检索结果-内蒙古大学图书馆

Motion-based visual inspection of optically indiscernible defects on the example of hazelnuts

COMPUTERS AND ELECTRONICS IN AGRICULTURE 2021年 185卷 106147-106147页

作者： Maier, Georg Shevchyk, Anja Flitter, Merle Gruna, Robin Laengle, Thomas Hanebeck, Uwe D. Beyerer, Juergen Fraunhofer IOSB Inst Optron Syst Technol & Image Exploitat Karlsruhe Germany Karlsruhe Inst Technol KIT Intelligent Sensor Actuator Syst Lab ISAS Karlsruhe Germany Karlsruhe Inst Technol KIT Vis & Fus Lab IES Karlsruhe Germany

Automatic quality control has long been an integral part of the processing of food and agricultural products. Visual inspection offers solutions for many issues in this context and can be employed in the form of sensor-based sorting to automatically remove foreign and low quality entities from a product stream. However, these methods are limited to defects that can be made visible by the employed sensor, which usually restricts the system to defects appearing on the surface. An alternative non-visual solution lies in impact-acoustic methods, which do not suffer from this constraint. However, these are strongly limited in terms of material throughput and consequently not suitable for large scale industrial application. In this paper, we present a novel approach that performs inspection based on optically acquired motion data. A high-speed camera captures image sequences of test objects during a transportation process on a chute with a specific structured surface. The trajectory data is then used to classify test objects based on their motion behavior. The approach is evaluated experimentally on the example of distinguishing defect-free hazelnuts from ones that suffer from insect damage. Results show that by merely utilizing the motion data, a recognition rate of up to 80% for undamaged hazelnuts can be achieved. A major advantage of our approach is that it can be integrated in sensor-based sorting systems and is suitable for high throughput applications.

关键词： Object trajectory Motion classification sensor-based Sorting Impact-acoustic

来源：评论

学校读者我要写书评

暂无评论

Infrared Small Target Detection via Low-Rank Tensor Completion With Top-Hat Regularization

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2020年第2期58卷 1004-1016页

作者： Zhu, Hu Liu, Shiming Deng, Lizhen Li, Yansheng Xiao, Fu Nanjing Univ Posts & Telecommun Jiangsu Prov Key Lab Image Proc & Image Commun Nanjing 210003 Peoples R China Nanjing Univ Posts & Telecommun Natl Engn Res Ctr Commun & Network Technol Nanjing 210003 Peoples R China Wuhan Univ Sch Remote Sensing & Informat Engn Wuhan 430079 Peoples R China Nanjing Univ Posts & Telecommun Jiangsu High Technol Res Key Lab Wireless Sensor Nanjing 210023 Peoples R China

Infrared small target detection technology is one of the key technologies in the field of computer vision. In recent years, several methods have been proposed for detecting small infrared targets. However, the existing methods are highly sensitive to challenging heterogeneous backgrounds, which are mainly due to: 1) infrared images containing mostly heavy clouds and chaotic sea backgrounds and 2) the inefficiency of utilizing the structural prior knowledge of the target. In this article, we propose a novel approach for infrared small target detection in order to take both the structural prior knowledge of the target and the self-correlation of the background into account. First, we construct a tensor model for the high-dimensional structural characteristics of multiframe infrared images. Second, inspired by the low-rank background and morphological operator, a novel method based on low-rank tensor completion with top-hat regularization is proposed, which integrates low-rank tensor completion and a ring top-hat regularization into our model. Third, a closed solution to the optimization algorithm is given to solve the proposed tensor model. Furthermore, the experimental results from seven real infrared sequences demonstrate the superiority of the proposed small target detection method. Compared with traditional baseline methods, the proposed method can not only achieve an improvement in the signal-to-clutter ratio gain and background suppression factor but also provide a more robust detection model in situations with low false-positive rates.

关键词： Object detection Morphology Weight measurement Periodic structures Optimization Signal to noise ratio Low-rank tensor completion multiframe infrared image ring top-hat regularization small target detection structural prior knowledge

来源：评论

学校读者我要写书评

暂无评论

Study on the segmentation method of multi-phase CT liver tumor based on dual channel U-Nets

Study on the segmentation method of multi-phase CT liver tum...

引用

2020 International Symposium on Automation, Information and Computing, ISAIC 2020

作者： Xu, Changchang Hu, Dong Zhang, YaoDong Pang, Yuwei Jiangsu Province’s Key Lab of Image Procession and Image Communications Nanjing University of Posts and Telecommunications Nanjing210003 China Education Ministry’s Key Lab of Broadband Wireless Communication and Sensor Network Technology Nanjing University of Posts and Telecommunications Nanjing210003 China Education Ministry’s Engineering Research Center of Ubiquitous Network and Heath Service Nanjing University of Posts and Telecommunications Nanjing210003 China first clinical medical college of Nanjing Medical University Nanjing University of Posts and Telecommunications Nanjing210003 China

As a common malignant tumor disease, hepatocellular carcinoma is the most common cancers in the world. The incidence of hepatocellular carcinoma in China is higher than that in the world. Therefore, it is very important for doctors to separate liver and tumor from CT images by means of computer-aided diagnosis and treatment. In this paper, a multiscale DC-CUNets network liver tumor segmentation method is proposed to enhance the fusion of multi-phase image features in CT, the scale of liver tumors, and the optimization of network training process. (1) A multistage CT liver tumor segmentation method based on two-channel cascaded U-Nets (DC-CUNets) is proposed. The liver was segmented using the first-order U-Net, and then the segmented area of interest of the liver was input into the second-order U-Net network to segment liver tumors. We designed two-channel U-Nets to learn the image characteristics of CT images in arterial and venous phases respectively, and to achieve two-channel feature fusion through feature cascade to improve the overall accuracy of liver tumor segmentation.(2) A multistage CT liver tumor segmentation method based on multiscale DC-CUNets was proposed. For the scale problem of liver tumors, we designed a two-layer multiscale void convolution module to obtain image features at different scales for large, medium and small tumors, and fuse the multiscale features at the output of the module. We have replaced the convolution layer of the fourth module in the second-order two-channel liver tumor segmentation U-Nets by the two-layer multiscale cavity convolution module to implement multiscale DC-CUNets. © 2021 Institute of Physics Publishing. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Towards a feed material adaptive optical belt sorter: A simulation study utilizing a DEM-CFD approach

引用

POWDER TECHNOLOGY 2022年 411卷 117917页

作者： Bauer, Albert Maier, Georg Reith-Braun, Marcel Kruggel-Emden, Harald Pfaff, Florian Gruna, Robin Hanebeck, Uwe Laengle, Thomas Tech Univ Berlin Chair Mech Proc Engn & Solids Proc Ernst Reuter Pl 1 D-10587 Berlin Germany Fraunhofer IOSB Inst Optron Syst Technol & Image Exploitat Fraunhoferstr 1 D-76131 Karlsruhe Germany Karlsruhe Inst Technol Intelligent Sensor Actuator Syst Lab ISAS D-76131 Karlsruhe Germany

In this investigation, a DEM-CFD model of an optical belt sorter is modified to become adaptive to varying belt speeds. For that, the positions and orientations of the nozzle bar and collecting containers are rearranged. Also, the duration of nozzle activation and optimal position of particle ejection are adjusted. For the derivation of optimal velocity-dependent parameters, a two-dimensional model is derived and optimized as a pre-processing step. The derived parameters are applied to the three-dimensional DEM-CFD model. Two optically distinguish-able types of demolition waste materials are considered. All conveyor belt velocities are investigated with instantaneously and lagged activated nozzles, which represent fast and realistic triggered nozzle activations. The application of optimized sorting setups shows promising sorting results for a broad range of conveyor belt ve-locities. The obtained results are discussed in terms of their feasibility in being applied to real optical belt sorters.

关键词： Discrete element method (DEM) Computational fluid dynamics (CFD) Optical belt sorting Sorting optimization

来源：评论

学校读者我要写书评

暂无评论

Nanophotonic sensor implants with 3D hybrid periodic-amorphous photonic crystals for wide-angle monitoring of long-term in-vivo intraocular pressure 66

Nanophotonic sensor implants with 3D hybrid periodic-amorpho...

引用

IEEE International Electron Devices Meeting (IEDM)

作者： Siddique, R. H. Liedtke, L. Park, H. Lee, S. Y. Raniwala, H. Park, D. Y. Lim, D. H. Choo, H. Samsung Semicond Inc Image Sensor Lab Pasadena CA 91101 USA CALTECH Pasadena CA 91125 USA Samsung Med Ctr Seoul South Korea Samsung Adv Inst Technol Suwon South Korea

ISBN: (纸本)9781728188881

Glaucoma, one of the leading cause of irreversible blindness, is largely caused by an elevated intraocular pressure (IOP). However, current IOP monitoring techniques inherit major disadvantages such as imprecision, no real or long time monitoring, and difficult readout. Here, we report on a highly miniaturized (200 um thick) optomechanical nanophotonic sensor implant for long-term, continuous and on-demand IOP monitoring. This IOP sensor is made of a flexible 3D hybrid photonic crystals (HPC) that functions as a pressure-sensitive optical resonator (0.1 nm/mm Hg) and delivers IOP readings when interrogated with near-infrared light with an average accuracy of 0.56 mm Hg over the range of 0-40 mm Hg. A new fabrication process is developed using colloidal self-assembly leading to a single step formation of hybrid periodic and amorphous layers exploiting the inverse process of a drying "coffee-stain" effect. The HPC results in a wide-angle strong resonance of +/- 40 degrees ensuring an easy and accurate remote and long readout distance. 8 sensors were mounted inside the anterior chamber in New Zealand white rabbits and provided continuous, accurate measurements of IOP with handheld detector for up to 6 months with no signs of inflammation.

关键词： Nanophotonics

来源：评论

学校读者我要写书评

暂无评论

Bioinspired Disordered Flexible Metasurfaces for Human Tear Analysis Using Broadband Surface-Enhanced Raman Scattering

引用

ACS OMEGA 2020年第22期5卷 12915-12922页

作者： Narasimhan, Vinayak Siddique, Radwanul Hasan Park, Haeri Choo, Hyuck CALTECH Dept Elect Engn Pasadena CA 91125 USA Samsung Elect Samsung Adv Inst Technol Suwon 16678 Gyeonggi Do South Korea CALTECH Dept Med Engn Pasadena CA 91125 USA Samsung Semicond Inc Image Sensor Lab Pasadena CA 91101 USA

Flexible surface-enhanced Raman scattering (SERS) has received attention as a means to move SERS-based broadband biosensing from bench to bedside. However, traditional flexible periodic nano-arrangements with sharp plasmonic resonances or their random counterparts with spatially varying uncontrollable enhancements are not reliable for practical broadband biosensing. Here, we report bioinspired quasi(dis) ordered nanostructures presenting a broadband yet tunable application-specific SERS enhancement profile. Using simple, scalable biomimetic fabrication, we create a flexible metasurface (flex-MS) of quasi(dis)ordered metal-insulator-metal (MIM) nanostructures with spectrally variable, yet spatially controlled electromagnetic hotspots. The MIM is designed to simultaneously localize the electromagnetic signal and block background Raman signals from the underlying polymeric substrate-an inherent problem of flexible SERS. We elucidate the effect of quasi(dis)ordering on broadband tunable SERS enhancement and employ the flex-MS in a practical broadband SERS demonstration to detect human tear uric acid within its physiological concentration range (25-150 mu M). The performance of the flex-MS toward noninvasively detecting whole human tear uric acid levels ex vivo is in good agreement with a commercial enzyme-based assay.

关键词： Diseases and disorders Nanostructures sensors Raman spectroscopy Chemical structure

来源：评论

学校读者我要写书评

暂无评论

Gesture Recognition Through sEMG with Wearable Device Based on Deep Learning

引用

MOBILE NETWORKS & APPLICATIONS 2020年第6期25卷 2447-2458页

作者： Shen, Shu Gu, Kang Chen, Xin-Rong Lv, Cai-Xia Wang, Ru-Chuan Nanjing Univ Posts & Telecommun Sch Comp Sci Nanjing 210023 Jiangsu Peoples R China Jiangsu High Technol Res Key Lab Wireless Sensor Nanjing 210023 Jiangsu Peoples R China Fudan Univ Acad Engn & Technol Shanghai 200433 Peoples R China Shanghai Key Lab Med Image Comp & Comp Assisted I Shanghai 200032 Peoples R China

It is conducive to the application of sEMG signals in helping disabled people through combining wearable devices with deep learning. Therefore, design of sEMG gesture recognition system using deep learning based on wearable device is proposed in this paper. The system is mainly consisted of wearable sEMG acquisition device and sEMG gesture recognition method based on deep learning. In the wearable sEMG acquisition device, the sEMG signal sensor is mainly used to convert the human bioelectrical signal into an analog electrical signal. Then it can be acquired using an analog to digital converter. We also use 2.4 GHz wireless communication for data transmission, and use the micro-controller as the core of system control and data processing. In the sEMG gesture recognition method, we designed a model of sEMG signal gesture classification based on convolutional neural network (CNN). It can avoid omission of important feature information and improve accuracy of recognition, effectively. In the experimental part, we collected the sEMG signals of three different gestures using our own wearable sEMG acquisition device. Then, we trained and evaluated on the designed sEMG gesture recognition model using these data. A recognition accuracy of about 79.43% can be achieved in three gestures. Finally, we trained and tested the sEMG gesture recognition model on the Ninapro DB5 dataset and can reach about 74.51% accuracy on 52 gestures. In the case that there are more types of gestures recognized, our accuracy is still 5.02%, 6.61%, and 2.58% higher than Linear Discriminant Analysis (LDA), Support Vector Machine (SVM), and Long Short Term Memory-CNN (LCNN), respectively. Also, the accuracy rate is 5.47% higher than SVM and Random Forests.

关键词： Surface electromyography Gesture recognition Convolutional neural network Wearable device

来源：评论

学校读者我要写书评

暂无评论

A Two-Stage Attribute-Constraint Network for Video-Based Person Re-Identification

引用

IEEE ACCESS 2019年 7卷 8508-8518页

作者： Song, Wanru Zheng, Jieying Wu, Yahong Chen, Changhong Liu, Feng Nanjing Univ Posts & Telecommun Jiangsu Key Lab Image Proc & Image Commun Nanjing 210003 Jiangsu Peoples R China Nanjing Univ Posts & Telecommun Key Lab Broadband Wireless Commun & Sensor Networ Minist Educ Nanjing 210003 Jiangsu Peoples R China

Person re-identification has gradually become a popular research topic in many fields such as security, criminal investigation, and video analysis. This paper aims to learn a discriminative and robust spatial-temporal representation for video-based person re-identification by a two-stage attribute-constraint network (TSAC-Net). The knowledge of pedestrian attributes can help re-identification tasks because it contains high-level information and is robust to visual variations. In this paper, we manually annotate three video-based person re-identification datasets with four static appearance attributes and one dynamic appearance attribute. Each attribute is regarded as a constraint that is added to the deep network. In the first stage of the TSAC-Net, we solve the re-identification problem as a classification issue and adopt a multi-attribute classification loss to train the CNN model. In the second stage, two LSTM networks are trained under the constraint of identities and dynamic appearance attributes. Therefore, the two-stage network provides a spatial-temporal feature extractor for pedestrians in video sequences. In the testing phase, a spatial-temporal representation can be obtained by inputting a sequence of images to the proposed TSAC-Net. We demonstrate the performance improvement gained with the use of attributes on several challenging person re-identification datasets (PRID2011, iLIDS-VID, MARS, and VIPeR). Moreover, the extensive experiments show that our approach achieves state-of-the-art results on three video-based benchmark datasets.

关键词： Attribute constraint feature extraction person re-identification video

来源：评论

学校读者我要写书评

暂无评论

Weighted Direct Nonlinear Regression for Effective image Interpolation

引用

IEEE ACCESS 2019年 7卷 8646-8659页

作者： Zheng, Jieying Song, Wanru Wu, Yahong Liu, Feng Nanjing Univ Posts & Telecommun Jiangsu Key Lab Image Proc & Image Commun Nanjing 210003 Jiangsu Peoples R China Nanjing Univ Posts & Telecommun Minist Educ Key Lab Broadband Wireless Commun & Sensor Networ Nanjing 210003 Jiangsu Peoples R China

This paper proposes a learning-based image interpolation method based on weighted direct nonlinear regression. It attempts to learn the nonlinear relationship between the low-resolution patches and their corresponding high-resolution patches by using an external database of natural images. In the training phase, without being initialized to the same size as the high-resolution patches using bicubic interpolation, low-resolution patches are directly used for training, which will reduce the number of parameters. Dictionary learning combined with nearest neighbor searching based on the normalized correlation coefficient in the entire training set is proposed as a soft classification method. Afterward, a single hidden-layer feed-forward network with random input weights is adopted to learn the direct nonlinear mapping for the regression in each class. In the interpolation phase, the strategy of weighting multiple estimations is applied to enhance the interpolation performance. Furthermore, a refinement process is proposed to improve the interpolation performance with sharper edges and richer details. Extensive experimental results demonstrate that our proposed method is not only effective and efficient but also outperforms many state-of-the-art methods.

关键词： image interpolation image processing super-resolution anchored neighborhood dictionary learning nonlinear regression training

来源：评论

学校读者我要写书评

暂无评论

Iterative Deep Fusion for 3D Semantic Segmentation 4

Iterative Deep Fusion for 3D Semantic Segmentation

引用

4th IEEE International Conference on Robotic Computing (IEEE IRC)

作者： Duerr, Fabian Weigel, Hendrik Maehlisch, Mirko Beyerer, Juergen AUDI AG Dept Sensor Fus & MapLearning Automated Driving Ingolstadt Germany Fraunhofer Ctr Machine Learning Fraunhofer Inst Optron Syst Technol & Image Exploitat IOSB Karlsruhe Germany Karlsruhe Inst Technol Vis & Fus Lab KIT Karlsruhe Germany

ISBN: (纸本)9781728152370

Understanding and interpreting a scene is a key task of environment perception for autonomous driving, which is why autonomous vehicles are equipped with a wide range of different sensors. Semantic segmentation of sensor data provides valuable information for this task and is often seen as key enabler. In this paper, we are presenting a deep learning approach for 3D semantic segmentation of lidar point clouds. The proposed architecture uses a range view representation of 3D point clouds and additionally exploits camera features to increase accuracy and robustness. In contrast to other approaches, which fuse lidar and camera feature maps once, we fuse them iteratively and at different scales inside our network architecture. We demonstrate the benefits of the presented iterative deep fusion approach over single fusion approaches on a large benchmark dataset. Our evaluation shows considerable improvements, resulting from the additional use of camera features. Furthermore, our fusion strategy outperforms the current state-of-the-art strategy by a considerable margin. Despite the use of camera features, the presented approach is also trainable solely with point cloud labels.

关键词： 3D Semantic Segmentation Convolutional Neural Network Deep sensor Fusion Lidar

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：