基于复原图像特征与深度视觉特征融合的锑粗选异常工况识别

本文针对锑粗选异常工况下泡沫层高度改变,导致位置固定的工业相机采集到的泡沫图像存在离焦模糊的问题,提出了一种基于泡沫复原图像特征和深度视觉特征融合的锑粗选异常工况识别方法.该方法首先通过分析不同工况下模糊泡沫图像的特点,采用基于L0和L2正则项的模糊核估计方法提取了模糊核零范数特征,再利用L–R算法提取了灰度平均梯度差特征.其次,为了往更深层次挖掘异常工况下模糊泡沫图像的特征信息,本文采用迁移学习方法,基于InceptionResNetV1深度神经网络,利用大量泡沫图像数据对深度神经网络进行微调,进而提取泡沫图像的深度视觉特征.最后,基于XGBoost机器学习算法,先对高维视觉特征进行降维,再融合复原图像特征与深度视觉特征,对不同工况下的泡沫图像进行分类识别.锑粗选实验结果表明,该方法能够有效降低样本错分率,提高锑粗选异常工况识别率.     

基于深度学习特征字典的单帧图像超分辨率重建

在基于字典的单帧图像超分辨率重建算法中,依赖人工浅层特征设计的字典表达图像特征能力有限。为此,提出基于深度学习特征字典的超分辨重建方法。该算法首先利用深度网络进行高、低分辨率训练样本图像深层次特征学习;然后,在稀疏字典超分辨框架下联合训练特征字典;最后,输入单帧低分辨率图像并利用该字典实现超分辨率重建。理论分析表明,引入深度网络提取图像深层次特征并用于字典训练,对低分辨率图像的高频信息补充更加有利。实验证明,与双三次插值以及基于一般人工特征字典的超分辨重建算法相比,本文算法的主观视觉和客观评价指标均高于对比算法。     

融合显著信息的层次特征学习图像分类

高效的图像特征表示是计算机视觉的基础.基于图像的视觉显著性机制及深度学习模型的思想,提出一种融合图像显著性的层次稀疏特征表示用于图像分类.这种层次特征学习每一层都由3个部分组成:稀疏编码、显著性最大值汇聚(saliency max pooling)和对比度归一化.通过在图像层次稀疏表示中引入图像显著信息,加强了图像特征的语义信息,得到图像显著特征表示.相比于手工指定特征,该模型采用无监督数据驱动的方式直接从图像中学习到有效的图像特征描述.最后采用支持向量机(support vector machine,SVM)分类器进行监督学习,实现对图像进行分类.在2个常用的标准图像数据集(Caltech 101和Caltech 256)上进行的实验结果表明,结合图像显著性信息的层次特征表示,相比于基于局部特征的单层稀疏表示在分类性能上有了显著提升.     

基于深度卷积特征的细粒度图像分类研究综述

细粒度图像分类问题是计算机视觉领域一项极具挑战的研究课题,其目标是对子类进行识别,如区分不同种类的鸟.由于子类别间细微的类间差异和较大的类内差异,传统的分类算法不得不依赖于大量的人工标注信息.近年来,随着深度学习的发展,深度卷积神经网络为细粒度图像分类带来了新的机遇.大量基于深度卷积特征算法的提出,促进了该领域的快速发展.本文首先从该问题的定义以及研究意义出发,介绍了细粒度图像分类算法的发展现状.之后,从强监督与弱监督两个角度对比分析了不同算法之间的差异,并比较了这些算法在常用数据集上的性能表现.最后,我们对这些算法进行了总结,并讨论了该领域未来可能的研究方向及其面临的挑战.     

基于多特征融合的显著性目标检测算法

显著性目标检测是获取图像中视觉显著目标的任务,它是计算机视觉及相关研究领域的重要内容。当前在复杂的自然场景下基于深度学习的算法依然存在特征学习不足和检测错误率较高的问题,因此提出一种新颖的基于多特征融合的显著性目标检测算法。以HDHF(hybrid deep and handcrafted feature)模型的预测显著图作为特征,融合全局像素的深度特征。此外,利用显著性提名获取候选目标的位置,并在各候选目标中添加中心先验。在全卷积神经网络中,利用前向传播算法最终预测得到像素级的显著性目标。在四个包含多个显著性目标和复杂背景的图像数据集上进行验证,实验结果表明,该算法有效地提高了复杂场景下显著性目标的检测精度,尤其是在背景复杂的图像上具有较优的检测效果。     

基于卷积神经网络的军事图像分类

由于军事背景下战场上不同目标的相似度极高以及复杂情况下的分类识别率不高,传统视觉特征的分类精度已不能满足要求。针对含有特定军事目标的大规模图像分类问题构造了一种新的基于主成分分析(Principal Components Analysis, PCA)白化的卷积神经网络结构,有效地降低数据间的相关性,加强学习能力,提高目标分类的准确率。利用大规模的军事图像数据集对该模型进行了识别精度评估,实验表明,与基于视觉特征的词袋模型以及经典的卷积神经网络分类算法相比,该算法对于军事目标的分类精度有明显提高。     

基于深度学习的目标检测算法研究综述

传统的目标检测算法主要依赖于人工选取的特征来对物体进行检测。人工提取的特征对主要针对某些特定对象,比如有的特征适合做边缘检测,有的适合做纹理检测,不具有普遍性。近年来,深度学习蓬勃发展,在计算机视觉领域比如图像分类、目标检测、图像语义分割等方面取得了重大的进展。深度学习作为一种特征学习方法能够自动学习到目标的有用特征,避免了人工提取特征,同时能够保证良好的检测效果。本文首先介绍基于深度学习的目标检测算法研究进展,其次总结目标检测算法中常见的难题与解决措施,最后对目标检测算法的可能发展方向进行展望。     

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。     

基于全局优化策略的场景分类算法

提出一种基于全局优化策略的场景分类算法.该算法基于整幅图像提取全局场景特征——空间包络特征.从图像块中提取视觉单词,且定义隐变量表示该视觉单词语义,然后引入隐状态结构图描述整幅图像的视觉单词上下文;在场景分类策略上,构造由相容函数组成的目标函数,其中相容函数度量全局场景特征、隐变量与场景类别标记的相容度,通过求解目标函数的全局最优解推断图像的场景类别标记.在标准场景图像库上的对比实验表明该算法优于当前有代表性的场景分类算法.     

基于潜子空间去噪的子空间学习图像分类方法

针对判别最小二乘回归(DLSR)对图像噪声鲁棒性不佳的问题,提出一种基于潜子空间去噪的子空间学习图像分类方法(DLSSL).该方法在架构上不同于现有基于回归的分类方法,其在视觉空间与标签空间中引入一个潜在子空间,将传统的图像分类框架改进为两步,即先降噪后分类.该方法先通过欠完备自编码将数据的高阶特征提取到潜在空间,再利用此高阶特征进行回归分类,同时辅以组核范数约束控制类内样本间距离.潜在子空间的引入为算法框架带来了更多灵活性,缓解了视觉空间与标签空间中数据维度与特性的差异,使得欠完备自编码可以有效地对数据进行降噪,提升了分类算法的鲁棒性.在人脸、生物指纹、物体和深度特征数据集上设计了多组对比实验,实验结果表明,算法对于图像中的噪声具有较强的鲁棒性,获得的投影矩阵具有良好的判别性,相比现有图像分类算法,性能更好、普适性更强,能有效地运用于各种图像分类任务.     

Visual tracking based on hierarchical framework and sparse representation

As the main challenge for object tracking is to account for drastic appearance change, a hierarchical framework that exploits the strength of both generative and discriminative models is devised in this paper. Our hierarchical framework consists of three appearance models: local-histogram-based model, weighted alignment pooling model, and sparsity-based discriminative model. Sparse representation is adopted in local-histogram-based model layer that considers the spatial information among local patches with a dual-threshold update schema to deal with occlusion. The weighted alignment pooling layer is introduced to weight the local image patches of the candidates after sparse representation. Different from the above two generative methods, the global discriminant model layer employs candidates to sparsely represent positive and negative templates. After that, an effective hierarchical fusion strategy is developed to fuse the three models via their similarities and the confidence. In addition, three reasonable online dictionary and template update strategies are proposed. Finally, experiments on various current popular image sequences demonstrate that our proposed tracker performs favorably against several state-of-the-art algorithms.     

Robust object recognition with cortex-like mechanisms

We introduce a new general framework for the recognition of complex visual scenes, which is motivated by biology: We describe a hierarchical system that closely follows the organization of visual cortex and builds an increasingly complex and invariant feature representation by alternating between a template matching and a maximum pooling operation. We demonstrate the strength of the approach on a range of recognition tasks: From invariant single object recognition in clutter to multiclass categorization problems and complex scene understanding tasks that rely on the recognition of both shape-based as well as texture-based objects. Given the biological constraints that the system had to satisfy, the approach performs surprisingly well: It has the capability of learning from only a few training examples and competes with state-of-the-art systems. We also discuss the existence of a universal, redundant dictionary of features that could handle the recognition of most object categories. In addition to its relevance for computer vision, the success of this approach suggests a plausibility proof for a class of feedforward models of object recognition in cortex     

Holistically-Nested Edge Detection

We develop a new edge detection algorithm that addresses two important issues in this long-standing vision problem: (1) holistic image training and prediction; and (2) multi-scale and multi-level feature learning. Our proposed method, holistically-nested edge detection (HED), performs image-to-image prediction by means of a deep learning model that leverages fully convolutional neural networks and deeply-supervised nets. HED automatically learns rich hierarchical representations (guided by deep supervision on side responses) that are important in order to resolve the challenging ambiguity in edge and object boundary detection. We significantly advance the state-of-the-art on the BSDS500 dataset (ODS F-score of 0.790) and the NYU Depth dataset (ODS F-score of 0.746), and do so with an improved speed (0.4 s per image) that is orders of magnitude faster than some CNN-based edge detection algorithms developed before HED. We also observe encouraging results on other boundary detection benchmark datasets such as Multicue and PASCAL-Context.     

Scale-Invariant Visual Language Modeling for Object Categorization

In recent years, ldquobag-of-wordsrdquo models, which treat an image as a collection of unordered visual words, have been widely applied in the multimedia and computer vision fields. However, their ignorance of the spatial structure among visual words makes them indiscriminative for objects with similar word frequencies but different word spatial distributions. In this paper, we propose a visual language modeling method (VLM), which incorporates the spatial context of the local appearance features into the statistical language model. To represent the object categories, models with different orders of statistical dependencies have been exploited. In addition, the multilayer extension to the VLM makes it more resistant to scale variations of objects. The model is effective and applicable to large scale image categorization. We train scale invariant visual language models based on the images which are grouped by Flickr tags, and use these models for object categorization. Experimental results show they achieve better performance than single layer visual language models and ldquobag-of-wordsrdquo models. They also achieve comparable performance with 2-D MHMM and SVM-based methods, while costing much less computational time.     

基于深度学习的双通道夜视图像复原方法

针对夜间场景光线微弱、能见度低导致夜视图像信噪比低、成像质量差的问题,提出了基于深度学习的双通道夜视图像复原方法。首先,用两种基于全连接多尺度残差学习分块（FMRB）的卷积神经网络（CNN）分别对红外夜视图像和微光夜视图像进行多尺度特征提取和层次特征融合,从而得到重建的红外图像和增强的微光图像;然后,两种处理后的图像通过自适应加权平均算法进行融合,并根据场景的不同自适应地凸显两个图像中具有更高显著性的有效信息;最后,得到分辨率高且视觉效果好的夜视复原图像。使用基于FMRB的深度学习网络得到的红外夜视重建图像,相较于卷积神经网络超分辨率（SRCNN）重建算法得到的在峰值信噪比（PSNR）和结构相似性（SSIM）的平均值上分别提升了3.56 dB和0.091 2;相较于MSRCR,得到的微光夜视增强图像在PSNR和SSIM的平均值上分别提升了6.82 dB和0.132 1。实验结果表明,所提方法得到的重建图像的清晰度明显得到改善,获得的增强图像的亮度也明显得到提升,而且前二者的融合图像的视觉效果较好,可见所提方法能有效改善夜视图像的复原效果。     

基于双通道R-FCN的图像篡改检测模型

随着大数据时代的到来和图像编辑软件的发展,恶意篡改图片的数量出现井喷式增长,为了确保图像的真实性,众多学者基于深度学习和图像处理技术提出了多种图像篡改检测算法.然而,当前提出的绝大多数方法在面对大量图片的情况下,篡改检测速率较低且小面积篡改区域检测效果较差.为了有效解决这些问题,本文首次将基于区域的全卷积网络(Regi...     

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。     

Hierarchical Reinforcement Learning With Automatic Sub-Goal Identification

In reinforcement learning an agent may explore ineffectively when dealing with sparse reward tasks where finding a reward point is difficult. To solve the problem, we propose an algorithm called hierarchical deep reinforcement learning with automatic sub-goal identification via computer vision (HADS) which takes advantage of hierarchical reinforcement learning to alleviate the sparse reward problem and improve efficiency of exploration by utilizing a sub-goal mechanism. HADS uses a computer vision method to identify sub-goals automatically for hierarchical deep reinforcement learning. Due to the fact that not all sub-goal points are reachable, a mechanism is proposed to remove unreachable sub-goal points so as to further improve the performance of the algorithm. HADS involves contour recognition to identify sub-goals from the state image where some salient states in the state image may be recognized as sub-goals, while those that are not will be removed based on prior knowledge. Our experiments verified the effect of the algorithm.