An Overview of Contour Detection Approaches

Object contour plays an important role in fields such as semantic segmentation and image classification. However, the extraction of contour is a difficult task, especially when the contour is incomplete or unclosed. In this paper, the existing contour detection approaches are reviewed and roughly divided into three categories: pixel-based, edge-based, and region-based. In addition, since the traditional contour detection approaches have achieved a high degree of sophistication, the deep convolutional neural networks (DCNNs) have good performance in image recognition, therefore, the DCNNs based contour detection approaches are also covered in this paper. Moreover, the future development of contour detection is analyzed and predicted.     

深度卷积神经网络在计算机视觉中的应用研究综述

随着大数据时代的到来,含更多 隐含层的深度卷积神经网络(Convolutional neural networks, CNNs)具有更复杂的网络结构,与传统机器学习方法相比具有更强大的特征学习和特征表达能力。使用深度学习算法训练的卷积神经网络模型自提出以来在计算机视觉领域的多个大规模识别任务上取得了令人瞩目的 成绩。本文首先简要介绍深度学习和卷积神经网络的兴起与展,概述卷积神经网络的基本模型结构、卷积特征提取和池化操作。然后综述了基于深度学习的卷积神经网络模型在图像分类、物体检测、姿态估计、图像分割和人脸识别等多个计算机视觉应用领域中的研究现状 和发展趋势,主要从典型的网络结构的构建、训练方法和性能表现3个方面进行介绍。最后对目前研究中存在的一些问题进行简要的总结和讨论,并展望未来发展的新方向。     

深度卷积神经网络图像语义分割研究进展

在计算机视觉领域中,语义分割是场景解析和行为识别的关键任务,基于深度卷积神经网络的图像语义分割方法已经取得突破性进展。语义分割的任务是对图像中的每一个像素分配所属的类别标签,属于像素级的图像理解。目标检测仅定位目标的边界框,而语义分割需要分割出图像中的目标。本文首先分析和描述了语义分割领域存在的困难和挑战,介绍了语义分割算法性能评价的常用数据集和客观评测指标。然后,归纳和总结了现阶段主流的基于深度卷积神经网络的图像语义分割方法的国内外研究现状,依据网络训练是否需要像素级的标注图像,将现有方法分为基于监督学习的语义分割和基于弱监督学习的语义分割两类,详细阐述并分析这两类方法各自的优势和不足。本文在PASCAL VOC（pattern analysis, statistical modelling and computational learning visual object classes）2012数据集上比较了部分监督学习和弱监督学习的语义分割模型,并给出了监督学习模型和弱监督学习模型中的最优方法,以及对应的MIoU（mean intersection-over-union）。最后,指出了图像语义分割领域未来可能的热点方向。     

Supervised semantic segmentation based on deep learning: a survey

Recently, many semantic segmentation methods based on fully supervised learning are leading the way in the computer vision field. In particular, deep neural networks headed by convolutional neural networks can effectively solve many challenging semantic segmentation tasks. To realize more refined semantic image segmentation, this paper studies the semantic segmentation task with a novel perspective, in which three key issues affecting the segmentation effect are considered. Firstly, it is hard to predict the classification results accurately in the high-resolution map from the reduced feature map since the scales are different between them. Secondly, the multi-scale characteristics of the target and the complexity of the background make it difficult to extract semantic features. Thirdly, the problem of intra-class differences and inter-class similarities can lead to incorrect classification of the boundary. To find the solutions to the above issues based on existing methods, the inner connection between past research and ongoing research is explored in this paper. In addition, qualitative and quantitative analyses are made, which can help the researchers to establish an intuitive understanding of various methods. At last, some conclusions about the existing methods are drawn to enhance segmentation performance. Moreover, the deficiencies of existing methods are researched and criticized, and a guide for future directions is provided.

     

显著性引导及不确定性监督的深度编解码网络

基于U-Net的编码-解码网络及其变体网络在医学图像语义分割任务中取得了卓越的分割性能.然而,网络在特征提取过程中丢失了部分空间细节信息,影响了分割精度.另一方面,在多模态的医学图像语义分割任务中,这些模型的泛化能力和鲁棒性不理想.针对以上问题,本文提出一种显著性引导及不确定性监督的深度卷积编解码网络,以解决多模态医学图像语义分割问题.该算法将初始生成的显著图和不确定概率图作为监督信息来优化语义分割网络的参数.首先,通过显著性检测网络生成显著图,初步定位图像中的目标区域;然后,根据显著图计算不确定分类的像素点集合,生成不确定概率图;最后,将显著图和不确定概率图与原图像一同送入多尺度特征融合网络,引导网络关注目标区域特征的学习,同时增强网络对不确定分类区域和复杂边界的表征能力,以提升网络的分割性能.实验结果表明,本文算法能够捕获更多的语义信息,在多模态医学图像语义分割任务中优于其他的语义分割算法,并具有较好的泛化能力和鲁棒性.     

Medical image semantic segmentation based on deep learning

The image semantic segmentation has been extensively studying. The modern methods rely on the deep convolutional neural networks, which can be trained to address this problem. A few years ago networks require the huge dataset to be trained. However, the recent advances in deep learning allow training networks on the small datasets, which is a critical issue for medical images, since the hospitals and research organizations usually do not provide the huge amount of data. In this paper, we address medical image semantic segmentation problem by applying the modern CNN model. Moreover, the recent achievements in deep learning allow processing the whole image per time by applying concepts of the fully convolutional neural network. Our qualitative and quantitate experiment results demonstrated that modern CNN can successfully tackle the medical image semantic segmentation problem.

     

A systematic survey of deep learning in breast cancer

In recent years, we witnessed a speeding development of deep learning in computer vision fields like categorization, detection, and semantic segmentation. Within several years after the emergence of AlexNet, the performance of deep neural networks has already surpassed human being experts in certain areas and showed great potential in applications such as medical image analysis. The development of automated breast cancer detection systems that integrate deep learning has received wide attention from the community. Breast cancer, a major killer of females that results in millions of deaths, can be controlled even be cured given that it is detected at an early stage with sophisticated systems. In this paper, we reviewed breast cancer diagnosis, detection, and segmentation computer-aided (CAD) systems based on state-of-the-art deep convolutional neural networks. The available data sets also indirectly determine CAD systems' performance, so we introduced and discussed the details of public data sets. The challenges remaining in CAD systems for breast cancer are discussed at the end of this paper. The highlights of this survey mainly come from three following aspects. First, we covered a wide range of the basics of breast cancer from imaging modalities to popular databases in the community; Second, we presented the key elements in deep learning to form the compactness for methods mentioned in reviewed papers; Third and lastly, the summative details in each reviewed paper are provided so that interested readers can have a refined version of these works without referring to original papers. Therefore, this systematic survey suits readers with varied backgrounds and will be beneficial to them.     

结合超像素分割的多尺度特征融合图像语义分割算法

深度学习的发展加快了图像语义分割的研究.目前,最有效的图像语义分割研究方法大部分都是基于全卷积神经网络(FCNN),尽管现有的语义分割方法能有效地对图像进行整体分割,但对于图像中的重叠遮挡物体不能清晰地识别出边缘信息,也不能有效地融合图像高低层的特征信息.针对以上问题,在采用FCNN来解决图像语义分割问题的基础上,利用...     

基于编码器-解码器的半监督图像语义分割

基于深度卷积神经网络的图像语义分割方法需要大量像素级标注的训练数据,但标注的过程费时又费力.本文基于生成对抗网络提出一种编码-解码结构的半监督图像语义分割方法,其中编码器-解码器模块作为生成器,整个网络通过耦合标准多分类交叉熵损失和对抗损失进行训练.为充分利用浅层网络包含的丰富的语义信息,本文将编码器中不同尺度的特征输入到分类器,并将得到的不同粒度的分类结果融合,进而优化目标边界.此外,鉴别器通过发现无标签数据分割结果中的可信区域,以此提供额外的监督信号,来实现半监督学习.在PASCAL VOC 2012和Cityscapes上的实验表明,本文提出的方法优于现有的半监督图像语义分割方法.     

Deep learning techniques for tumor segmentation: a review

Recently, deep learning, especially convolutional neural networks, has achieved the remarkable results in natural image classification and segmentation. At the same time, in the field of medical image segmentation, researchers use deep learning techniques for tasks such as tumor segmentation, cell segmentation, and organ segmentation. Automatic tumor segmentation plays an important role in radiotherapy and clinical practice and is the basis for the implementation of follow-up treatment programs. This paper reviews the tumor segmentation methods based on deep learning in recent years. We first introduce the common medical image types and the evaluation criteria of segmentation results in tumor segmentation. Then, we review the tumor segmentation methods based on deep learning from technique view and tumor view, respectively. The technique view reviews the researches from the architecture of the deep learning and the tumor view reviews from the type of tumors.

     

残差密集空间金字塔网络的城市遥感图像分割

目的 遥感图像语义分割是根据土地覆盖类型对图像中每个像素进行分类,是遥感图像处理领域的一个重要研究方向。由于遥感图像包含的地物尺度差别大、地物边界复杂等原因,准确提取遥感图像特征具有一定难度,使得精确分割遥感图像比较困难。卷积神经网络因其自主分层提取图像特征的特点逐步成为图像处理领域的主流算法,本文将基于残差密集空间金字塔的卷积神经网络应用于城市地区遥感图像分割,以提升高分辨率城市地区遥感影像语义分割的精度。方法 模型将带孔卷积引入残差网络,代替网络中的下采样操作,在扩大特征图感受野的同时能够保持特征图尺寸不变;模型基于密集连接机制级联空间金字塔结构各分支,每个分支的输出都有更加密集的感受野信息;模型利用跳线连接跨层融合网络特征,结合网络中的高层语义特征和低层纹理特征恢复空间信息。结果 基于ISPRS （International Society for Photogrammetry and Remote Sensing） Vaihingen地区遥感数据集展开充分的实验研究,实验结果表明,本文模型在6种不同的地物分类上的平均交并比和平均F₁值分别达到69.88%和81.39%,性能在数学指标和视觉效果上均优于SegNet、pix2pix、Res-shuffling-Net以及SDFCN （symmetrical dense-shortcut fully convolutional network）算法。结论 将密集连接改进空间金字塔池化网络应用于高分辨率遥感图像语义分割,该模型利用了遥感图像不同尺度下的特征、高层语义信息和低层纹理信息,有效提升了城市地区遥感图像分割精度。     

基于全卷积网络的图像语义分割方法综述

自全卷积网络(Fully Convolutional Network,FCN)提出以后,应用深度学习技术在图像语义分割领域受到了许多计算机视觉和机器学习研究者的关注,现在这一方向已经成为人工智能方向的研究热点.FCN的核心思想是搭建一个全卷积网络,输入任意尺寸的图像,经过模型的有效学习和推理得到相同尺寸的输出.FCN的提出给图像语义分割领域提供了新的思路,但也存在很多的缺点,比如特征分辨率低、对象存在多尺度问题等.随着研究者不断的钻研,卷积神经网络在图像分割领域逐渐得到了优化和拓展,基于FCN的主流分割框架也层出不穷.图像语义分割对于场景理解的重要性日渐突出,被广泛应用到无人驾驶技术、无人机领域和医疗影像检测与分析等任务中.因此,对图像语义分割领域的研究将值得深入研究,使其能够更好在实际应用中大放异彩.     

聚焦—识别网络架构的细粒度图像分类

目的 细粒度图像分类是指对一个大类别进行更细致的子类划分,如区分鸟的种类、车的品牌款式、狗的品种等。针对细粒度图像分类中的无关信息太多和背景干扰问题,本文利用深度卷积网络构建了细粒度图像聚焦—识别的联合学习框架,通过去除背景、突出待识别目标、自动定位有区分度的区域,从而提高细粒度图像分类识别率。方法 首先基于Yolov2（youonly look once v2）的网络快速检测出目标物体,消除背景干扰和无关信息对分类结果的影响,实现聚焦判别性区域,之后将检测到的物体（即Yolov2的输出）输入双线性卷积神经网络进行训练和分类。此网络框架可以实现端到端的训练,且只依赖于类别标注信息,而无需借助其他的人工标注信息。结果 在细粒度图像库CUB-200-2011、Cars196和Aircrafts100上进行实验验证,本文模型的分类精度分别达到84.5%、92%和88.4%,与同类型分类算法得到的最高分类精度相比,准确度分别提升了0.4%、0.7%和3.9%,比使用两个相同D（dence）-Net网络的方法分别高出0.5%、1.4%和4.5%。结论 使用聚焦—识别深度学习框架提取有区分度的区域对细粒度图像分类有积极作用,能够滤除大部分对细粒度图像分类没有贡献的区域,使得网络能够学习到更多有利于细粒度图像分类的特征,从而降低背景干扰对分类结果的影响,提高模型的识别率。     

基于场景理解与改进型BUG算法的移动机器人避障

针对现有移动机器人在视觉避障上存在的局限,将深度学习算法和路径规划技术相结合,提出了一种基于深层卷积神经网络和改进Bug算法的机器人避障方法;该方法采用多任务深度卷积神经网络提取道路图像特征,实现图像分类和语义分割任务;其次,基于语义分割结果构建栅格地图,并将图像分类结果与改进的Bug算法相结合,搜索出最优避障路径;同时,为降低冗余计算,设计了特征对比结构来对避免对重复计算的特征信息,保障机器人在实际应用中实时性;通过实验结果表明,所提方法有效的平衡了多视觉任务的精度与效率,并能准确规划出安全的避障路径,辅助机器人完成导航避障。     

基于深度学习的涂层织物折皱识别与检测

涂层织物在生产制造和使用中易产生折皱损伤,人工折皱检测效率较低,传统图像处理方法的检测精度无法满足要求。提出一种基于深度卷积神经网络的涂层织物折皱识别和检测方法。通过标准揉搓试验建立数据集,网络编码和解码器分别采用多尺度特征融合结构和优化上采样模块,使用形态学方法进行折皱几何信息的实时统计。当前检测方法准确率达到95.78%,比传统语义分割技术及其他深度学习模型有很大的提升。     

Fusion of multispectral data through illumination-aware deep neural networks for pedestrian detection

Multispectral pedestrian detection has received extensive attention in recent years as a promising solution to facilitate robust human target detection for around-the-clock applications (e.g., security surveillance and autonomous driving). In this paper, we demonstrate illumination information encoded in multispectral images can be utilized to boost the performance of pedestrian detection significantly. A novel illumination-aware weighting mechanism is present to depict illumination condition of a scene accurately. Such illumination information is incorporated into two-stream deep convolutional neural networks to learn multispectral human-related features under different illumination conditions (daytime and nighttime). Moreover, we utilized illumination information together with multispectral data to generate more accurate semantic segmentation which is used to supervise the training of pedestrian detector. Putting all of the pieces together, we present an effective framework for multispectral pedestrian detection based on multi-task learning of illumination-aware pedestrian detection and semantic segmentation. Our proposed method is trained end-to-end using a well-designed multi-task loss function and outperforms state-of-the-art approaches on KAIST multispectral pedestrian dataset.     

YOLOv3和双线性特征融合的细粒度图像分类

目的 细粒度图像分类是计算机视觉领域具有挑战性的课题,目的是将一个大的类别分为更详细的子类别,在工业和学术方面都有着十分广泛的研究需求。为了改善细粒度图像分类过程中不相关背景干扰和类别差异特征难以提取的问题,提出了一种将目标检测方法YOLOv3（you only look once）和双线性融合网络相结合的细粒度分类优化算法,以此提高细粒度图像分类的性能。方法 利用重新训练过的目标检测算法YOLOv3粗略确定目标在图像中的位置;使用背景抑制方法消除目标以外的信息干扰;利用融合不同通道、不同层级卷积层特征的方法对经典的细粒度分类算法双线性卷积神经网络（bilinear convolutional neural network,B-CNN）进行改进,优化分类性能,通过融合双线性网络中不同卷积层的特征向量,得到更加丰富的互补信息,从而提高细粒度分类精度。结果 实验结果表明,在CUB-200-2011（Caltech-UCSD Birds-200-2011）、Cars196和Aircrafts100数据集中,本文算法的分类准确率分别为86.3%、92.8%和89.0%,比经典的B-CNN细粒度分类算法分别提高了2.2%、1.5%和4.9%,验证了本文算法的有效性。同时,与已有细粒度图像分类算法相比也表现出一定的优势。结论 改进算法使用YOLOv3有效滤除了大量无关背景,通过特征融合方法来改进双线性卷积神经分类网络,丰富特征信息,使分类的结果更加精准。     

图像理解中的卷积神经网络

近年来,卷积神经网络（Convolutional neural networks,CNN）已在图像理解领域得到了广泛的应用,引起了研究者的关注. 特别是随着大规模图像数据的产生以及计算机硬件（特别是GPU）的飞速发展,卷积神经网络以及其改进方法在图像理解中取得了突破性的成果,引发了研究的热潮. 本文综述了卷积神经网络在图像理解中的研究进展与典型应用. 首先,阐述卷积神经网络的基础理论;然后,阐述其在图像理解的具体方面,如图像分类与物体检测、人脸识别和场景的语义分割等的研究进展与应用.     

A survey of deep learning methods and software tools for image classification and object detection

Deep learning methods for image classification and object detection are overviewed. In particular we consider such deep models as autoencoders, restricted Boltzmann machines and convolutional neural networks. Existing software packages for deep learning problems are compared.     

基于深度学习的实例分割研究进展

目标检测确定检测图像中目标对象所在区域及其类别,语义分割对检测图像实现像素级分类,实例分割可以定义为同时解决目标检测与语义分割问题,在分类的同时确定每个目标实例语义。实例分割网络在无人机驾驶、机器人抓取、工业筛检等领域具有重要应用意义,针对目前基于深度学习实例分割综述性文章的空白,对实例分割进展进行概述,按照单阶段实例分割与双阶段实例分割的分类对不同网络模型进行论述,重点介绍近两年网络框架的发展,总结各网络特点的同时提出未来发展方向。