检索结果-内蒙古大学图书馆

VSMCNN-dynamic summarization of videos using salient features from multi-CNN model

Journal of Ambient Intelligence and Humanized Computing 2023年第10期14卷 14071-14080页

作者： Nair, Madhu S. Mohan, Jesna Artificial Intelligence & Computer Vision Lab Department of Computer Science Cochin University of Science and Technology Kerala Kochi682022 India Department of Computer Science and Engineering Mar Baselios College of Engineering and Technology Nalanchira Kerala Thiruvananthapuram695015 India

A dynamic video summarization system detects key parts of the input video to generate its compact representation. The summaries can be used for efficient management of video data. This paper proposes an approach, Video summarization based on multi-CNN model (VSMCNN), that exploits major aspects of human cognition to generate meaningful summaries from videos. As the method focuses on dynamic summarization, the input video is divided into a set of shots. A multi-CNN model, which is a combination of different pre-trained models of CNN, is used for feature extraction from shots. The salient features are extracted from high dimensional feature vector using an unsupervised feature reduction technique applied in multiple subspaces to rank features in the vector. The distance measure between feature vectors is then thresholded to detect prime parts of the tested video. Experiments are performed on SumMe dataset and the results prove that our approach is successful in detecting portions of the tested video that has an essential message. The analysis shows that the method outperforms the state-of-the-art methods in the literature. Further evaluation on comparison with human-generated summaries in the ground truth proves the effectiveness of the proposed method. The paper also presents a detailed analysis to show which combination of pre-trained models of CNN is best suitable for generating dynamic summaries. © 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Video recording

来源：评论

学校读者我要写书评

暂无评论

Fire and Smoke Detection using an Enhanced YOLOv8 Model

Fire and Smoke Detection using an Enhanced YOLOv8 Model

引用

2024 IEEE International Conference on computer vision and Machine Intelligence, CVMI 2024

作者： Bohra, Bhavesh Kumar Rajesh, Bulla Javed, Mohammed Doermann, David Iiit Computer Vision and Biometrics Lab Department of It Allahabad India Iiit Sricity Department of Computer Science and Engineering India University at Buffalo Department of Computer Science and Engineering BuffaloNY United States

ISBN: (纸本)9798350376876

Due in part to global warming, the frequency of wildfires has increased in recent years, significantly impacting humans, wildlife, and forest ecosystems. To address this challenge, using technology for early fire detection through smoke can help firefighters and other stakeholders limit their spread and reduce the impact. In this research, we adopt the latest object detection model - YOLOv8 and use a fine-tuned version for detecting smoke and fire using the latest datasets. YOLOv8 backbone begins with two convolutional (Conv) layers, followed by a series of alternating Conv layers and C2F modules, and ends with a Spatial Pyramid Pooling - Fast (SPPF) module. Our improvement involves adding two extra Conv layers at the beginning of the backbone, between the alternating sequence of Conv and C2F layers. As the smoke and fire detection problem involves searching for smaller objects in the image, increasing the feature extraction layers improves the performance of smoke and fire detection. The fine-tuned model is tested with the FASDD v4 dataset, which depicts fire, smoke, non-fire, and non-smoke scenarios. © 2024 IEEE.

关键词： Premixed flames

来源：评论

学校读者我要写书评

暂无评论

Evaluation of OCT Image Synthesis for Choroidal and Retinal Layer Segmentation Using Denoising Diffusion Probabilistic Models

Evaluation of OCT Image Synthesis for Choroidal and Retinal ...

引用

18th International Joint Conference on Biomedical engineering Systems and Technologies, BIOSTEC 2025

作者： Yamauchi, Yudai Wu, Yuli Okada, Eiji Keio University Department of Electronics and Electrical Engineering Japan Institute of Imaging and Computer Vision RWTH Aachen University Germany

Machine learning can automatically conduct the layer segmentation task of retinal optical coherence tomog raphy (OCT) image, but annotated data is required to train these models. Synthetic retinal OCT images are generated using denoising diffusion probabilistic models (DDPMs), which can be used to train segmentation models effectively and automatically create annotated data. However, the extent to which these synthetic im ages contribute to segmentation accuracy compared to real data has not been investigated. In this study, we synthesized retinal OCT images from sketch images using DDPMs, trained a segmentation model using syn thetic and real images, and evaluated how the use of synthetic images influenced the accuracy of choroidal and retinal layer segmentation compared to results using only real images. Through a comparison of the Dice score, we confirmed that training with both synthetic and real OCT images led to higher Dice scores than train ing with only real OCT images. These findings suggest that using synthetic images can enhance segmentation accuracy, offering a promising approach to improving model performance in situations with limited annotated real data. © 2025 by SCITEPRESS– Science and Technology Publications, Lda.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Review of dehazing techniques: challenges and future trends

引用

Multimedia Tools and Applications 2025年第3期84卷 1103-1131页

作者： Ayoub, Abeer El-Shafai, Walid El-Samie, Fathi E. Abd Hamad, Ehab K. I. EL-Rabaie, El-Sayed M. Department of Electronics and Electrical Communication Engineering Faculty of Electronic Engineering Menoufia University Menouf32952 Egypt Security Engineering Lab Computer Science Department Prince Sultan University Riyadh11586 Saudi Arabia Department of Information Technology College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University Riyadh11671 Saudi Arabia Electrical Engineering Department Faculty of Engineering Aswan University Aswan81542 Egypt

The phenomenon of atmospheric haze arises due to the scattering of light by minute particles suspended in the atmosphere. This optical effect gives rise to visual degradation in images and videos. The degradation is primarily influenced by two key factors: atmospheric attenuation and scattered light. Scattered light causes an image to be veiled in a whitish veil, while attenuation diminishes the image inherent contrast. Efforts to enhance image and video quality necessitate the development of dehazing techniques capable of mitigating the adverse impact of haze. This scholarly endeavor presents a comprehensive survey of recent advancements in the domain of dehazing techniques, encompassing both conventional methodologies and those founded on machine learning principles. Traditional dehazing techniques leverage a haze model to deduce a dehazed rendition of an image or frame. In contrast, learning-based techniques employ sophisticated mechanisms such as Convolutional Neural Networks (CNNs) and different deep Generative Adversarial Networks (GANs) to create models that can discern dehazed representations by learning intricate parameters like transmission maps, atmospheric light conditions, or their combined effects. Furthermore, some learning-based approaches facilitate the direct generation of dehazed outputs from hazy inputs by assimilating the non-linear mapping between the two. This review study delves into a comprehensive examination of datasets utilized within learning-based dehazing methodologies, elucidating their characteristics and relevance. Furthermore, a systematic exposition of the merits and demerits inherent in distinct dehazing techniques is presented. The discourse culminates in the synthesis of the primary quandaries and challenges confronted by prevailing dehazing techniques. The assessment of dehazed image and frame quality is facilitated through the application of rigorous evaluation metrics, a discussion of which is incorporated. To provide empiri

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Low-Cost Real-World Benchmark Framework for Closed-Loop Robot Navigation Systems with SLAM

Low-Cost Real-World Benchmark Framework for Closed-Loop Robo...

引用

2024 IEEE Opportunity Research Scholars Symposium, ORSS 2024

作者： Cort, Carlton Dalal, Aditya De Ocampo, James Du, Yanwei Feng, Shiyu Vela, Patricio A. Intelligent Vision and Automation Lab Georgia Tech Institute for Robots and Intelligent Machines Georgia Tech School of Electrical and Computer Engineering United States

ISBN: (纸本)9798350390698

Simultaneous localization and mapping (SLAM) and navigation systems are pivotal to realizing autonomous robotic capabilities. Research toward these systems will have direct impacts on the already large and rapidly growing market of autonomous robotics. Typically, research efforts in SLAM and navigation isolate one of the two systems when benchmarking their performance. As such, potential confounding issues from integrating the full navigation stack with pose estimates from a SLAM algorithm, such as the compounded latency of both systems, never arise. This paper aims to remove this shortcoming by providing a cost-effective closed-loop benchmarking framework for several navigation stacks integrated with several SLAM algorithms on a physical platform (Turtlebot2 in an office environment). A frugal vision-based motion capture method is utilized to capture the localization data. The lessened cost of such a system removes the barriers to real-world testing of this type often presented by common expensive motion capture systems. In the benchmarking framework, conventional performance metrics for both SLAM and navigation research and novel metrics were collected to characterize the closed-loop performance. An analysis of these metrics will enable the selection of algorithms for real-world applications since the framework tests complete mobile autonomy stacks in a task-driven closed-loop environment. © 2024 IEEE.

关键词： SLAM robotics

来源：评论

学校读者我要写书评

暂无评论

A hypothetical comparative evaluation system for arctic indoors

引用

Frontiers of Architectural Research 2025年第1期14卷 210-223页

作者： Seyed-Amin Tabatabaeifard Jean-Francois Lalonde Marc Hebert Andre Potvin Claude MH.Demers GRAP(Groupe de Recherche en Ambiances Physiques) Ecole d’architectureUniversite LavalQuebecCanada Computer Vision and Systems Lab Department of Electrical and Computer EngineeringUniversite LavalQuebecCanada CERVO Brain Research Centre Faculty of MedicineUniversite LavalQuebecCanada

This research presents an innovative approach to evaluating indoor spaces,combining qualitative attributes with numerical architectural metrics. A hypothetical comparative visualization system is introduced, utilizing HDR visual imaging and thermal imaging in 360° field of view across multiple indoor environments. The study aims to provide architectsand occupants with a user-friendly tool informing them about the primary considerations oftheir built spaces, with a specific focus on indoor environmental qualities in remote Arctic regions. Key inquiries delve into the efficacy of the spherical approach and the capacity ofcomparative visualization to offer insights into space quality. Preliminary experiments contrastindoor environments in terms of circadian lighting, thermal uniformity, and view access tooutside in the 360° field of view (VAR360). The resulting visualizations hold significance inintroducing an immersive approach for depicting specific non-visible environmental qualities,particularly in relation to the window characteristics of spaces. It demonstrates the integration of multiple environmental variables, both steady-state and temporal, from central pointswithin spaces, providing a comprehensive view over their non-visible qualities. These resultsshould be useful for researchers and practitioners within building sciences, computer vision,and photobiology, showcasing an out-of-the-box approach for categorizing indoor spaces basedon standards and human-environmental qualifications.

关键词： Environmental assessment 360°imaging Comparative systems Low-cost tools Built environments

来源：评论

学校读者我要写书评

暂无评论

An Ensemble Technique for Classification of Oral Cancer by Using Histopathological Imaging 3rd

An Ensemble Technique for Classification of Oral Cancer by...

引用

3rd International Conference on Machine vision and Augmented Intelligence, MAI 2023

作者： Saikia, Trishna Dhamaniya, Ashutosh Gupta, Puneet Singh, Koushlendra Kumar Department of Computer Science and Engineering IIT Indore Indore India Machine Vision and Intelligence Lab NIT Jamshedpur Jamshedpur India

ISBN: (纸本)9789819743582

Oral cancer primarily affects the oral chamber within the head and neck area, and underscores the critical need for effective classification to initiate timely treatment. Deep learning (DL)-based computer-aided diagnostic (CAD) systems have demonstrated notable success in various applications, offering accurate and prompt diagnosis of oral squamous cell carcinomas (OSCC). One of the challenges in biomedical image classification is the acquisition of a sufficiently large training dataset. Transfer learning presents an efficient solution by extracting general features from natural image datasets and adapting them to new image datasets. In this study, we focus on classifying OSCC histopathology images to develop a productive DL-based CAD solution. To this end, we employ an average weighted ensemble technique, harnessing the strengths of deep learning-based models. To address the limitation of a small dataset, we fine-tune pre-trained deep CNN models, specifically VGG-16, VGG-19, MobileNet-V2, and Inception-V3, within our proposed method. Additionally, we conduct a comprehensive comparative analysis of these models, considering classification accuracy, precision, recall, and F-score as metrics. Our experimental findings reveal that VGG-19 consistently delivers substantially superior performance compared to the other fine-tuned deep CNN models. However, our proposed weighted ensemble technique outperforms all these deep CNN models, particularly when employing the RMSProp optimizer. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Ensemble Histopathological imaging Inception-V3 MobileNet-V2 OSCC Transfer learning VGG-16 VGG-19

来源：评论

学校读者我要写书评

暂无评论

Psycho Acoustic Testing to Determine the Optimal Frequency for Audible Safety Alerts for Freediving

Psycho Acoustic Testing to Determine the Optimal Frequency f...

引用

2024 Systems and Information engineering Design Symposium, SIEDS 2024

作者： Nanda, Arnav Zoraiz, Mohammad Barua, Dhruva Mohamed, Raghad Duke Pratt School of Engineering Department of Electrical and Computer Engineering Duke Marine Lab United States

ISBN: (纸本)9798350385144

Freediving is a captivating sport that involves diving underwater on a single breath, pushing the boundaries of human capability and exploring the depths of the ocean with minimal equipment. While free diving offers a unique and thrilling underwater experience, it also poses several difficulties. Having been in the water for long periods, many divers can develop hypoxia or decompression sickness. To solve this issue many divers use watches that allow them to monitor the heart rate, oxygen levels, and depth levels. Most of these watches can track and monitor vital signs and warn in case of potential harm or risk to the diver. While these watches are helpful, they are not preventative and many divers have passed away due to oxygen-related issues, decompression sickness, and a myriad of other problems. This project aims to address these problems and improve upon current products produced by Garmin Inc. Duke's EGR102 team's goal is to create an effective data collection and signal analysis algorithm dedicated for efficiently analyzing data regarding different pitches, timbers, and audible tones at varying depths of water. More importantly, the product should be able to stay underwater at 6 meters depth for more than an hour. © 2024 IEEE.

关键词： Oxygen

来源：评论

学校读者我要写书评

暂无评论

Optimization of 5G Antenna Using Machine Learning 5

Optimization of 5G Antenna Using Machine Learning

引用

5th IEEE Middle East and North Africa COMMunications Conference, MENACOMM 2025

作者： Hassan, Aline Sharanek, Aya Hamzeh, Rayan Serhal, Dina Zantout, Rached American University of Beirut Electrical and Computer Engineering Department Beirut Lebanon Rafik Hariri University Electrical and Computer Engineering Department Mechref Lebanon EFREI Paris EFREI Research Lab Paris France

ISBN: (纸本)9798331519957

This paper presents a machine learning (ML)-based approach to optimize 5G base station patch antennas operating in the 3.3-4.2 GHz range. Traditional antenna design methods are often complex and time-consuming, particularly as the demand for high-speed communication is increasing, motivating the use of ML. Due to the lack of existing data for training the ML models, a custom dataset was created to be used in training and testing of the ML models. The optimized antenna achieved a return loss less than-10 dB and a resonant frequency of 3.5 GHz. An array of the optimized antennas was also designed and analyzed for base station applications. To select the best ML model, the project involved training and testing various models. Random Forest was identified as the best model for the single antenna, while Random Tree performed best for the antenna array. © 2025 IEEE.

关键词： Slot antennas

来源：评论

学校读者我要写书评

暂无评论

CRLB-based Data-driven Covariance Tuning for 5G KF Vehicular Tracking

CRLB-based Data-driven Covariance Tuning for 5G KF Vehicular...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Bader, Qamar Saleh, Sharief Noureldin, Aboelmagd Chalmers University of Technology Department of Electrical Engineering Gothenburg Sweden Queen's University Department of Electrical and Computer Engineering KingstonON Canada Research Lab Gothenburg Sweden Royal Military College of Canada Department of Electrical and Computer Engineering KingstonON Canada

ISBN: (纸本)9798350351255

5G mmWave offers a high-precision positioning solution, functioning effectively in both line-of-sight (LoS) and operable non-line-of-sight (NLoS) conditions. However, in scenarios with complete signal blockage, integrating with motion-based models becomes crucial. This integration is achieved through Bayesian-based estimators, which entail a prediction and a correction stage weighted by their respective covariance matrices. Although covariance matrices of different prediction models have been extensively studied in the literature, the measurement covariance matrix derived from 5G-based position computations remains largely unexplored. In this paper, we propose a measurement covariance matrix tuning scheme based on a data-driven Cramér-Rao lower bound CRLB model. We validate the proposed algorithm within a simple linear Kalman filter (LKF) positioning framework. The methodology was tested in a controlled simulation scenario using a real 24-minute-long vehicular trajectory in a deep-urban environment. The results demonstrate that the developed data-driven model is reliable, maintaining a standard deviation error of less than 7 cm for 95% of the time and less than 0.5 m for 100% of the time relative to the true computed CRLB. The proposed adaptive KF sustains a position error below 30 cm for 99.3% of the time. © 2024 IEEE.

关键词： Kalman filters

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：