检索结果-内蒙古大学图书馆

Novel hybrid object-based non-parametric clustering approach for grouping similar objects in specific visual domains

引用

APPLIED SOFT COMPUTING 2018年 62卷 667-701页

作者： Kuru, Kaya Khan, Wasiq Univ Cent Lancashire Sch Engn Preston PR1 2HE Lancs England Manchester Metropolitan Univ Sch Comp Math & Digital Technol Manchester M15 6BH Lancs England

Current widely employed clustering approaches may not yield satisfactory results with regard to the characteristics and distribution of datasets and number of clusters to be sought, especially for visual domains in multidimensional space. This study establishes a novel clustering methodology using a pair-wise similarity matrix, Clustering visual objects in Pairwise Similarity Matrix (CVOIPSM), for grouping similar objects in specific visual domains. A dimensionality reduction and feature extraction technique, along with a distance measuring method and a newly established algorithm, Clustering in Pairwise Similarity Matrix (CIPSM), are combined to develop the CVOIPSM methodology. CIPSM utilizes both Rk-means and an agglomerative, contractible, expandable (ACE) technique to calculate a membership degree based on maximizing inter-class similarity and minimizing intra-class similarity. CVOIPSM has been tested on several datasets, with average success rates on downsized subsamples between 87.5% and 97.75% and between 81% and 87% on the larger datasets. The difference in the success rates for small and large datasets is not statistically significant (p > 0.01). Moreover, this method automatically determines the likely number of clusters without any user dictation. The empirical results and the statistical significancet est on these results ensure that CVOIPSM performs effectively and efficiently on specific visual domains, disclosing the interrelated patterns of similarities among objects. (C) 2017 Elsevier B.V. All rights reserved.

关键词： Cluster analysis visual object detection Feature extraction Image processing Pairwise similarity comparison Nonparametric clusteringa

来源：评论

学校读者我要写书评

暂无评论

Fruit ripeness identification using YOLOv8 model

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2024年第9期83卷 28039-28056页

作者： Xiao, Bingjie Nguyen, Minh Yan, Wei Qi Auckland Univ Technol Auckland 1010 New Zealand

Deep learning-based visual object detection is a fundamental aspect of computer vision. These models not only locate and classify multiple objects within an image, but they also identify bounding boxes. The focus of this paper's research work is to classify fruits as ripe or overripe using digital images. Our proposed model extracts visual features from fruit images and analyzes fruit peel characteristics to predict the fruit's class. We utilize our own datasets to train two "anchor-free" models: YOLOv8 and CenterNet, aiming to produce accurate predictions. The CenterNet network primarily incorporates ResNet-50 and employs the deconvolution module DeConv for feature map upsampling. The final three branches of convolutional neural networks are applied to predict the heatmap. The YOLOv8 model leverages CSP and C2f modules for lightweight processing. After analyzing and comparing the two models, we found that the C2f module of the YOLOv8 model significantly enhances classification results, achieving an impressive accuracy rate of 99.5%.

关键词： YOLOv8 CenterNet visual object detection

来源：评论

学校读者我要写书评

暂无评论

Scalable greedy algorithms for transfer learning

引用

COMPUTER VISION AND IMAGE UNDERSTANDING 2017年 156卷 174-185页

作者： Kuzborskij, Ilja Orabona, Francesco Caputo, Barbara Ctr Parc Idiap Res Inst Rue Marconi 19 CH-1920 Martigny Switzerland Ecole Polytech Federate Lausanne EPFL Lausanne Switzerland SUNY Stony Brook Dept Comp Sci Stony Brook NY 11794 USA Univ Roma La Sapienza Dept Comp Control & Management Engn Rome Italy

In this paper we consider the binary transfer learning problem, focusing on how to select and combine sources from a large pool to yield a good performance on a target task. Constraining our scenario to real world, we do not assume the direct access to the source data, but rather we employ the source hypotheses trained from them. We propose an efficient algorithm that selects relevant source hypotheses and feature dimensions simultaneously, building on the literature on the best subset selection problem. Our algorithm achieves state-of-the-art results on three computer vision datasets, substantially outperforming both transfer learning and popular feature selection baselines in a small-sample setting. We also present a randomized variant that achieves the same results with the computational cost independent from the number of source hypotheses and feature dimensions. Also, we theoretically prove that, under reasonable assumptions on the source hypotheses, our algorithm can learn effectively from few examples. (C) 2016 Elsevier Inc. All rights reserved.

关键词： Transfer learning Domain adaptation visual object detection Greedy algorithms Feature selection

来源：评论

学校读者我要写书评

暂无评论

Enhanced Small Drone detection Using Optimized YOLOv8 With Attention Mechanisms

引用

IEEE ACCESS 2024年 12卷 90629-90643页

作者： Zamri, Fatin Najihah Muhamad Gunawan, Teddy Surya Yusoff, Siti Hajar Alzahrani, Ahmad A. Bramantoro, Arif Kartiwi, Mira Int Islamic Univ Malaysia Dept Elect & Comp Engn Kuala Lumpur 53100 Malaysia King Abdulaziz Univ Fac Comp & Informat Technol Jeddah 21589 Saudi Arabia Univ Teknol Brunei Sch Comp & Informat Bandar Seri Begawan 1410 Brunei Int Islamic Univ Malaysia Dept Informat Syst Kuala Lumpur 53100 Malaysia

The increasing misuse of drones poses significant safety and security risks, including illegal transportation of prohibited goods, interference with manned aircraft, and threats to public safety. This has raised concerns about the increased use of unmanned aerial vehicles (UAVs) due to their small size. Addressing these concerns has sparked significant research into developing effective drone detection systems. Deep learning, especially YOLO, is known as a lightweight model that offers real-time detection capabilities. Attention mechanisms have proven effective in many studies for detecting objects. This research focused on optimizing the YOLOv8n-based model by incorporating the Attention Module into the neck and improving the detection head by adding a tiny detection head, making the model work efficiently in detecting objects of tiny size. To obtain the most effective model, multiple training sets have been experimented with involving different types of attention modules, such as the Convolutional Block Attention Module (CBAM), ResBlock CBAM, Global Attention Mechanism (GAM), and Efficient Channel Attention (ECA). Therefore, based on the results, YOLOv8n + ResCBAM + high-resolution detection head, called P2-YOLOv8n-ResCBAM significantly improves the mean Average Accuracy (mAP) from 90.3% to 92.6%. Although the increased model complexity reduced frames per second (fps) from 263 to 166, the detection speed remains suitable for real-time applications. The proposed model effectively distinguishes drones from birds and recognizes them at long distances, demonstrating its potential for enhancing aerial surveillance and security measures.

关键词： Drones YOLO Training Feature extraction Accuracy Neck Artificial intelligence Deep learning Convolutional neural networks Real-time systems Surveillance Autonomous aerial vehicles object detection deep learning convolutional neural networks small drone detection YOLOv8 attention mechanism visual object detection real-time detection aerial surveillance autonomous systems

来源：评论

学校读者我要写书评

暂无评论

Fruit ripeness identification using transformers

引用

APPLIED INTELLIGENCE 2023年第19期53卷 22488-22499页

作者： Xiao, Bingjie Nguyen, Minh Yan, Wei Qi Auckland Univ Technol Auckland 1010 New Zealand

Pattern classification has always been essential in computer vision. Transformer paradigm having attention mechanism with global receptive field in computer vision improves the efficiency and effectiveness of visual object detection and recognition. The primary purpose of this article is to achieve the accurate ripeness classification of various types of fruits. We create fruit datasets to train, test, and evaluate multiple Transformer models. Transformers are fundamentally composed of encoding and decoding procedures. The encoder is to stack the blocks, like convolutional neural networks (CNN or ConvNet). Vision Transformer (ViT), Swin Transformer, and multilayer perceptron (MLP) are considered in this paper. We examine the advantages of these three models for accurately analyzing fruit ripeness. We find that Swin Transformer achieves more significant outcomes than ViT Transformer for both pears and apples from our dataset.

关键词： visual object detection Vision Transformer Swin Transformer Mask R-CNN MLP

来源：评论

学校读者我要写书评

暂无评论

A Gabor Wavelet Pyramid-Based object detection Algorithm

A Gabor Wavelet Pyramid-Based Object Detection Algorithm

引用

8th International Symposium on Neural Networks

作者： Sato, Yasuomi D. Jitsev, Jenia Bornschein, Joerg Pamplona, Daniela Keck, Christian von der Malsburg, Christoph Kyushu Inst Technol Grad Sch Life Sci & Syst Engn Dept Brain Sci & Engn 2-4 Hibikino Kitakyushu Fukuoka 8080196 Japan Goethe Univ Frankfurt FIAS D-60438 Frankfurt Germany Max Planck Inst Neurol Res Gleueler Str 50 D-50931 Cologne Germany

ISBN: (纸本)9783642210891

We introduce visual object detection architecture, making full use of technical merits of so-called multi-scale feature correspondence in the neurally inspired Gabor pyramid. The remarkable property of the multi-scale Gabor feature correspondence is found with scale-space approaches, which an original image Gabor-filtered with the individual frequency levels is approximated to the correspondingly sub-sampled image smoothed with the low-pass filter. The multi-scale feature correspondence is used for effectively reducing computational costs in filtering. In particular, we show that the multi-scale Gabor feature correspondence play an effective role in matching between an input image and the model representation for object detection.

关键词： Gabor Pyramid visual object detection Multi-scale Feature Correspondence Computer Vision

来源：评论

学校读者我要写书评

暂无评论

Sailboat detection Based on Automated Search Attention Mechanism and Deep Learning Models 36

Sailboat Detection Based on Automated Search Attention Mecha...

引用

36th International Conference on Image and Vision Computing New Zealand (IVCNZ)

作者： Luo, Ziyuan Minh Nguyen Yan, Wei Qi Auckland Univ Technol Sch Engn Comp & Math Sci Auckland 1010 New Zealand

ISBN: (纸本)9781665406451

The development of deep learning-based visual object recognition has achived great progress in recent years. Deep learning models based on attention mechanisms are able to further improve the ability to detect the regions of interest (ROI), but creating an appropriate module is a difficult task. Therefore, in this paper, we propose an automated design scheme based on neural architecture search (NAS) to migrate the attention mechanism for visual object detection and obtain better results of sailboat detection by using both public datasets and our own collected datasets. We verify the effectiveness of our proffered method and evaluate the performance compared with other algorithms. The obtained results have demonstrated better robustness in terms of generalization than other deep learning models.

关键词： Deep learning attention automated machine learning CNN visual object detection

来源：评论

学校读者我要写书评

暂无评论

Feature Selection for object detection: The Best Group vs. the Group of Best 37th

Feature Selection for Object Detection: The Best Group vs. t...

引用

37th International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO)

作者： Fuerst, Luka Leonardis, Ales Univ Ljubljana Fac Comp & Informat Sci SI-1000 Ljubljana Slovenia

ISBN: (纸本)9789532330816

The problem of visual object detection, the goal of which is to predict the locations and sizes of all objects of a given visual category (e. g., cars) in a given set of images, is often based on a possibly large set of local features, only a few of which might actually be useful for the given detection setup. Feature selection is concerned with finding a 'useful' subset of features. In this paper, we compare two approaches to feature selection in a visual object detection setup. One of them selects features based on their individual utility scores alone, regardless of possible interdependence with other features. The other approach employs the AdaBoost framework and hence implicitly deals with interdependence. Using two feature extraction methods and several image datasets, we experimentally confirm the significance of feature interdependence: features that perform well individually do not necessarily perform well as a group.

关键词： feature extraction learning (artificial intelligence) object detection AdaBoost framework detection setup feature extraction methods feature selection image datasets individual utility scores visual category visual object detection visual object detection setup detection algorithms Educational institutions Feature extraction Image segmentation object detection Training visualization Feature extraction visualization image segmentation object detection Functional training detection algorithms Educational institutions

来源：评论

学校读者我要写书评

暂无评论

Large Scale Audio-visual Video Analytics Platform for Forensic Investigations of Terroristic Attacks 25th

Large Scale Audio-Visual Video Analytics Platform for Forens...

引用

25th International Conference on MultiMedia Modeling (MMM)

作者： Schindler, Alexander Boyer, Martin Lindley, Andrew Schreiber, David Philipp, Thomas AIT Austrian Inst Technol GmbH Ctr Digital Safety & Secur A-1210 Vienna Austria LIquA Linzer Inst Qualitat Anal A-4020 Linz Austria

ISBN: (纸本)9783030057169;9783030057152

The forensic investigation of a terrorist attack poses a huge challenge to the investigative authorities, as several thousand hours of video footage need to be spotted. To assist law enforcement agencies (LEA) in identifying suspects and securing evidences, we present a platform which fuses information of surveillance cameras and video uploads from eyewitnesses. The platform integrates analytical modules for different input-modalities on a scalable architecture. Videos are analyzed according their acoustic and visual content. Specifically, Audio Event detection is applied to index the content according to attack-specific acoustic concepts. Audio similarity search is utilized to identify similar video sequences recorded from different perspectives. visual object detection and tracking are used to index the content according to relevant concepts. The heterogeneous results of the analytical modules are fused into a distributed index of visual and acoustic concepts to facilitate rapid start of investigations, following traits and investigating witness reports.

关键词： Audio event detection Audio similarity visual object detection Large scale computing Ethics of security Ethics of technology

来源：评论

学校读者我要写书评

暂无评论

visual detection of objects by Mobile Agents using CBVIR Techniques of Low Complexity

Visual Detection of Objects by Mobile Agents using CBVIR Tec...

引用

3rd International Conference on Innovative Network Systems and Applications (iNetSApp) held in conjunction with Federated Conference on Computer Science and Information Systems (FedCSIS)

作者： Sluzek, Andrzej Khalifa Univ Abu Dhabi CampusPOB 127788 Abu Dhabi U Arab Emirates

ISBN: (纸本)9788360810668

visual search for objects of interest in complex environment is an important (and still challenging) problem in mobile robotics. In particular, the usage of content-based visual information retrieval (CBVIR) methods, which are a natural choice for such tasks, is often constrained by the real-time requirements, and the mobility of searching agents is sometimes not sufficiently exploited in the search model. In this paper, a CBVIR-based scheme is proposed, which takes into account motion of the searching agents to achieve a low-cost and highspeed detection of objects of interest in cluttered scenes, with good overall performances. We combine standard CBVIR tools, i.e. MSER detector and SIFT descriptor (quantized into sufficiently large vocabularies) assuming additionally that objects become objects of interest only when approached closely enough by the mobile agent, i.e. when seen at an adequately large scale. Thus, an object of interest is considered detected only if a sufficient number of keypoints from the current video-frame are matched (including the corresponding matches of scales) to the keypoints from the database images of the object. Preliminary experiments on a limited-size dataset confirm performances of the scheme, although in the classical task of video-frame retrieval the scheme cannot compete with more sophisticated CBVIR algorithms. The scheme can prospectively become more flexible if combined with a range-finding device so that the approximate distances to the scene components within the currently inspected part of the image can be used to proportionally modify the scale correspondences.

关键词： content-based retrieval feature extraction image matching image sequences mobile agents mobile robots object detection robot vision transforms video retrieval CBVIR techniques CBVIR tools CBVIR-based scheme MSER detector SIFT descriptor content-based visual information retrieval methods high-speed object detection mobile robotics object image database range-finding device real-time requirements search model searching agent mobility video-frame matching video-frame retrieval visual object detection visual search Databases Mobile agents object detection Search problems Videos visualization Vocabulary

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：