检索结果-内蒙古大学图书馆

International Conference on Advances in Information Technology (ICAIT)

作者： Akey Sungheetha Kevin Christopher T.Latha Maheswari K. Sasikalarani Rajesh Sharma R Computer Science & Engineering Alliance university Bengaluru India Computer Science & Engineering Sri Krishna College of Engineering & Technology (Autonomous) Coimbatore India

ISBN: (数字)9798350383867

ISBN: (纸本)9798350383874

The car scratch detection is a pivotal aspect of automotive maintenance and safety, crucial for preserving the visual appeal and structural integrity of vehicle exteriors. This paper investigates contemporary methodologies and advancements in car scratch detection, emphasizing both conventional and computer vision-based techniques. By scrutinizing diverse approaches including image processing algorithms, machine learning models, and sensor-driven systems, this study elucidates the efficacy and constraints of existing methodologies while delineating prospective avenues for further research and development in the realm of car scratch detection. Additionally, the paper underscores the significance of real-time detection systems and the integration of advanced technologies such as artificial intelligence and deep learning to enhance the accuracy and efficiency of car scratch detection mechanisms, ultimately contributing to the longevity and aesthetic maintenance of automotive surfaces.

关键词： Visualization Machine learning algorithms Transfer learning real-time systems Maintenance Safety Automobiles Surface treatment Research and development Automotive engineering

来源：评论

学校读者我要写书评

暂无评论

Enhancing Passive Digital image Splicing Forensics Using Data-Efficient image Transformer and Lightweight Pretrained ShuffleNet-V2 Models - A Comparative Analysis

Enhancing Passive Digital Image Splicing Forensics Using Dat...

引用

Trends in Engineering Systems and Technologies (ICTEST), International Conference on

作者： Chithra Raj N. Maitreyee Dutta Jagriti Saini CSE Department NITTTR Chandigarh Chandigarh India IMEE Department NITTTR Chandigarh Chandigarh India Eternal RESTEM Chandigarh India

ISBN: (数字)9798350307795

ISBN: (纸本)9798350307801

An investigation into the challenge of detecting image splicing, a prevalent form of digital image manipulation, using advanced deep learning techniques is of paramount importance, owing to its serious legal implications in every realm of life. The study explores two models focused on passive image splicing forensics: the lightweight, pretrained ShuffleNet-V2 and the Data-efficient image Transformer (DeiT-Base). ShuffleNet-V2, known for its efficiency and speed, demonstrates a significant reduction of 3% in trainable parameters compared to the state-of-the-art method, making it ideal for real-time applications. DeiT-Base excels in complex image processing due to its superior computational and contextual analysis capabilities. Both models were tested using the Columbia dataset and showcased remarkable accuracy, with ShuffleNet-V2 achieving 94.44% and DeiT-Base 97.22%. They outperformed existing techniques, such as MobilePSP-Net, TransU2-Net by delivering 100% precision and specificity. The F1-score (0.9412 and 0.9714, respectively) and recall (88.89% and 94.44% respectively) also showed notable improvements, indicating these models' potential to enhance image splicing detection methods. With this research's excellent outcomes, both models hold considerable promise in performance, as their distinct approaches provide valuable perspectives for advancing image splicing detection methodologies.

关键词： deep learning Analytical models Splicing Digital images image processing Forensics Transformers

来源：评论

学校读者我要写书评

暂无评论

Implementing Practical DNN-Based Object Detection Offloading Decision for Maximizing Detection Performance of Mobile Edge Devices

引用

IEEE ACCESS 2021年 9卷 140199-140211页

作者： Yoon, Giha Kim, Geun-Yong Yoo, Hark Kim, Sung Chang Kim, Ryangsoo Elect & Telecommun Res Inst ETRI Honam Res Ctr HRC Gwangju 61012 South Korea

In the last decade, deep neural network (DNN)-based object detection technologies have received significant attention as a promising solution to implement a variety of image understanding and video analysis applications on mobile edge devices. However, the execution of computationally intensive DNN-based object detection workloads in mobile edge devices is insufficient in fulfilling the object detection requirements with high accuracy and low latency, owing to the limited computation capacity. In this paper, we implement and evaluate a DNN-based object detection offloading framework to improve the object detection performance of mobile edge devices by offloading computation-intensive workloads to a remote edge server. However, preliminary experimental results have shown that offloading all object detection workloads of mobile edge devices may lead to worse performance than executing the workloads locally. This degradation is obtained from the inefficient resource utilization in the edge computing architectures, both for the edge server and mobile edge devices. To resolve the aforementioned problem with degradation, we devise a device-aware DNN offloading decision algorithm that is aimed to maximize resource utilization in the edge computing architecture. The proposed algorithm decides whether or not to offload the object detection workloads of edge devices by considering their computing power and network bandwidth, and therefore maximizing their average object detection processing frames per second. Through various experiments conducted in a real-life wireless local area network (WLAN) environment, we verified the effectiveness of the proposed DNN-based object detection offloading framework.

关键词： image edge detection Object detection Servers Wireless LAN deep learning Performance evaluation Edge computing deep learning offloading object detection wireless edge computing resource optimization

来源：评论

学校读者我要写书评

暂无评论

Evolution of automatic visual description techniques-a methodological survey

引用

MULtimeDIA TOOLS AND APPLICATIONS 2021年第18期80卷 28015-28059页

作者： Bhowmik, Arka Kumar, Sanjay Bhat, Neeraj Delhi Technol Univ Dept Comp Sci & Engn Main Bawana Rd New Delhi 110042 India

Describing the contents and activities in an image or video in semantically and syntactically correct sentences are known as captioning. Automated captioning is one of the most researched topics these days, with new sophisticated models being discovered every day. Captioning models require intense training and perform intense, complex calculations before successfully generating a caption and hence, takes a considerable amount of time even in machines with high specifications. In this survey, we go through the recent state-of-the-art advancements in automatic image and video description methodologies using deep neural networks and summarize the concepts inferred from them. The summarization has been done with a systematic, detailed, and critical analysis of the latest methodologies published in high impact proceedings and journals. Our investigation focuses on techniques that can optimize existing concepts and incorporate new methods of visual attention for generating captions. This survey emphasizes on the importance of applicability and effectiveness of existing works in real-life applications and highlights those computationally feasible and optimized techniques which can be supported in multiple devices, including lightweight devices like smartphones. Furthermore, we propose possible improvements and model architecture to support online video captioning.

关键词： image captioning Video captioning Activity recognition deep learning Convolutional neural networks Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

deep Edge Computing for Videos

引用

IEEE ACCESS 2021年 9卷 123348-123357页

作者： Kim, Jun-Hwa Kim, Namho Won, Chee Sun Dongguk Univ Dept Elect & Elect Engn Seoul 04620 South Korea

This paper provides a modular architecture with deep neural networks as a solution for real-time video analytics in an edge-computing environment. The modular architecture consists of two networks of Front-CNN (Convolutional Neural Network) and Back-CNN, where we adopt Shallow 3D CNN (S3D) as the Front-CNN and a pre-trained 2D CNN as the Back-CNN. The S3D (i.e., the Front CNN) is in charge of condensing a sequence of video frames into a feature map with three channels. That is, the S3D takes a set of sequential frames in the video shot as input and yields a learned 3 channel feature map (3CFM) as output. Since the 3CFM is compatible with the three-channel RGB color image format, we can use the output of the S3D (i.e., the 3CFM) as the input to a pre-trained 2D CNN of the Back-CNN for the transfer-learning. This serial connection of Front-CNN and Back-CNN architecture is end-to-end trainable to learn both spatial and temporal information of videos. Experimental results on the public datasets of UCF-Crime and UR-Fall Detection show that the proposed S3D-2DCNN model outperforms the existing methods and achieves state-of-the-art performance. Moreover, since our Front-CNN and Back-CNN modules have a shallow S3D and a light-weighted 2D CNN, respectively, it is suitable for real-time video recognition in edge-computing environments. We have implemented our CNN model on NVIDIA Jetson Nano Developer as an edge-computing device to show its real-time execution.

关键词： Convolutional neural networks Three-dimensional displays Streaming media Cameras Optical imaging image edge detection Optical computing Edge computing CNN the IoT anomaly detection video recognition

来源：评论

学校读者我要写书评

暂无评论

Super-Resolution Ultrasound Localization Microscopy Through deep learning

引用

IEEE TRANSACTIONS ON MEDICAL IMAGING 2021年第3期40卷 829-839页

作者： van Sloun, Ruud J. G. Solomon, Oren Bruce, Matthew Khaing, Zin Z. Wijkstra, Hessel Eldar, Yonina C. Mischi, Massimo Eindhoven Univ Technol Dept Elect Engn NL-5612 AZ Eindhoven Netherlands Techion Israel Inst Technol Dept Elect Engn IL-3200003 Haifa Israel Univ Minnesota Ctr Magnet Resonance Res Dept Radiol Minneapolis MN 55455 USA Univ Washington Appl Phys Lab Seattle WA 98195 USA Univ Washington Dept Neurol Surg Seattle WA 98195 USA Univ Amsterdam Acad Med Ctr Dept Urol NL-1012 WX Amsterdam Netherlands Weizmann Inst Sci Fac Math & Comp Sci IL-7610001 Rehovot Israel

Ultrasound localization microscopy has enabled super-resolution vascular imaging through precise localization of individual ultrasound contrast agents (microbubbles) across numerous imaging frames. However, analysis of high-density regions with significant overlaps among the microbubble point spread responses yields high localization errors, constraining the technique to low-concentration conditions. As such, long acquisition times are required to sufficiently cover the vascular bed. In this work, we present a fast and precise method for obtaining super-resolution vascular images from high-density contrast-enhanced ultrasound imaging data. This method, which we term deep Ultrasound Localization Microscopy (deep-ULM), exploits modern deep learning strategies and employs a convolutional neural network to perform localization microscopy in dense scenarios, learning the nonlinear image-domain implications of overlapping RF signals originating from such sets of closely spaced microbubbles. deep-ULM is trained effectively using realistic on-line synthesized data, enabling robust inference in-vivo under a wide variety of imaging conditions. We show that deep learning attains super-resolution with challenging contrast-agent densities, both in-silico as well as in-vivo. deep-ULM is suitable for real-time applications, resolving about 70 high-resolution patches (128 x 128 pixels) per second on a standard PC. Exploiting GPU computation, this number increases to 1250 patches per second.

关键词： Ultrasound deep learning super resolution ultrasound localization microscopy neural network

来源：评论

学校读者我要写书评

暂无评论

Determining Top Fully Connected Layer's Hidden Neuron Count for Transfer learning, Using Knowledge Distillation: a Case Study on Chest X-Ray Classification of Pneumonia and COVID-19

引用

JOURNAL OF DIGITAL IMAGING 2021年第6期34卷 1349-1358页

作者： Ghosh, Ritwick Indian Inst Engn Sci & Technol Dept Min Engn Howrah 711103 W Bengal India

deep convolutional neural network (CNN)-assisted classification of images is one of the most discussed topics in recent years. Continuously innovation of neural network architectures is making it more correct and efficient every day. But training a neural network from scratch is very time-consuming and requires a lot of sophisticated computational equipment and power. So, using some pre-trained neural network as feature extractor for any image classification task or "transfer learning" is a very popular approach that saves time and computational power for practical use of CNNs. In this paper, an efficient way of building full model from any pre-trained model with high accuracy and low memory is proposed using knowledge distillation. Using the distilled knowledge of the last layer of pre-trained networks passes through fully connected layers with different hidden layers, followed by Softmax layer. The accuracies of student networks are mildly lesser than the whole models, but accuracy of student models clearly indicates the accuracy of the real network. In this way, the best number of hidden layers for dense layer for that pre-trained network with best accuracy and no-overfitting can be found with less time. Here, VGG16 and VGG19 (pre-trained upon "imageNet" dataset) is tested upon chest X-rays (pneumonia and COVID-19). For finding the best total number of hidden layers, it saves nearly 44 min for VGG19 and 36 min and 37 s for VGG16 feature extractor.

关键词： deep learning COVID-19 Pneumonia Chest X-ray Medical imaging Knowledge distillation Transfer learning image classification

来源：评论

学校读者我要写书评

暂无评论

Applying deep learning to real-time UAV-based forest monitoring: Leveraging multi-sensor imagery for improved results

引用

EXPERT SYSTEMS WITH APPLICATIONS 2024年 245卷

作者： Marques, Tomas Carreira, Samuel Miragaia, Rolando Ramos, Joao Pereira, Antonio Polytech Leiria Comp Sci & Commun Res Ctr Sch Technol & Management Morro Lena Alto VieiroApartado 4163 P-2411901 Leiria Portugal Inst New Technol Leiria INOV INESC INNOVAT Morro Lena Alto VieiroApartado 4163 P-2411901 Leiria Portugal

Rising global fire incidents necessitate effective solutions, with forest surveillance emerging as a crucial strategy. This paper proposes a complete solution using technology that integrates visible and infrared spectrum images through Unmanned Aerial Vehicles (UAVs) for enhanced detection of people and vehicles in forest environments. Unlike existing computer vision models relying on single-sensor imagery, this approach overcomes limitations posed by limited spectrum coverage, particularly addressing challenges in low-light conditions, fog, or smoke. The developed 4-channel model uses both types of images to take advantage of the strengths of each one simultaneously. This article presents the development and implementation of a solution for forest monitoring ranging from the transmission of images captured by a UAV to their analysis with an object detection model without human intervention. This model consists of a new version of the YOLOv5 (You Only Look Once) architecture. After the model analyzes the images, the results can be observed on a web platform on any device, anywhere in the world. For the model training, a dataset with thermal and visible images from the aerial perspective was captured with a UAV. From the development of this proposal, a new 4channel model was created, presenting a substantial increase in precision and mAP (Mean Average Precision) metrics compared to traditional SOTA (state-of-the-art) models that only make use of red, green, and blue (RGB) images. Allied with the increase in precision, we confirmed the hypothesis that our model would perform better in conditions unfavorable to RGB images, identifying objects in situations with low light and reduced visibility with partial occlusions. With the model's training using our dataset, we observed a significant increase in the model's performance for images in the aerial perspective. This study introduces a modular system architecture featuring key modules: multisensor image capture, transmi

关键词： deep learning Computer vision image fusion Object detection real-time Unmanned Aerial Vehicle

来源：评论

学校读者我要写书评

暂无评论

Layer-wise multi-defect detection for laser powder bed fusion using deep learning algorithm with visual explanation

引用

OPTICS AND LASER TECHNOLOGY 2024年 174卷

作者： Zhao, Yingjian Ren, Hang Zhang, Yuhui Wang, Chengyun Long, Yu Guangxi Univ Inst Laser Intelligent Mfg & Precis Proc Sch Mech Engn Nanning 530004 Guangxi Peoples R China Cent South Univ Coll Mech & Elect Engn Changsha 410083 Hunan Peoples R China Cent South Univ State Key Lab Precis Mfg Extreme Serv Performance Changsha 410083 Hunan Peoples R China

In Laser Powder Bed Fusion (LPBF), it is a major challenge to obtain detailed spatial information on different powder bed defects in real-time and simultaneously. deep learning (DL) algorithms under the field of Machine learning (ML) have promoted the intelligent development of the powder bed defect detection method. However, they still need to be further evaluated in terms of detection accuracy and time delay, training data overhead, and model robustness under complex environments. Also, the DL model usually treated as a black-box demands further explanation. Herein, three advanced DL models are constructed using bounding boxes to locate multidefects quickly and accurately for the powder spreading of LPBF. High detection accuracy is achieved with limited training samples through both data augmentation aiming at expanding image samples and model-based Transfer learning (TL) used for transferring from the source domain to the target domain by reusing trained models. Further, the data augmentation method is employed to generate low-resolution images with interference to test the robustness of the detection model in harsh environments. Besides, visual feature maps and saliency maps were generated with the Detector Randomized Input Sampling for Explanation (D-RISE) method to help understand the validity of the defect detection process of the DL model. Overall, this work shows that the proposed multi-defect detection algorithms can provide comprehensive information on powder bed defects accurately and quickly.

关键词： Laser powder bed fusion Process monitoring Defect detection deep learning

来源：评论

学校读者我要写书评

暂无评论

Lessons learned from the NeurIPS 2021 MetaDL challenge: Backbone fine-tuning without episodic meta-learning dominates for few-shot learning image classification 35

Lessons learned from the NeurIPS 2021 MetaDL challenge: Back...

引用

35th Conference on Neural Information processing Systems - Competitions and Demonstrations, NeurIPS 2021

作者： El Baz, Adrian Ullah, Ihsan Alcobaça, Edesio Carvalho, André C.P.L.F. Chen, Hong Ferreira, Fabio Gouk, Henry Guan, Chaoyu Guyon, Isabelle Hospedales, Timothy Hu, Shell Huisman, Mike Hutter, Frank Liu, Zhengying Mohr, Felix Öztürk, Ekrem van Rijn, Jan N. Sun, Haozhe Wang, Xin Zhu, Wenwu

Although deep neural networks are capable of achieving performance superior to humans on various tasks, they are notorious for requiring large amounts of data and computing resources, restricting their success to domains where such resources are available. Metalearning methods can address this problem by transferring knowledge from related tasks, thus reducing the amount of data and computing resources needed to learn new tasks. We organize the MetaDL competition series, which provide opportunities for research groups all over the world to create and experimentally assess new meta-(deep)learning solutions for real problems. In this paper, authored collaboratively between the competition organizers and the top-ranked participants, we describe the design of the competition, the datasets, the best experimental results, as well as the top-ranked methods in the NeurIPS 2021 challenge, which attracted 15 active teams who made it to the final phase (by outperforming the baseline), making over 100 code submissions during the feedback phase. The solutions of the top participants have been open-sourced. The lessons learned include that learning good representations is essential for effective transfer learning. © 2022 A. El Baz et al.

关键词： image classification

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：