检索结果-内蒙古大学图书馆

作者： Iftekhar, A. S. M. University of California Santa Barbara

学位级别：Ph.D., Doctor of Philosophy

The development of automated methods capable of detecting and localizing actions is crucial for a variety of applications, ranging from surveillance and autonomous driving to content moderation. This thesis focuses on creating action detection methods that deliver robust performances. At the heart of these methods’ robustness lie two fundamental elements: the detection of atomic actions and the ability for compositional understanding. Atomic actions are those that are identifiable from a single image or a short video. In this research, we developed innovative methods to detect and localize such actions that achieve state-of-the art performance. The key strength of these methods lies in their ability to refine visual features both spatially and semantically, enabling precise identification of action-specific regions. For scalability, we further developed a multi-branch network to recognize new composition of objects and actions. Our design ensures that each branch learns decoupled features, allowing the network to transfer previously learned concepts to identify new compositions. This approach outperforms existing methods by a good margin as our extensive experiments on benchmark datasets demonstrate. Further, the correct identification of the attributes of the participating objects in actions helps to detect unknown compositions. Therefore, we have created a network utilizing spatially localized learning to correctly associate objects and attributes. This network achieves state-of-the-art performance in object-attribute association on cluttered scenes. The developed methods in this thesis can do robust action detection at scale and serve as a base for numerous future applications.

关键词： Action detection Compositional learning Computer vision Deep learning image processing machine learning

来源：评论

学校读者我要写书评

暂无评论

Research on Key Technologies of target location based on Intelligent Robot 3

Research on Key Technologies of target location based on Int...

引用

3rd International Conference on Computer vision, image and Deep Learning and International Conference on Computer Engineering and applications, CVIDL and ICCEA 2022

作者： Li, Zhong Guo, Caihui Guangzhou City Construction College Guangdong China Citi University Ulaanbaatar Mongolia

ISBN: (纸本)9781665459112

In recent years, the country has proposed the strategic development goal of 'Made in China 2025', and the intelligent manufacturing industry has gradually received national attention. Intelligent robots rely on the advantages of high efficiency and strong adaptability to the working environment to promote the development of intelligent manufacturing industry. machine vision technology makes robots more intelligent, and the robot system integrating vision has also developed rapidly. Compared with monocular vision, binocular vision can obtain target stereo information, and it has become a key research topic in related fields. Under this background, this paper designs an intelligent robot target recognition and positioning system based on binocular vision according to the actual industrial demand. This paper mainly studies the recognition and localization algorithm of circular object workpiece by intelligent robot based on binocular vision system, and designs and realizes the whole experimental system according to the research content. Based on the system experiment, this paper introduces the calibration of the binocular camera system and the robot vision system, the target image pretreatment algorithm, the recognition and positioning algorithm of the target workpiece and so on. Finally, the visual interface is designed to control the robot to complete the simulated grasping action and realize the whole system. The object image is acquired by binocular camera, the object identification and location are completed according to the image processing algorithm, and the robot is controlled to complete the simulation grasping experiment, which has certain reference significance in practical application. © 2022 IEEE.

关键词： Binocular vision

来源：评论

学校读者我要写书评

暂无评论

Wiper Arm Defect Detection Using Laplacian Pyramids and Genetic Algorithm 18

Wiper Arm Defect Detection Using Laplacian Pyramids and Gene...

引用

18th IEEE International Colloquium on Signal processing and applications (CSPA)

作者： Ler, Wei Xian Tay, Lee Choo Goh, Kam Meng Tunku Abdul Rahman Univ Coll Fac Engn & Technol Dept Elect & Elect Engn Kuala Lumpur Malaysia

ISBN: (纸本)9781665485296

Due to its uneven and curvy surface, researchers had difficulty in getting the wiper arm surface to be evenly illuminated for appearance defect detection using machine vision. As a result, some defects, especially those located at the edge of the region of interest (ROI) were missed. In this paper, the ROI was widened by stitching two sequential images together using Laplacian pyramids. Genetic algorithm was then used to enhance the important features of the defects using the best fitness value, parent mating, crossover and mutation. The algorithm was able to reduce the effect of uneven-illumination by repeating regeneration. The resultant image was converted into binary for defect identification, and localized according to its contour. Experimental results showed 90.5% accuracy.

关键词： Laplacian pyramids genetic algorithm wiper arm defect detection image stitching

来源：评论

学校读者我要写书评

暂无评论

Bridging the machine-Human Gap in Blurred-image Classification via Entropy Maximisation

Bridging the Machine-Human Gap in Blurred-Image Classificati...

引用

International image processing, applications and Systems Conference (IPAS)

作者： Emilio Sansano-Sansano Marina Martínez-García Javier Portilla INIT Universitat Jaume I Castellón de la Plana Spain IMAC Universitat Jaume I Castellón de la Plana Spain Instituto de Óptica CSIC Madrid Spain

ISBN: (数字)9798331506520

ISBN: (纸本)9798331506537

Recent studies point to an accuracy gap between humans and Artificial Neural Network (ANN) models when classifying blurred images, with humans outperforming ANNs. To bridge this gap, we introduce a spectral channel-based range-constrained entropy merit function, from which we devise a zero-phase, circular symmetric blind deblurring method. We apply it as a pre-processing step for image classification and test it using pre-trained classification models and images blurred by Gaussian kernels. We compare our method to state-of-the-art restoration methods, showing its superiority, effectively bridging the machine-human gap for most models and blur levels. Our results also rank higher than the competitors in no-reference and full-reference image quality metrics. Notwithstanding the limitation to zero-phase blur, this work shows that, for image pre-processing aimed at visual tasks, it may be advantageous to use merit functions based on vision science and information theory, rather than on the expected error to the latent image.

关键词： Measurement image quality Visualization Computer vision Artificial neural networks Entropy Kernel Optimization Information theory image classification

来源：评论

学校读者我要写书评

暂无评论

Traffic Monitoring and Violation Detection Using Deep Learning 2nd

Traffic Monitoring and Violation Detection Using Deep Learni...

引用

2nd International Conference on Big Data, machine Learning, and applications, BigDML 2021

作者： Sargar, Omkar Jain, Saharsh Chittupalli, Sravan Tatipamula, Aniket Department of Electronics Engineering Veermata Jijabai Technological Institute Mumbai India Department of Computer Science Veermata Jijabai Technological Institute Mumbai India AIRPIX Geoanalytics Navi Mumbai India

ISBN: (纸本)9789819934805

The traffic density on roads has been increasing rapidly for the past few decades, which has in turn been reflected in the increase in traffic violations and accidents. Official reports from various governments and private entities bolster the fact that, indeed, the current methods for traffic monitoring are inept to deal with the huge traffic density [1, 2]. These methods, which traditionally included the deployment of traffic police personnel at a select few junctions where the traffic density is high, ignore the majority of the other roads. Traffic monitoring systems that exploit image processing, computer vision and deep learning techniques thus come out to be a viable and optimal solution to monitor traffic and detect violations. These systems can easily be integrated with the architecture of law enforcement to penalize violators in real time. The proposed method—which utilizes YOLOv3 and SORT—is effective and accurate in detecting several violations like—over-speeding, wrong-way driving, signal jumping, driving without helmet and triple seat violation. It also helps to keep track of the count of vehicles, their types and also the number of axels for multi-axle vehicles, thus, asserting itself as a novel and indigenous solution to a widely recognized problem. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Lipschitz energy functional for anisotropic diffusion applications

引用

INFORMATION SCIENCES 2024年 678卷

作者： Maiseli, Baraka Univ Dar Es Salaam Coll Informat & Commun Technol Dept Elect & Telecommun Engn Dar Es Salaam Tanzania

image denoising remains a key research problem because of its potential role as a pre-processing component in image processing, computer vision, and machine learning tasks. Of the available approaches for image denoising, those inspired by anisotropic diffusion processes have been a center of discussion for decades. Despite the efforts and promising results achieved by diffusion-inspired denoising methods, we noted insufficient attention on the design of energy functionals for anisotropic diffusion equations. Most researchers consider heuristic approaches to design diffusivity functionals, a practice that cannot provide mathematical explanations on why their approaches work. The current research presents a strictly convex and Lipschitz energy functional that guarantees a unique solution for an evolutionary process. Based on this functional, we derive an anisotropic diffusion equation for image denoising applications. Experimental results show that an algorithm corresponding to the proposed equation is computationally efficient, and generates informative and visually appealing images with competitive values of peak signal-to-noise ratio and structural similarity. Guided by the compelling properties of our energy functional, we provide an additional insight to describe quality of the results. Implementation codes and test datasets of the proposed approach are publicly accessible at the MATLAB File Exchange (https://www .mathworks .com /matlabcentral /fileexchange /160108- lipschitz -diffusion -inspired -energy-functional).

关键词： Anisotropic diffusion image denoising image restoration Noise image quality assessment

来源：评论

学校读者我要写书评

暂无评论

Defect Detection and Removal for Depth Map Quality Enhancement in Manufacturing with Deep Learning 12

Defect Detection and Removal for Depth Map Quality Enhanceme...

引用

Dimensional Optical Metrology and Inspection for Practical applications XII 2023

作者： Gapon, N. Voronin, V. Sizyakin, R. Zhdanova, M. Semenishchev, E. Zelensky, A. Don State Technical University Rostov-on-Don Russia Center for Cognitive Technology and Machine Vision Moscow State University of Technology «STANKIN» Moscow Russia

ISBN: (数字)9781510661639

ISBN: (纸本)9781510661622

A system for determination the distance from the robot to the scene is useful for object tracking, and 3-D reconstruction may be desired for many manufacturing and robotic tasks. While the robot is processing materials, such as welding parts, milling, drilling, fragments of materials fall on the camera installed on the robot, introducing unnecessary information when building a depth map, as well as the emergence of new lost areas, which leads to incorrect determination of the size of objects. There is a problem comprising a decrease in the accuracy of planning the movement trajectory caused by incorrect sections on the depth map because of incorrect distance determination of objects. We present a two-stage approach combining defect detection and depth reconstruction algorithms. The first step is image defects detection based on convolutional auto-encoder (U-Net) and deep feature fusion network (DFFN-Net). The second step is a depth map reconstruction with the exemplar-based and the anisotropic gradient concepts. The proposed modified block fusion algorithm uses a local image descriptor obtained by an automatic encoder for image reconstruction, which extracts image features and depth maps using a decoding network. Our technique outperforms the state-of-the-art methods quantitatively in reconstruction accuracy on RGB-D benchmark for evaluating manufacturing vision systems. © 2023 SPIE.

关键词： Robots

来源：评论

学校读者我要写书评

暂无评论

Robust Event-Based vision Model Estimation by Dispersion Minimisation

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND machine INTELLIGENCE 2022年第12期44卷 9561-9573页

作者： Nunes, Urbano Miguel Demiris, Yiannis Imperial Coll London Dept Elect & Elect Engn Personal Robot Lab London SW7 2AZ England

We propose a novel Dispersion Minimisation framework for event-based vision model estimation, with applications to optical flow and high-speed motion estimation. The framework extends previous event-based motion compensation algorithms by avoiding computing an optimisation score based on an explicit image-based representation, which provides three main benefits: i) The framework can be extended to perform incremental estimation, i.e., on an event-by-event basis. ii) Besides purely visual transformations in 2D, the framework can readily use additional information, e.g., by augmenting the events with depth, to estimate the parameters of motion models in higher dimensional spaces. iii) The optimisation complexity only depends on the number of events. We achieve this by modelling the event alignment according to candidate parameters and minimising the resultant dispersion, which is computed by a family of suitable entropy-based measures. Data whitening is also proposed as a simple and effective pre-processing step to make the framework's accuracy performance more robust, as well as other event-based motion-compensation methods. The framework is evaluated on several challenging motion estimation problems, including 6-DOF transformation, rotational motion, and optical flow estimation, achieving state-of-the-art performance.

关键词： Dispersion Estimation Cameras Optical imaging Optimization Computational modeling Motion estimation Event-based vision optimisation framework optical flow and high-speed motion estimation dispersion minimisation real-time motion estimation

来源：评论

学校读者我要写书评

暂无评论

11th EAI International Conference on Context-Aware Systems and applications, ICCASA 2022

11th EAI International Conference on Context-Aware Systems a...

引用

11th EAI International Conference on Context-Aware Systems and applications, ICCASA 2022

ISBN: (纸本)9783031288159

The proceedings contain 14 papers. The special focus in this conference is on Context-Aware Systems and applications. The topics include: Prediction of Chaotic Time Series Based on LSTM, Autoencoder and Chaos Theory;an Approach to Selecting Students Taking Provincial and National Excellent Student Exams;safe Interaction Between Human and Robot Using vision Technique;application of the image processing Technique for Powerline Robot;collaborative Recommendation with Energy Distance Correlation;blockchain Model in Industrial Pangasius Farming;multiple-Criteria Rating Recommendation with Ordered Weighted Averaging Aggregation Operators;a Survey of On-Chip Hybrid Interconnect for Multicore Architectures;a Framework for Brain-Computer Interfaces Closed-Loop Communication Systems;identification of Abnormal Cucumber Leaves image Based on Recurrent Residual U-Net and Support Vector machine Techniques;lung Lesion images Classification Based on Deep Learning Model and Adaboost Techniques;balltree Similarity: A Novel Space Partition Approach for Collaborative Recommender Systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing Human-Computer Interaction: Hand Detection for Air Writing Utilizing NumPy and OpenCV 3

Enhancing Human-Computer Interaction: Hand Detection for Air...

引用

3rd International Conference on Technological Advancements in Computational Sciences, ICTACS 2023

作者： Shukla, Pranjal Das, Prasenjit Chandigarh University Department of Cse Punjab Mohali India

ISBN: (纸本)9798350342338

In recent years, there has been a remarkable increase in interest and challenges in image processing and pattern recognition, specifically in the context of air writing. This exciting research area has significant potential to advance automation processes and improve human-machine interfaces in various applications. The emergence of faster computers, affordable high-performance video cameras, and the need for automated analysis of videos has led to an increase in the popularity of object tracking, a critical task in computer vision. The process of video analysis typically encompasses object detection, tracking, and behavior analysis. Object tracking involves four main aspects choosing the suitable object representation, selecting features for tracking, detecting the object, and tracking the object. Object tracking algorithms find applications in different domains, including vehicle navigation, video indexing, and surveillance that are automated. The objective of the paper is to create a software application for smart wearable devices that utilizes computer vision to track finger gestures in the air, functioning as a motion-to-text converter for air-writing. The technology will facilitate communication for people by enabling them to generate text for multiple purposes, like sending emails and messages, through intermittent gestures. This is a productive means of communication that curbs the usage of laptops and mobiles, making it particularly beneficial for individuals who are deaf. © 2023 IEEE.

关键词： Air Writing Computer vision Digital sketching Gesture Recognition Hand Detection Hand Tracking Interactive whiteboard

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：