检索结果-内蒙古大学图书馆

Spectral methods for view-based 3-D object recognition using silhouettes 9th

Joint IAPR 9th International Workshop on Structural and Syntactic Pattern Recognition, SSPR 2002 and 4th International Workshop on Statistical Techniques in Pattern Recognition, SPR 2002

作者： Macrini, Diego Shokoufandeh, Ali Dickinson, Sven Siddiqi, Kaleem Zucker, Steven Department of Computer Science University of Toronto Canada Department of Mathematics and Computer Science Drexel University United States Department of Computer Science University of Toronto Canada Centre for Intelligent Machines School of Computer Science McGill University Canada Center for Computational Vision and Control Yale University United States

ISBN: (纸本)3540440119

The shockg raph is an emerging shape representation for object recognition, in which a 2-D silhouette is decomposed into a set of qualitative parts, captured in a directed acyclic graph. Although a number of approaches have been proposed for shockgrap h matching, these approaches do not address the equally important indexing problem. We extend our previous workin both shockgrap h matching and hierarchical structure indexing to propose the first unified frameworkf or view-based 3-D object recognition using shockgrap hs. The heart of the framework is an improved spectral characterization of shockgrap h structure that not only drives a powerful indexing mechanism (to retrieve similar candidates from a large database), but also drives a matching algorithm that can accommodate noise and occlusion. We describe the components of our system and evaluate its performance using both unoccluded and occluded queries. The large set of recognition trials (over 25,000) from a large database (over 1400 views) represents one of the most ambitious shockg raph-based recognition experiments conducted to date. This paper represents an expanded version of [12]. © Springer-Verlag Berlin Heidelberg 2002.

关键词： Directed graphs

来源：评论

学校读者我要写书评

暂无评论

PointPillars Backbone Type Selection for Fast and Accurate LiDAR Object Detection

PointPillars Backbone Type Selection for Fast and Accurate L...

引用

International Conference on computer vision and Graphics, ICCVG 2022

作者： Lis, Konrad Kryjak, Tomasz Embedded Vision Systems Group Computer Vision Laboratory Department of Automatic Control and Robotics AGH University of Science and Technology Al. Mickiewicza 30 Krakow30-059 Poland

ISBN: (纸本)9783031220241

3D object detection from LiDAR sensor data is an important topic in the context of autonomous cars and drones. In this paper, we present the results of experiments on the impact of backbone selection of a deep convolutional neural network on detection accuracy and computation speed. We chose the PointPillars network, which is characterised by a simple architecture, high speed, and modularity that allows for easy expansion. During the experiments, we paid particular attention to the change in detection efficiency (measured by the mAP metric) and the total number of multiply-addition operations needed to process one point cloud. We tested 10 different convolutional neural network architectures that are widely used in image-based detection problems. For a backbone like MobilenetV1, we obtained an almost 4x speedup at the cost of a 1.13% decrease in mAP. On the other hand, for CSPDarknet we got an acceleration of more than 1.5x at an increase in mAP of 0.33%. We have thus demonstrated that it is possible to significantly speed up a 3D object detector in LiDAR point clouds with a small decrease in detection efficiency. This result can be used when PointPillars or similar algorithms are implemented in embedded systems, including SoC FPGAs. The code is available at https://***/vision-agh/pointpillars-backbone. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Ridge polynomial neural network with error feedback for recursive multi-step forecast strategy: A case study of carbon dioxide emissions forecasting 2

Ridge polynomial neural network with error feedback for recu...

引用

2nd International Conference on computer and Information sciences, ICCIS 2020

作者： Waheeb, Waddah Shah, Habib Jabreel, Mohammed Puig, Domenec School of Computing Asia Pacific University of Technology Innovation Kuala Lumpur Bukit Jalil57000 Malaysia College of Computer Science King Khalid University Department of Computer Science Abha62529 Saudi Arabia IRCV - Intelligent Robotics and Computer Vision Group Universitat Rovira i Virgili Tarragona43007 Spain

ISBN: (数字)9781728154671

ISBN: (纸本)9781728154671

Neural networks (NNs) have been used extensively for forecasting problems. NN with error feedbacks is a type of NNs that showed more accurate forecasts compared to feedforward NNs and NNs with output feedbacks with some forecasting problems. The main issue with NN s with error feedbacks appears when there is a need for recursive multi-step forecast strategy because the observed values must be known in order to calculate network errors. This paper proposes to use the last calculated error after finishing training NNs with error feedbacks because the observed values are unknown. This last calculated error is used as a fixed value when producing forecasts using recursive multi-step forecast strategy. For that, this paper investigated this simple solution with a NN with error feedback called the ridge polynomial neural network with error feedback (RPNN-EF). Carbon dioxide emissions for three countries in the organization of the petroleum exporting countries (OPEC) were used in this investigation. The forecasting accuracy of RPNN-EF was compared with seven forecasting methods. According to the obtained results, on average, the proposed solution produces reasonable forecasts compared to the seven forecasting methods. Therefore, this solution can be suggested for NNs with error feedbacks for recursive multi-step forecast strategy. © 2020 IEEE.

关键词： Polynomials

来源：评论

学校读者我要写书评

暂无评论

Bitcoin price forecasting: A comparative study between statistical and machine learning methods 2

Bitcoin price forecasting: A comparative study between stati...

引用

2nd International Conference on computer and Information sciences, ICCIS 2020

ISBN: (纸本)9781728154671

This paper presents a comparative study between statistical and machine learning methods in forecasting Bitcoin's closing prices. Thirteen forecasting methods namely average, naive, drift, auto-regressive integrated moving-average, simple exponential smoothing (SES), Holt, and damped exponential smoothing, the average of SES, Holt and damped methods, exponential smoothing (ETS), bagged ETS, Theta, multilayer perceptron, and extreme learning machines (ELM) were used to forecast the closing prices for the next 14 days. The findings of this study are three folds. First, there are seven forecasting methods outperformed the naive method namely MLP, ELM, damped exponential smoothing, simple exponential smoothing, Theta, ETS, and ARIMA. Second, MLP and ELM showed better forecasting accuracy on both validation and out-of-sample data among the forecasting methods used in this study. Third, the size of the training data is essential factor that should be considered when training forecasting methods. © 2020 IEEE.

关键词： Bitcoin

来源：评论

学校读者我要写书评

暂无评论

Traffic Sign Detection With Event Cameras and DCNN 25

Traffic Sign Detection With Event Cameras and DCNN

引用

25th IEEE Signal Processing: Algorithms, Architectures, Arrangements, and Applications, SPA 2022

作者： Wzorek, Piotr Kryjak, Tomasz Embedded Vision Systems Group Agh University of Science and Technology Computer Vision Laboratory Department of Automatic Control and Robotics Kraków Poland Silesian University of Technology Department of Digital Systems Gliwice Poland

ISBN: (数字)9788362065424

ISBN: (纸本)9788362065424

In recent years, event cameras (DVS - Dynamic vision Sensors) have been used in vision systems as an alternative or supplement to traditional cameras. They are characterised by high dynamic range, high temporal resolution, low latency, and reliable performance in limited lighting conditions - parameters that are particularly important in the context of advanced driver assistance systems (ADAS) and self-driving cars. In this work, we test whether these rather novel sensors can be applied to the popular task of traffic sign detection. To this end, we analyse different representations of the event data: event frame, event frequency, and the exponentially decaying time surface, and apply video frame reconstruction using a deep neural network called FireNet. We use the deep convolutional neural network YOLOv4 as a detector. For particular representations, we obtain a detection accuracy in the range of 86.9-88.9% mAP@0.5. The use of a fusion of the considered representations allows us to obtain a detector with higher accuracy of 89.9% mAP@0.5. In comparison, the detector for the frames reconstructed with FireNet is characterised by an accuracy of 72.67% mAP@0.5. The results obtained illustrate the potential of event cameras in automotive applications, either as standalone sensors or in close cooperation with typical frame-based cameras. © 2022 Division of Signal Processing and Electronic Systems, Poznan University of Technology (DSPES PUT).

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

On adapting pixel-based classification to unsupervised texture segmentation

On adapting pixel-based classification to unsupervised textu...

引用

2010 20th International Conference on Pattern Recognition, ICPR 2010

作者： Melendez, Jaime Puig, Domenec Angel Garcia, Miguel Intelligent Robotics and Computer Vision Group Rovira I Virgili University Dept. of Computer Science and Mathematics Av. Paisos Catalans 26 43007 Tarragona Spain Autonomous University of Madrid Dept. of Informatics Engineering Francisco Tomas y Valiente 11 28049 Madrid Spain

ISBN: (纸本)9780769541099

An inherent problem of unsupervised texture segmentation is the absence of previous knowledge regarding the texture patterns present in the images to be segmented. A new efficient methodology for unsupervised image segmentation based on texture is proposed. It takes advantage of a supervised pixel-based texture classifier trained with feature vectors associated with a set of texture patterns initially extracted through a clustering algorithm. Therefore, the final segmentation is achieved by classifying each image pixel into one of the patterns obtained after the previous clustering process. Multi-sized evaluation windows following a top-down approach are applied during pixel classification in order to improve accuracy. The proposed technique has been experimentally validated on MeasTex, VisTex and Brodatz compositions, as well as on complex ground and aerial outdoor images. Comparisons with state-of-the-art unsupervised texture segmenters are also provided. © 2010 IEEE.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Real-time tracking of recreational boats in coastal areas using deep learning

引用

Ocean and Coastal Management 2025年 267.0卷

作者： Signaroli, Marco Lana, Arancha Cutolo, Eugenio Alós, Josep Gonzalez-Cid, Yolanda Institut Mediterrani d'Estudis Avançats IMEDEA (CSIC-UIB) Marine Research in Ecological and Social Systems Group (MARES) C/. Miquel Marquès 21 Illes Balears Esporles 07190 Spain AtalaIA Detection Technologies Av. Gabriel Alomar I Villalonga 22 Illes Balears Palma 07006 Spain Institut Mediterrani d'Estudis Avançats IMEDEA (CSIC-UIB) DataLab Service C/. Miquel Marquès 21 Illes Balears Esporles 07190 Spain IMT Atlantique Lab-STICC UMR CNRS 6285 and Odyssey Inria/IMT Technopôle Brest-Iroise 655 Avenue du Technopôle Plouzané 29280 France Universitat de les Illes Balears (UIB) Department of Mathematics and Computer Science Systems Robotics and Vision Group (SRV) Cra. de Valldemossa km 7.5 Illes Balears Palma 07122 Spain

To effectively manage and conserve coastal ecosystems, accurate spatial data on marine recreational activities are crucial. This study introduces a deep-learning-based system designed for real-time detection and tracking of recreational vessels in coastal environments using cameras. We fine-tuned and evaluated two object detection and classification algorithms, YOLOv5 and YOLOv7, for automated, real-time vessel detection, classification and positioning within Marine Protected Areas (MPAs). Additionally, we optimized two multiple object tracking algorithms, StrongSORT and ByteTrack, for tracking the movements of the detected vessels in sequential timeframes. We implemented the best combination (YOLOv5 and ByteTrack) on an NVIDIA Jetson platform, an edge computing device specifically designed for AI applications, conducting thorough benchmarking across various simulated hardware configurations to determine its minimal computational and power needs. Then, we conducted field tests by positioning the system on a coastal cliff overlooking a recreational fishery located in a partial MPA. These tests aimed to validate the system's real-time operational viability and to acquire precise vessel trajectories. The results confirmed the system's efficacy and its data collection capabilities within a real marine environment. Finally, we evaluated two camera calibration techniques for converting image trajectories to geographic coordinates: a projective transformation with homography for accurate perspective adjustment, and an innovative neural network-based approach. The system we have developed could markedly enhance the monitoring and surveillance capabilities within MPAs, generating spatial-temporal data of recreational fishing effort that can be easily transferred to other case studies. © 2025 The Authors

关键词： Artificial intelligence Boat detection Deep learning Fishing effort Marine protected areas Multiple object tracking Recreational fishing

来源：评论

学校读者我要写书评

暂无评论

Robust color image segmentation through tensor voting

Robust color image segmentation through tensor voting

引用

International Conference on Pattern Recognition

作者： Moreno, Rodrigo Garcia, Miguel Angel Puig, Domenec Rovira I Virgili University Intelligent Robotics and Computer Vision Group Dept. of Computer Science and Mathematics Av. Països Catalans 26 43007 Tarragona Spain Autonomous University of Madrid Dept. of Informatics Engineering Francisco Tomas y Valiente 11 28049 Madrid Spain

ISBN: (纸本)9780769541099

This paper presents a new method for robust color image segmentation based on tensor voting, a robust perceptual grouping technique used to extract salient information from noisy data. First, an adaptation of tensor voting to both image denoising and robust edge detection is applied. Second, pixels in the filtered image are classified into likely-homogeneous and likely-inhomogeneous by means of the edginess maps generated in the first step. Third, the likely-homogeneous pixels are segmented through an efficient graph-based segmenter. Finally, a modified version of the same graph-based segmenter is applied to the likely-inhomogeneous pixels in order to obtain the final segmentation. Experiments show that the proposed algorithm has a better performance than the state-of-the-art. © 2010 IEEE.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Detecting abnormal mammographic cases in temporal studies using image registration features

引用

12th International Workshop on Breast Imaging, IWDM 2014

作者： Martí, Robert Díez, Yago Oliver, Arnau Tortajada, Meritxell Zwiggelaar, Reyer Lladó, Xavier Computer Vision and Robotics Group University of Girona Av. Lluís Santaló 17071 Spain Department of Computer Science Aberystwyth University Ceredigion SY23 3DB United Kingdom

ISBN: (纸本)9783319078861

Image registration is increasingly being used to help radiologists when comparing temporal mammograms for lesion detection and classification. This paper evaluates the use of image and deformation features extracted from image registration results in order to detect abnormal cases with masses. Using a dataset of 264 mammographic images from 66 patients (33 normals and 33 with masses) results show that the use of a non-rigid registration method clearly improves detection results compared to no registration (AUC: 0.76 compared to 0.69). Moreover, feature combination using left and right breasts further improves the performance (AUC to 0.88) compared to single image features. © 2014 Springer International Publishing.

关键词： Image registration

来源：评论

学校读者我要写书评

暂无评论

Gabor-based texture classification through efficient prototype selection via normalized cut

Gabor-based texture classification through efficient prototy...

引用

IEEE International Conference on Image Processing

作者： Jaime Melendez Domenec Puig Miguel Angel Garcia Intelligent Robotics and Computer Vision Group Department of Computer Science and Mathematics Rovira i Virgili University Spain Department of Informatics Engineering Autonomous University of Madrid Spain

This paper presents a new efficient technique for supervised pixel-based texture classification. The proposed scheme first performs a selection process that automatically determines a subset of prototypes that characterize each texture class based on the outcome of a multichannel Gabor wavelet filter bank. Then, every image pixel is classified into one of the given texture classes by using a K-NN classifier fed with the prototypes determined previously. The proposed technique is compared to previous texture classifiers by using both Brodatz and real outdoor textured images.

关键词： Prototypes Gabor filters Pixel Feature extraction Filter bank Testing intelligent robots Image texture analysis Pattern recognition Image recognition

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：