method

Ultrasensitive Ammonia Gas Sensor Based on Ti3c2tx/Ti3alc2 Planar Composite at Room Temperature

学校读者我要写书评

暂无评论

SSRN 2022年

作者： Liu, Zhihua Han, Dan Liu, Lulu Li, Donghui Han, Xiaomei Chen, Yi Liu, Xiaoru Zhuo, Kai Cheng, Yongqiang Sang, Shengbo Shanxi Key Laboratory of Micro Nano Sensors & Artificial Intelligence Perception College of Information and Computer Taiyuan University of Technology Taiyuan030024 China Key Lab of Advanced Transducers and Intelligent Control System the Ministry of Education Taiyuan University of Technology Taiyuan030024 China

Two-dimensional (2D) transition metal carbides (MXene) have attracted great attention for device applications due to their unique structures and excellent properties, such as high electrical conductivity and abundant functional groups on the surface. However, gas sensors based on Ti3C2Tx MXene have the problems of high detection limit and poor long-term stability. Herein, we report a simple method to prepare Ti3C2Tx/Ti3AlC2 planar composite gas sensing materials using high molar ratio of HCl and LiF with Ti3AlC2 as a framework. The Ti3C2Tx/Ti3AlC2 planar composite gas sensor has a high sensitivity, good selectivity and low detection limit for NH3, which can detect 50 ppb (1.2%) at room temperature ((25 ± 2) °C). Furthermore, the gas sensor has good repeatability and long-term stability. After 120 days, the response of the gas sensor to 500 ppb of NH3 fluctuated little due to the Ti3AlC2 as a framework. The superior performances can be attributed to the special heterojunction between Ti3C2Tx and Ti3AlC2 and the high proportion of -O and -OH functional groups on the surface of Ti3C2Tx/Ti3AlC2 composite. This study provides an important reference for the realization of high performance NH3 sensing by Ti3C2Tx. © 2022, The Authors. All rights reserved.

关键词： Gases

Biocompatible chitosan/polyethylene glycol/multi-walled carbon nanotube composite scaffolds for neural tissue engineering

学校读者我要写书评

暂无评论

Journal of Zhejiang University-Science B(Biomedicine & Biotechnology) 2022年第1期23卷 58-73页

作者： Shengbo SANG Rong CHENG Yanyan CAO Yayun YAN Zhizhong SHEN Yajing ZHAO Yanqing HAN Shanxi Key Laboratory of Micro Nano Sensors&Artificial Intelligence Perception College of Information and ComputerTaiyuan University of TechnologyTaiyuan030024China Key Lab of Advanced Transducers and Intelligent Control System of the Ministry of Education Taiyuan University of TechnologyTaiyuan030024China College of Information Science and Engineering Hebei North UniversityZhangjiakou075000China Shanxi Six-Dimensional Artificial Intelligence Biomedical Research Institute Taiyuan030031China Department of Neurology Shanxi Provincial Cardiovascular HospitalTaiyuan030024China

Carbon nanotube(CNT)composite materials are very attractive for use in neural tissue engineering and biosensor *** scaffolds are excellent mimics of extracellular matrix due to their hydrophilicity,viscosity,and *** can also impart conductivity to other insulating materials improve mechanical stability guide neuronal cell behavior and trigger axon *** performance of chitosan(CS)/polyethylene glycol(PEG)composite scaffolds could be optimized by introducing multi-walled CNTs(MWCNTs).CS/PEG/CNT composite scaffolds with CNT content of 1%,3%,and 5%(1%=0.01 g/mL)were prepared by *** physical and chemical properties and biocompatibility were *** electron microscopy(SEM)showed that the composite scaffolds had a highly connected porous *** electron microscope(TEM)and Raman spectroscopy proved that the CNTs were well dispersed in the CS/PEG matrix and combined with the CS/PEG nanofiber *** enhanced the elastic modulus of the *** porosity of the scaffolds ranged from 83%to 96%.They reached a stable water swelling state within 24 h,and swelling decreased with increasing MWCNT *** electrical conductivity and cell adhesion rate of the scaffolds increased with increasing MWCNT *** showed that rat pheochromocytoma(PC12)cells grown in the scaffolds had characteristics similar to nerve *** measured changes in the expression of nerve cell markers by quantitative real-time polymerase chain reaction(qRT-PCR),and found that PC12 cells cultured in the scaffolds expressed growth-associated protein 43(GAP43),nerve growth factor receptor(NGFR),and class IIIβ-tubulin(TUBB3)*** research showed that the prepared CS/PEG/CNT scaffold has good biocompatibility and can be further applied to neural tissue engineering research.

关键词： Multi-walled carbon nanotube(MWCNT) Cell-scaffold PC12 cells Biocompatibility