检索结果-内蒙古大学图书馆

2023 International Conference on Electronics, Information, and Communication, ICEIC 2023

作者： Kim, Heegwang Sung, Junghoon Kim, Mingi Park, Chanyeong Paik, Joonki Chung-Ang University Image Processing and Intelligent System Laboratory Graduate School of Advanced Imaging Science Multimedia and Film Seoul Korea Republic of Chung-Ang University Image Processing and Intelligent System Laboratory Graduate School of Artificial Intelligence Seoul Korea Republic of

ISBN: (纸本)9798350320213

Since the drone input images are usually filmed at very high altitudes and with various viewing angles, cracks appear in many different sizes and shapes. A commonly used crack detection dataset has a small size such as 480x320, and it is important that how well it detects the prominent continuous cracks. To detect pavement cracks, we proposed an efficient crack detection network. The proposed network achieved better performance than the conventional network. © 2023 IEEE.

关键词： crack detection sigmoid fusion module YOLOX

来源：评论

学校读者我要写书评

暂无评论

Enhancing Thermal Infrared Object Detection Using SimAM-Integrated YOLOX for Improved Feature Representation

Enhancing Thermal Infrared Object Detection Using SimAM-Inte...

引用

IEEE International Conference on Consumer Electronics (ICCE)

作者： Jaehong Yoon Heegwang Kim Chanyeong Park Junbo Jang Jiyoon Lee Joonki Paik Image Processing and Intelligent System Laboratory Graduate School of Advanced Imaging Science Multimedia and Film Chung-Ang University Seoul Korea Image Processing and Intelligent System Laboratory Graduate School of Artificial Intelligence Chung-Ang University Seoul Korea

ISBN: (数字)9798331521165

ISBN: (纸本)9798331521172

Object detection with thermal infrared images is vital for applications like autonomous driving in low-light and adverse environmental conditions. While TIRDet has improved thermal-only object detection through a Thermal-To-Visible (T2V) translation model, this module can suffer from information loss in certain scenarios. To address this, we propose enhancing the CSPDarknet53 backbone of YOLOX within TIRDet by incorporating SimAM, a parameter-free attention mechanism. SimAM enhances feature representation by inferring 3D attention weights based on an energy function inspired by neuroscience theories, without increasing model parameters. By strengthening feature extraction within the backbone, our approach compensates for the T2V module's information loss, thereby improving detection performance under challenging conditions. Experiments on the LLVIP and FLIR datasets demonstrate superior performance, underscoring the effectiveness of parameter-free attention mechanisms for advancing thermal object detection.

关键词： Solid modeling Translation Attention mechanisms Three-dimensional displays Neuroscience Object detection Feature extraction Text to video Autonomous vehicles Consumer electronics

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Privacy Protection Solution: Enhancing Face Obscuring Techniques with Automated Identification, Mobile Integration, and Scalable Services

A Comprehensive Privacy Protection Solution: Enhancing Face ...

引用

IEEE International Conference on Consumer Electronics (ICCE)

作者： Ilhwan Kim Hyeongseok Oh Sangwoo Yun Heunseung Lim Jaeseok Ryu Joonki Paik Image Processing and Intelligent System Laboratory Graduate School of Advanced Imaging Science Multimedia and Film Chung-Ang University Seoul Korea Image Processing and Intelligent System Laboratory Graduate School of Artificial Intelligence Chung-Ang University Seoul Korea

ISBN: (数字)9798331521165

ISBN: (纸本)9798331521172

We propose a novel application aimed at protecting personal privacy. With the proliferation of various media platforms, issues related to personal portraits have emerged. To address these problems, previous applications propose methods for either Mosaic or replace it with another object. However, existing methods suffer from issues such as high time costs and unnatural rendering. To address these problems, we propose designing an automatic face identification and replacement system by combining face detection, super-resolution, and face replacement models. This approach aims to reduce processing time and enhance natural rendering. In addition to the technological advancements, we suggest expanding this system into a mobile service, allowing users to easily protect their privacy on the go. This mobile platform would provide a user-friendly interface and seamless integration with various social media and communication apps, making it accessible to a broader audience. Furthermore, we explore potential expansion opportunities, such as cloud-based processing for scalability and the development of APIs that other developers can integrate into their own applications, thereby broadening the service's reach and impact. We demonstrate that our approach is simpler and more natural compared to traditional handcrafted tasks by applying it to diverse scenarios.

关键词： Privacy Accuracy Scalability Superresolution Media Rendering (computer graphics) Face detection Protection Usability Faces

来源：评论

学校读者我要写书评

暂无评论

ViSeNet: A Visual-Semantic Fusion Network for Enhancing Few-Shot Classification

ViSeNet: A Visual-Semantic Fusion Network for Enhancing Few-...

引用

IEEE International Conference on Consumer Electronics (ICCE)

作者： Dongheon Lee Sangwoo Yun Joonki Paik Image Processing and Intelligent & System Laboratory Graduate School of Artificial Intelligence Chung-Ang University Seoul Korea Image Processing and Intelligent & System Laboratory Graduate School of Advanced & Imaging Science Multimedia and Film Chung-Ang University Seoul Korea

ISBN: (数字)9798331521165

ISBN: (纸本)9798331521172

Few-shot learning addresses the challenge of recognizing novel classes with only a few labeled examples, a critical issue in limited data scenarios. This paper proposes a multi-modal Visual and Semantic Network (ViSeNet), which enhances few-shot classification by mining linguistic features and fusing weighted vectors. ViSeNet generates enriched class prototypes by leveraging both visual and semantic information. The linguistic feature mining process utilizes image-to-text models to produce class-specific textual descriptions, which are then transformed into representative semantic embeddings. For visual feature extraction, we employ a pretrained Swin Transformer, while text embeddings are integrated for each class using weighted factors. By combining these modalities, ViSeNet constructs class prototypes that capture both visual and semantic characteristics. Experimental results on benchmark datasets, particularly CIFAR-FS, demonstrate that ViSeNet achieves performance comparable to state-of-the-art approaches.

关键词： Visualization Semantics Prototypes Linguistics Transformers Feature extraction Vectors Data mining Few shot learning Consumer electronics

来源：评论

学校读者我要写书评

暂无评论

Efficient Light-Weight Deep Neural Network for Person Detection in Drone images

Efficient Light-Weight Deep Neural Network for Person Detect...

引用

2022 IEEE International Conference on Consumer Electronics, ICCE 2022

作者： Kim, Mingi Kim, Heegwang Mok, Yeongheon Paik, Joonki Image Processing and Intelligent System Laboratory Graduate School of Artificial Intelligence Chung-Ang University Seoul Korea Republic of Graduate School of Advanced Imaging Science Multimedia and Film Chung-Ang University Seoul Korea Republic of

ISBN: (纸本)9781665441544

In this paper, we propose an efficient light-weight deep neural network model for small object (person) detection in drone images. The proposed method performs light-weight as well as efficient small object detection by removing the head layers that detects large and medium-sized objects. In addition, the feature was extracted by focusing the weight on the small object while performing feature fusion through the Weighting Module. Finally, since the class imbalance problem between the object and the background is more serious in the drone image, the problem is alleviated by using the focal loss. As a result, the light-weight that can be mounted on the drone and the inference time are faster, and the Average Precision (AP) is higher than the original model. © 2022 IEEE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

Learning-based Framework for Color Conversion between Digital Cinema Package and Streaming Movie

引用

IEIE Transactions on Smart processing and Computing 2022年第5期11卷 324-331页

作者： Lim, Younghoon Park, Kwanwoo Paik, Joonki Image Processing and Intelligent Systems Laboratory Graduate School of Advanced Imaging Science Multimedia and Film Chung-Ang University Seoul06975 Korea Republic of Samsung Research Seoul06765 Korea Republic of Graduate School of Artificial Intelligence Chung-Ang University Seoul06974 Korea Republic of

Humans feel different experiences when viewing a cinema at the theater and home. This paper presents methods to reduce the difference in the viewing experience. Based on the workflow of digital cinema distribution, the proposed method attempts to minimize the color difference between digital cinema packages (DCP) for the theater and streaming movies. For end-to-end mapping between the DCP and streaming movie, this paper proposes a convolutional neural network (CNN)-based color conversion algorithm based on the SMPTE standard. The proposed method consists of three steps: i) color conversion using standard matrices, ii) color conversion using the CNN, and iii) color saturation error removal by fusing the results in steps i) and ii). The proposed method enhances the color of TV streaming images because it minimizes the color difference from the DCP and appropriately extends the color gamut. As a result, the proposed method can provide consumers with indistinguishable quality from a DCP movie at the theater. © 2022 Institute of Electronics and Information Engineers. All rights reserved.

关键词： Color

来源：评论

学校读者我要写书评

暂无评论

Efficient Pavement Crack Detection in Drone images using Deep Neural Networks

Efficient Pavement Crack Detection in Drone Images using Dee...

引用

International Conference on Electronics, Information and Communications (ICEIC)

作者： Heegwang Kim Junghoon Sung Mingi Kim Chanyeong Park Joonki Paik Image Processing and Intelligent System Laboratory Graduate School of Advanced Imaging Science Multimedia and Film Chung-Ang University Seoul Korea Image Processing and Intelligent System Laboratory Graduate School of Artificial Intelligence Chung-Ang University Seoul Korea

关键词： Deep learning Shape Neural networks Drones

来源：评论

学校读者我要写书评

暂无评论

Improved deeplab v3+ with metadata extraction for small object detection in intelligent visual surveillance systems

引用

IEIE Transactions on Smart processing and Computing 2021年第3期10卷 209-218页

作者： Oh, Heungmin Lee, Minjung Kim, Hyungtae Paik, Joonki Department of Image Engineering Processing and Intelligent Systems Laboratory Graduate School of Advanced Imaging Science Multimedia and Film Chung-Ang University / Seoul06974 Korea Republic of

A surveillance system deploys multiple cameras to monitor a wide area in real time to detect abnormal situations such as a crime scene, traffic accident, and natural disaster. An Increased number of cameras results in the same number of monitors, which makes human decisions or automatic decisions difficult. To solve the problem, a smart surveillance scheme has recently been proposed. The smart surveillance system automatically detects an object and provides an alarm to a surveillant. In this paper, we present a metadata extraction method for object-based video summary. The proposed method adopts deep learning-based object detection and background elimination to correctly estimate an object region. Finally, metadata extraction is performed on the estimated object information. The proposed metadata consists of the representative color, size, aspect ratio, and patch of an object. The proposed method can extract reliable metadata without motion features in both static and dynamic cameras. The proposed method can be applied to various object detection areas using complex metadata. Copyrights © 2021 The Institute of Electronics and Information Engineers

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Self-Supervised Plant Phenotyping by Combining Domain Adaptation with 3D Plant Model Simulations: Application to Wheat Leaf Counting at Seedling Stage

引用

Plant Phenomics 2023年第2期5卷 226-238页

作者： Yinglun Li Xiaohai Zhan Shouyang Liu Hao Lu Ruibo Jiang Wei Guo Scott Chapman Yufeng Ge Benoit de Solan Yanfeng Ding Frédéric Baret Plant Phenomics Research Centre Academy for Advanced Interdisciplinary StudiesJiangsu Collaborative Innovation Center for Modern Crop ProductionNanjing Agricultural UniversityNanjingChina Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and AutomationHuazhong University of Science and TechnologyWuhanChina Graduate School of Agricultural and Life Sciences The University of Tokyo1-1-1 Midori-choNishitokyo CityTokyoJapan School of Agriculture and Food Sciences The University of QueenslandSt.LuciaQueensland 4072Australia Department of Biological Systems Engineering University of Nebraska-LincolnLincolnNebraska 68583United States INRAE Avignon UniversitéUMR EMMAHUMT CAPTE228route de l’aérodrome-CS 4050984914 Avignon Cedex 9France ARVALIS Institut du Végétal 3 Rue Joseph et Marie Hackin75116 ParisFrance

The number of leaves at a given time is important to characterize plant growth and *** this work,we developed a high-throughput method to count the number of leaves by detecting leaf tips in RGB *** digital plant phenotyping platform was used to simulate a large and diverse dataset of RGB images and corresponding leaf tip labels of wheat plants at seedling stages(150,000 images with over 2 million labels).The realism of the images was then improved using domain adaptation methods before training deep learning *** results demonstrate the efficiency of the proposed method evaluated on a diverse test dataset,collecting measurements from 5 countries obtained under different environments,growth stages,and lighting conditions with different cameras(450 images with over 2,162 labels).Among the 6 combinations of deep learning models and domain adaptation techniques,the Faster-RCNN model with cycle-consistent generative adversarial network adaptation technique provided the best performance(R^(2)=0.94,root mean square error=8.7).Complementary studies show that it is essential to simulate images with sufficient realism(background,leaf texture,and lighting conditions)before applying domain adaptation ***,the spatial resolution should be better than 0.6 mm per pixel to identify leaf *** method is claimed to be self-supervised since no manual labeling is required for model *** self-supervised phenotyping approach developed here offers great potential for addressing a wide range of plant phenotyping *** trained networks are available at https://***/YinglunLi/Wheat-leaf-tip-detection.

关键词： Wheat seedling Plant

来源：评论

学校读者我要写书评

暂无评论

Cone-Beam Computed Tomography Limited-Angle image Reconstruction Using Planning CT-Guided Deep Diffusion Model

引用

IEEE Transactions on Instrumentation and Measurement 2025年

作者： Wu, Zhan Yang, Yang Hu, Dianlin Lyu, Tianling Li, Yinsheng Tang, Hao Shu, Huazhong Xi, Yan Zhang, Yi Chen, Yang Southeast University Laboratory of Image Science and Technology Nanjing210096 China Southeast University Ministry of Education Key Laboratory of Computer Network and Information Integration Nanjing210096 China Zhejiang University of Technology Academy for Advanced Interdisciplinary Science and Technology Hangzhou China Chinese Academy of Sciences Key Laboratory of Biomedical Imaging Science and System China Capital Medical University Beijing Jishuitan Hospital China First-Imaging Tech Shanghai China Sichuan University School of Cyber Science and Engineering Chengdu China Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Southeast University Ministry of Education Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing Laboratory of Image Science and Technology the School of Computer Science and Engineering Nanjing210096 China

For existing image-guided radiation therapy systems (IGRT), the limited angular range of the cone-beam computed tomography (CBCT) scanning improves the compactness of the system and compatibility between CBCT and linear accelerator configurations. However, the limited-angle CBCT reconstruction under incomplete projection data causes severe artifacts in the reconstructed images, further having a negative impact on the registration accuracy in IGRT. In this paper, we propose a planning CT-guided deep diffusion model, termed LARGE-DiffNet, to improve imaging quality and registration accuracy for limited-angle CBCT image reconstruction. In stark contrast to existing approaches leveraging hand-crafted regularization, such as local smoothness and/or sparsity of the image, LARGE-DiffNet learns the distribution-level prior knowledge to describe the features of ideal CBCT images via a planning CT-guided diffusion model. The proposed LARGE-DiffNet is evaluated on the clinical CBCT dataset, and extensive experimental results demonstrate that the proposed method outperforms the state-of-the-art methods. The proposed LARGE-DiffNet technique has great potential in IGRT. © 1963-2012 IEEE.

关键词： cone-beam computed tomography deep learning diffusion model image registration image-guided radiation therapy limited-angle

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：