基于深度学习的单视图三维重建综述

计算机视觉是计算机领域研究的热门方向,而三维重建在计算机视觉方面具有很高的研究价值.近年来,随着深度学习、人工智能不断的发展,基于深度学习的单视图三维重建工作受到大量学者的关注.介绍了基于深度学习的单视图三维重建的三种常用方法、三维重建工作常用数据集和其具体的应用领域,并对基于深度学习的单视图三维重建进行了小结与展望.     

计算机视觉下的车辆目标检测算法综述

车辆目标检测是基于计算机视觉的目标检测领域的一个重要应用领域,近年来随着深度学习在图像分类方面取得的巨大进展,机器视觉技术结合深度学习方法的车辆目标检测算法逐渐成为该领域的研究重点和热点。介绍了基于机器视觉的车辆目标检测的任务、难点与发展现状,以及深度学习方法中几种具有代表性的卷积神经网络模型,通过这些网络模型衍生出的two stage、one stage车辆目标检测算法和用于模型训练的相关数据集与检测效果评价标准,对其存在的问题及未来可能的发展方向进行了讨论。     

计算机视觉下的果实目标检测算法综述

基于计算机视觉的果实目标检测识别是目标检测、计算机视觉、农业机器人等多学科的重要交叉研究课题,在智慧农业、农业现代化、自动采摘机器人等领域,具有重要的理论研究意义和实际应用价值。随着深度学习在图像处理领域中广泛应用并取得良好效果,计算机视觉技术结合深度学习方法的果实目标检测识别算法逐渐成为主流。本文介绍基于计算机视觉的果实目标检测识别的任务、难点和发展现状,以及2类基于深度学习方法的果实目标检测识别算法,最后介绍用于算法模型训练学习的公开数据集与评价模型性能的评价指标,且对当前果实目标检测识别存在的问题和未来可能的发展方向进行讨论。     

基于深度学习的目标视频跟踪算法综述

深度学习理论在计算机视觉中的应用日趋广泛,在目标分类、检测领域取得了令人瞩目的成果,但是深度学习理论在目标跟踪领域的早期应用中,由于存在跟踪时只有目标为正样本,缺乏数据支持,对位置信息依赖程度高等问题,因而应用效果并不理想,传统方法仍占据主流地位.近年来,随着技术的不断发展,深度学习在目标跟踪方向取得了长足的进步.本文首先介绍了目标跟踪技术的基本概念和主要方法,然后针对深度学习在目标跟踪领域的发展现状,从基于深度特征的目标跟踪和基于深度网络的目标跟踪两方面重点阐述了深度学习在该领域的应用方法,并对近期较为流行的基于孪生网络的目标跟踪进行了详细介绍.最后对近年来深度学习在目标跟踪领域取得的成果,以及未来的发展方向作了总结和展望.     

基于深度学习的视觉跟踪算法研究综述

视觉跟踪是计算机视觉的重要研究领域之一。传统的视觉跟踪算法难以很好地解决复杂背景中的跟踪问题,如光线变化、目标发生较大的尺寸和姿态变化或目标被遮挡等。而深度学习的引入为视觉跟踪研究开辟了新的途径。但目前国内外基于深度学习的视觉跟踪研究文献相对较少,为 吸引更多视觉跟踪领域研究者对深度学习进行探索和讨论,并推动视觉跟踪算法的研究,简要介绍了视觉跟踪和深度学习的研究现状,重点分析了基于深度学习的视觉跟踪算法的相关文献,讨论了各算法的优缺点,最后提出了进一步研究的方向以及对基于深度学习的视觉跟踪算法的展望。     

基于深度学习的图像语义分割技术研究综述

图像语义分割技术是智能系统理解自然场景的关键技术之一,作为视觉智能领域的重要研究方向,该技术在移动机器人、无人机、智能驾驶以及智慧安防等领域具有广阔的应用前景。对于图像语义分割技术的研究发展历程进行了详细评述,包括从传统的语义分割方法到当前主流的基于深度学习的图像语义分割理论及其方法,重点阐述了基于深度学习的图像语义分割技术的框架及其实现过程,进而对当前具有代表性的典型算法的效果以及优缺点进行了分析,然后归纳了算法评价指标,最后对该技术的发展进行了总结与展望。该研究对于从事图像语义分割技术的研究人员和工程技术人员均具有很好的参考意义。     

胶囊神经网络研究现状与未来的浅析

当今时代的人工智能技术迅速发展,推动了社会的巨大进步。深度学习作为人工智能领域重要的一部分,具有非常广阔的应用前景,近年来,越来越多的专家学者开始研究深度学习领域相关技术,比较典型的两个方向就是自然语言处理和计算机视觉,其中计算机视觉的发展大力引领着深度学习领域的进步。介绍了卷积神经网络的经典模型和深度学习中新型神经网络模型--胶囊网络以及其动态路由算法,并对比了二者的优劣性。对胶囊网络的应用给予综述,以图像和文本两方面来阐述胶囊网络的应用领域和优势所在。最后进行概括总结,并展望了胶囊网络可能的改进方向。     

基于深度学习的图像风格迁移研究进展

图像风格迁移是计算机视觉领域的一个热点研究方向。随着深度学习的兴起,图像风格迁移领域得到了突破性的发展。为了推进图像风格迁移领域的发展,对基于深度学习的图像风格迁移的现有研究方法进行综述。对基于深度学习的图像风格迁移方法进行分类和梳理,并对比分析基于卷积神经网络和基于生成对抗网络的风格迁移方法,介绍了图像风格迁移的改进性和拓展性工作,讨论了图像风格迁移领域目前面临的挑战和未来的研究方向。     

基于深度学习的视觉单目标跟踪综述

单目标跟踪是一种在视频中利用目标外观和上下文信息对单个目标分析运动状态、提供定位的技术,在智能监控、智能交互、导航制导等方面具有应用前景,但遮挡、背景干扰、目标变化等问题导致实际应用的进展缓慢.随着近年来深度学习的快速发展,研究使用深度学习技术优化单目标跟踪算法已成为计算机视觉领域的热点之一.围绕基于深度学习的单目标跟踪算法,在分析了单目标跟踪的基本原理基础上,从相关滤波、孪生网络、元学习、注意力、循环神经网络和生成对抗网络六个方面,根据核心算法的不同分别进行了概述和分析;此外,对研究现状进行了总结,提出了算法的发展趋势和优化思路.     

深度神经网络图像语义分割方法综述

图像语义分割是计算机视觉领域近年来的热点研究课题,随着深度学习技术的兴起,图像语义分割与深度学习技术进行融合发展,取得了显著的进步,在无人驾驶、智能安防、智能机器人、人机交互等真实场景中应用广泛。首先对应用于图像语义分割的几种深度神经网络模型进行简单介绍,接着详细阐述了现有主流的基于深度神经网络的图像语义分割方法,依据实现技术的区别对图像语义分割方法进行分类,并对每类方法中代表性算法的技术特点、优势和不足进行分析与总结。之后归纳了图像语义分割常用的大规模公共数据集和性能评价指标,并在此基础上对经典的语义分割方法的实验结果进行了对比,最后对语义分割领域未来可行的研究方向进行展望。     

Self-supervised deep metric learning for ancient papyrus fragments retrieval

International Journal on Document Analysis and Recognition (IJDAR) - This work focuses on document fragments association using deep metric learning methods. More precisely, we are interested in...     

A survey of deep learning techniques for autonomous driving

The last decade witnessed increasingly rapid progress in self‐driving vehicle technology, mainly backed up by advances in the area of deep learning and artificial intelligence (AI). The objective of this paper is to survey the current state‐of‐the‐art on deep learning technologies used in autonomous driving. We start by presenting AI‐based self‐driving architectures, convolutional and recurrent neural networks, as well as the deep reinforcement learning paradigm. These methodologies form a base for the surveyed driving scene perception, path planning, behavior arbitration, and motion control algorithms. We investigate both the modular perception‐planning‐action pipeline, where each module is built using deep learning methods, as well as End2End systems, which directly map sensory information to steering commands. Additionally, we tackle current challenges encountered in designing AI architectures for autonomous driving, such as their safety, training data sources, and computational hardware. The comparison presented in this survey helps gain insight into the strengths and limitations of deep learning and AI approaches for autonomous driving and assist with design choices.     

Knowledge discovering for document classification using tree matching in TEXPROS

This paper describes a knowledge-based system for classifying documents based upon the layout structure and conceptual information extracted from their contents. The spatial elements in a document are laid out in rectangular blocks which are represented by nodes in an ordered labeled tree, called the “Layout Structure Tree” (L-S Tree). Each leaf node of an L-S Tree points to its corresponding block content. A Knowledge Acquisition Tool (KAT) is devised to perform the inductive learning from L-S Trees of document samples, and then generate the Document Sample Tree and Document Type Tree bases. A testing document is classified if a Document Type Tree is discovered as a substructure of the L-S Tree of the testing document. Then we match the L-S Tree with the Document Sample Trees of the classified document type to find the format of the testing document. The Document Sample Trees and Document Type Trees are called Structural Knowledge Base (SKB). The tree discovering and matching processes involve comparing the SKB trees and a testing document's L-S Tree by using pattern matching and discovering toolkits. Our experimental results demonstrate that many office documents can be classified correctly using the proposed approach.     

TableSegNet: a fully convolutional network for table detection and segmentation in document images

International Journal on Document Analysis and Recognition (IJDAR) - Advances in image object detection lead to applying deep convolution neural networks in the document image analysis domain....     

EAML: ensemble self-attention-based mutual learning network for document image classification

International Journal on Document Analysis and Recognition (IJDAR) - In the recent past, complex deep neural networks have received huge interest in various document understanding tasks such as...     

Segmentation for document layout analysis: not dead yet

International Journal on Document Analysis and Recognition (IJDAR) - Document layout analysis is often the first task in document understanding systems, where a document is broken down into...     

The role of AI technology in prediction,diagnosis and treatment of colorectal cancer

Artificial intelligence (AI) is a fascinating new technology that incorporates machine learning and neural networks to improve existing technology or create new ones. Potential applications of AI are introduced to aid in the fight against colorectal cancer (CRC). This includes how AI will affect the epidemiology of colorectal cancer and the new methods of mass information gathering like GeoAI, digital epidemiology and real-time information collection. Meanwhile, this review also examines existing tools for diagnosing disease like CT/MRI, endoscopes, genetics, and pathological assessments also benefitted greatly from implementation of deep learning. Finally, how treatment and treatment approaches to CRC can be enhanced when applying AI is under discussion. The power of AI regarding the therapeutic recommendation in colorectal cancer demonstrates much promise in clinical and translational field of oncology, which means better and personalized treatments for those in need.

     

Kubernetes集群上深度学习负载优化

人工智能技术的快速发展和在云原生上部署应用高效等优点让越来越多的开发者和互联网企业将人工智能应用部署在Kubernetes集群上,但Kubernetes并不是主要针对深度学习而设计,对深度学习这个特定领域需要做定制优化.本文针对具有一定规模的Kubernetes集群上部署深度学习负载的场景,设计和实现了一系列优化方案,主要从深度学习所要求的数据处理、graphics processing unit (GPU)计算、分布式训练等几个方面进行优化,本文提出的优化方案覆盖了数据处理、计算等方面,这些技术极大简化人工智能负载在规模化云原生平台上的部署难度和提高运行效率,同时从实践上来看也验证了以上技术对人工智能应用有着显著的提升作用.     

Unbox the black-box for the medical explainable AI via multi-modal and multi-centre data fusion: A mini-review,two showcases and beyond

Explainable Artificial Intelligence (XAI) is an emerging research topic of machine learning aimed at unboxing how AI systems’ black-box choices are made. This research field inspects the measures and models involved in decision-making and seeks solutions to explain them explicitly. Many of the machine learning algorithms cannot manifest how and why a decision has been cast. This is particularly true of the most popular deep neural network approaches currently in use. Consequently, our confidence in AI systems can be hindered by the lack of explainability in these black-box models. The XAI becomes more and more crucial for deep learning powered applications, especially for medical and healthcare studies, although in general these deep neural networks can return an arresting dividend in performance. The insufficient explainability and transparency in most existing AI systems can be one of the major reasons that successful implementation and integration of AI tools into routine clinical practice are uncommon. In this study, we first surveyed the current progress of XAI and in particular its advances in healthcare applications. We then introduced our solutions for XAI leveraging multi-modal and multi-centre data fusion, and subsequently validated in two showcases following real clinical scenarios. Comprehensive quantitative and qualitative analyses can prove the efficacy of our proposed XAI solutions, from which we can envisage successful applications in a broader range of clinical questions.     

A survey of document image classification: problem statement,classifier architecture and performance evaluation

Document image classification is an important step in Office Automation, Digital Libraries, and other document image analysis applications. There is great diversity in document image classifiers: they differ in the problems they solve, in the use of training data to construct class models, and in the choice of document features and classification algorithms. We survey this diverse literature using three components: the problem statement, the classifier architecture, and performance evaluation. This brings to light important issues in designing a document classifier, including the definition of document classes, the choice of document features and feature representation, and the choice of classification algorithm and learning mechanism. We emphasize techniques that classify single-page typeset document images without using OCR results. Developing a general, adaptable, high-performance classifier is challenging due to the great variety of documents, the diverse criteria used to define document classes, and the ambiguity that arises due to ill-defined or fuzzy document classes.