检索结果-内蒙古大学图书馆

2023 International Conference on Engineering of Optical System and Precision Instruments, ICEOP 2023

作者： Shi, Jiashuo Zhou, Liang Zhang, Xinyu National Key Laboratory of Science and Technology on Multi-spectral Information Processing Huazhong University of Science and Technology Wuhan430074 China School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China

A novel approach called DE-ED (Diffractive Encoding-Electronic Decoding) for rapid all-in-focus capturing is presented in this paper. The paradigm combines the strengths of diffractive networks (DON) for encoding and electronic-based networks (ENN) for decoding, resulting in a robust computational imaging framework driven by advanced deep learning techniques. By leveraging the collaboration between diffractive layers and electronic layers, our model achieves remarkable enhancements in the ability to generalize and fit data. This means that the model can effectively capture and process complex visual information, resulting in superior image quality and enhanced performance. © Published under licence by IOP Publishing Ltd.

关键词： Computational Imaging

来源：评论

学校读者我要写书评

暂无评论

HLA: Harmonized Label Assigner for Two-stage Oriented Object Detection

HLA: Harmonized Label Assigner for Two-stage Oriented Object...

引用

2022 International Conference on Automation, Robotics and Computer Engineering, ICARCE 2022

作者： Chen, Qimeng Zheng, Tong Liu, Liu Yu, Longji Chen, Zhong Huazhong University of Science and Technology National Key Laboratory of Science and Technology on Multi-Spectral Information Processing Wuhan China Huazhong University of Science and Technology National Key Laboratory of Science and Technology on Multispectral Information Processing Wuhan China

ISBN: (纸本)9781665475488

The existing state-of-the-arts two-stage oriented object detectors have no significant improvement in the label assignment strategies, and the most widely-used one is the so-called Max IoU Assigner (MIA). In this paper, we first illustrate that MIA may cause matching conflicts in some cases, hinder the matching of ground-truth (GT) boxes with high-quality samples, which is extremely harmful to the training process. After that, we propose a Harmonized Label Assigner (HLA) for the oriented RPN, which can automatically harmonize the assignment priority of each GT box according to the corresponding number of candidate samples, solve the matching conflicts, and improve the detection accuracy of the two-stage oriented detectors. Finally, we implement the proposed HLA on Oriented R-CNN and conduct sufficient experiments on two public datasets (MAR20 and HRSC2016). Without tricks, our HLA significantly improves the detection accuracy of the detector to 83.97% mAP (on MAR20) and 90.42% mAP (on HRSC2016), respectively. © 2022 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Cross-Domain Defect GAN: Defect Generation for Defect Detection in Industrial Area 3

Cross-Domain Defect GAN: Defect Generation for Defect Detect...

引用

3rd International Conference on Big Data, information and Computer Network, BDICN 2024

作者： Wang, Xin Huang, Xiao Yue, Zhongmu Ma, Jie School of China-EU Institute for Clean and Renewable Energy Huazhong University of Science and Technology National Key Laboratory of Science and Technology on Multi-spectral Information Processing Wuhan Hubei China China Ship Development and Design Center Wuhan Hubei China

ISBN: (纸本)9798350363821

Automatic defect detection is more and more widely applied in the industrial field, and the accuracy of detection is significant for product quality control. However, the defect samples that can be collected in the industrial field are limited. Therefore, this paper proposes Cross-Domain Defect GAN, which can generate realistic and diverse defect samples in the absence of real defect data in the target domain. There are totally two generator-detector parts. The first part is to generate similar domain defect images according to the shape and the position of the defect mask generated in the previous stage. In this part, the similar domain defect image dataset is able to be further expanded. The second part is to convert the original similar domain defect images and defect images of similar domains which has generated in the first part are transferred to the target domain defect samples. There are two characteristics of our methods: (1) Generate target defect images without real defect images input;(2) Improve the structure of image-image translation network to meet our purpose. In addition, it also verifies the effectiveness of synthetic defect samples in training defect classification. © 2024 IEEE.

关键词： Data augmentation Defect detection Generative adversarial network

来源：评论

学校读者我要写书评

暂无评论

Small and Dim Target Detection of Infrared Sequence Based on Tensor Average Rank and Prior Target Weight 4

Small and Dim Target Detection of Infrared Sequence Based on...

引用

4th International Conference on information Science, Electrical, and Automation Engineering, ISEAE 2022

作者： Yadong, Yang Yihua, Tan National Key Laboratory of Science and Technology on Multi-spectral Information Processing School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)9781510655157

The detection of small and dim targets in infrared image sequences is a key technology in infrared search and tracking systems. The optimization method based on low-rank and sparse decomposition is the mainstream research method in this field. Most of the existing optimization methods are based on a single frame, only exploiting spatial information but ignoring the time dimension. The multi-frame detection method makes full use of temporal and spatial information to achieve higher accuracy. However, the existing multi-frame detection method is very slow, because they rely on slow decomposition methods. To solve the problem, we propose the infrared sequence tensor model for multi-frame detection. First, we select the tensor average rank to describe the low-rank property of the infrared sequence. It can be solved quickly. Second, we introduce a new approach to extract prior information as a prior weight tensor, which can highlight the target and suppress noise and strong edges on the background. Third, we formulate the optimization equation based on the tensor average rank and prior weight, which can be solved efficiently with tensor robust principal component analysis(TRPCA). Experiments show that our proposed method has high detection accuracy. The speed of our proposed method is much faster than that of the current multi-frame optimization methods and is comparable to that of the single-frame optimization methods. © 2022 SPIE.

关键词： Tensors

来源：评论

学校读者我要写书评

暂无评论

Differentiable Filter Pruning with Attention For Surface Object Detection Network 10

Differentiable Filter Pruning with Attention For Surface Obj...

引用

10th IEEE Joint International information technology and Artificial Intelligence Conference, ITAIC 2022

作者： Xing, Tingzhuang He, Shitan Shang, Zhenqiao Ma, Jie National Key Laboratory of Science and Technology on Multi-spectral Information Processing School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

ISBN: (数字)9781665422079

ISBN: (纸本)9781665422079

The memory requirements and large computing costs make it difficult to deploy object detection networks on unmanned surface vessel embedded platform. Many existing pruning approaches are often based on heuristic criteria, and require manual setting of the compression ratios in each layer. It makes network pruning more difficult and inaccurate. In this paper, we propose a differentiable filter pruning framework with attention(DPA) for the surface object detection network. We added light channel attention module to estimate filter's importance on the original network. After the attention module, we designed a differentiable sparse mask layer, which can mask the unimportant filters without manually setting the compression ratios. Our proposed approach pruned the YOLO-v4 network and the mAP of the pruned model was 0.6% higher than the original model, with a reduction of 70% parameters and 50% FLOPs. In addition, our approach also achieved excellent results on CIFAR-10/100. © 2022 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

A target-oriented method for dividing the effective region of laser interference

A target-oriented method for dividing the effective region o...

引用

2023 International Conference on Computer Graphics, Artificial Intelligence, and Data processing, ICCAID 2023

作者： Hu, Jing Lv, SiQi Ren, LiJun Ren, Jie Zhong, WeiWei Ouyang, Yan He, Jia National Key Laboratory of Science and Technology on Multi-Spectral Information Processing Wuhan China Huazhong Univ. of Science and Technology Wuhan China Air Force Early Warning Academy Wuhan China Chinese People s Liberation Army Troops 95841 China

ISBN: (纸本)9781510677685

Laser interference can interfere with target detection systems to achieve the goal of protecting the target. For example, it can obscure the target and change information such as brightness and contrast in the surrounding region of the interference zone. Therefore, it is necessary to analyze the impact of laser interference on target detection algorithms and evaluate the anti-interference performance of the algorithm. This paper analyzes the impact of laser interference on two target detection algorithms, Faster-RCNN and YOLO-V3, from two perspectives: target occlusion rate and target similarity. Then, a target-oriented method for dividing the effective region of laser interference (TODERLI) is proposed. The effectiveness of the algorithm is verified through experiments. © 2024 SPIE.

关键词： Signal detection

来源：评论

学校读者我要写书评

暂无评论

Attention-Guided Memory Model for Video Object Segmentation 16th

Attention-Guided Memory Model for Video Object Segmentation

引用

16th International Conference on Bio-Inspired Computing: Theories and Applications, BIC-TA 2021

作者： Lin, Yunjian Tan, Yihua National Key Laboratory of Science and Technology on Multi-spectral Information Processing School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9789811912528

Semi-supervised video object segmentation (S-VOS) is defined as pixel-wise separating the object of interest specified to initial mask during inference period. For small object, the exploitable information contained in single frame is limited, making S-VOS task more challenging. Existing methods cannot reach a balance between accuracy and speed on small object sequences. To resolve the problem, we develop an Attention-Guided Memory model (AGM) for video object segmentation by introducing two novel modules, namely Joint Attention Guider (JAG) and spatial-temporal feature fusion (STFF). For accuracy, JAG employs multi-dimension attention mechanism to generate salient feature map, which highlights the object area through visual guide, spatial guide and channel guide. Further, STFF integrates more complete spatial-temporal information by fusing previous memory feature, current high-level salient feature and low-level features, which provides an effective representation of small object. For speed, the STFF employs several light-weight RNNs whose embedded computation architecture is more efficient than the explicit query approach used in the state-of-the-art models. We conduct extensive experiments on DAVIS and YouTube-VOS datasets. For small object on DAVIS 2017, AGM obtains 63.5 % J& F mean with 28.0 fps for 480p, which achieves similar accuracy with about 5x faster speed compared with the state-of-the-art method. © 2022, Springer Nature Singapore Pte Ltd.

关键词： Motion compensation

来源：评论

学校读者我要写书评

暂无评论

HS-FPN: High Frequency and Spatial Perception FPN for Tiny Object Detection

arXiv

引用

arXiv 2024年

作者： Shi, Zican Hu, Jing Ren, Jie Ye, Hengkang Yuan, Xuyang Ouyang, Yan He, Jia Ji, Bo Guo, Junyu Huazhong University of Science and Technology Wuhan China National Key Laboratory of Science and Technology on Multi-Spectral Information Processing Wuhan China

The introduction of Feature Pyramid Network (FPN) has significantly improved object detection performance. However, substantial challenges remain in detecting tiny objects, as their features occupy only a very small proportion of the feature maps. Although FPN integrates multi-scale features, it does not directly enhance or enrich the features of tiny objects. Furthermore, FPN lacks spatial perception ability. To address these issues, we propose a novel High Frequency and Spatial Perception Feature Pyramid Network (HS-FPN) with two innovative modules. First, we designed a high frequency perception module (HFP) that generates high frequency responses through high pass filters. These high frequency responses are used as mask weights from both spatial and channel perspectives to enrich and highlight the features of tiny objects in the original feature maps. Second, we developed a spatial dependency perception module (SDP) to capture the spatial dependencies that FPN lacks. Our experiments demonstrate that detectors based on HS-FPN exhibit competitive advantages over state-of-the-art models on the AI-TOD dataset for tiny object detection. Copyright © 2024, The Authors. All rights reserved.

关键词： High pass filters

来源：评论

学校读者我要写书评

暂无评论

CNS/Pulsar Integrated Navigation Using Two-level Filter

引用

Chinese Journal of Electronics 2023年第2期19卷 265-269页

作者： Jin Liu Jie Ma Jinwen Tian Key Laboratory of National Defense Science and Technology for Multi-spectral Information Processing Technologies Huazhong University of Science and Technology Wuhan China

To improve the position accuracy, a CNS (Celestial navigation system)/pulsar integrated navigation system with clock drift is proposed. In the pulsar navigation subsystem, the epoch-difference method is adopted to eliminate clock drift, but it induces colored noise. The two-level filter, which is composed of an UKF (Unscented Kalman filter) and an $\mathrm{H}_{\infty}$ filter in series connected, is proposed for fusing the data from the celestial navigation and pulsar navigation subsystems. The celestial navigation subsystem adopts the UKF because of its good performance in nonlinear estimation, while the pulsar navigation subsystem utilizes the $\mathrm{H}_{\infty}$ filter due to its robustness to colored noise. Compared with CNS and two CNS/pulsar integrated navigation methods without two-level filter, the proposed method can provide higher navigation accuracy. Simulation results show that the position estimation accuracy of the proposed method can achieve 140m in the presence of clock drift.

关键词： Navigation Simulation Estimation information filters Robustness Space exploration Kalman filters

来源：评论

学校读者我要写书评

暂无评论

A novel active-passive protection strategy endows carbonyl iron with excellent intelligent anti-corrosion and microwave absorption dual functional characteristics

引用

Nano Research 2025年第1期18卷 487-500页

作者： Wei Tian Quanyuan Feng Linbo Zhang Yinfan Liu Xian Jian Longjiang Deng Institute of Microelectronics School of Information Science and TechnologySouthwest Jiaotong UniversityChengdu 611756China National Engineering Researching Centre of Electromagnetic Radiation Control Materials Key Laboratory of Multi-Spectral Absorbing Materials and Structures of Ministry of EducationState Key Laboratory of Electronic Thin Films and Integrated DevicesSchool of Electronic Science and EngineeringUniversity of Electronic Science and Technology of ChinaChengdu 611731China School of Materials and Energy University of Electronic Science and Technology of ChinaChengdu 611731China The Yangtze Delta Region Institute(Huzhou)&School of Electronic Science and Engineering University of Electronic Science and Technology of ChinaHuzhou 313001China

Carbonyl iron absorbers(CI)face significant challenges in practical applications,such as corrosion,interface bonding failure,detachment,and high maintenance ***,we have developed intelligent self-healing technology based on proactive/passive mechanisms via in situ synthesis of self-healing factors(polydopamine/benzotriazole(PDA/BTA))and physical barrier layers(SiO_(2)/1,1,1,3,3,3-hexamethyl disilazane,SiO_(2)/HMDS)to enhance corrosion resistance,while also being compatible with efficient microwave absorption *** unique multiscale structure gives full play to the utilization of the roles of each functional layer,including the intelligent self-healing features of PDA/BTA,physical shielding and spatial confinement characteristics of SiO_(2)/HMDS,and magnetic-dielectric synergistic mechanism resulted from the good impedance matching characteristics,the conduction loss,the interfacial polarization loss and natural *** asfabricated composites achieved an exceptional minimum reflection loss value of-55.4 dB at 10.7 GHz and the effective absorption band of 7.6 ***,it still exhibits obvious self-healing and corrosion resistance characteristics after 360 h corrosion treatment,ascribed to the self-healing mechanism of PDA/BTA and the blocking intervention effect of SiO_(2)/*** work is considered to pave the way for the synthesis of high-performance magnetic absorbers,especially in enhancing their intelligent self-healing ability in corrosive environments.

关键词： microwave absorption intelligent self-healing technology carbonyl iron multiscale structure magneticdielectric synergistic mechanism

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：