A framework for visual-context-aware object detection in still images

Visual context provides cues about an object’s presence, position and size within the observed scene, which should be used to increase the performance of object detection techniques. However, in computer vision, object detectors typically ignore this information. We therefore present a framework for visual-context-aware object detection. Methods for extracting visual contextual information from still images are proposed, which are then used to calculate a prior for object detection. The concept is based on a sparse coding of contextual features, which are based on geometry and texture. In addition, bottom-up saliency and object co-occurrences are exploited, to define auxiliary visual context. To integrate the individual contextual cues with a local appearance-based object detector, a fully probabilistic framework is established. In contrast to other methods, our integration is based on modeling the underlying conditional probabilities between the different cues, which is done via kernel density estimation. This integration is a crucial part of the framework which is demonstrated within the detailed evaluation. Our method is evaluated using a novel demanding image data set and compared to a state-of-the-art method for context-aware object detection. An in-depth analysis is given discussing the contributions of the individual contextual cues and the limitations of visual context for object detection.     

Salient object detection via region contrast and graph regularization基于区域对比度和图正则化的显著目标检测

Detection of salient objects in an image is now gaining increasing research interest in computer vision community. In this study, a novel region-contrast based saliency detection solution involving three phases is proposed. First, a color-based super-pixels segmentation approach is used to decompose the image into regions. Second, three high-level saliency measures which could effectively characterize the salient regions are evaluated and integrated in an effective manner to produce the initial saliency map. Finally, we construct a pairwise graphical model to encourage that adjacent image regions with similar features take continuous saliency values, thus producing the more perceptually consistent saliency map. We extensively evaluate the proposed method on three public benchmark datasets, and show it can produce promising results when compared to 14 state-of-the-art salient object detection approaches.     

自适应多维特征减少的模糊C-均值遥感图像分割算法

针对传统分割算法难以对遥感图像进行有效分割的问题,提出了一种自适应特征减少的图像分割算法。首先对源图像进行超像素分割,将获得的超像素作为算法的基本操作对象。其次,提取图像的颜色、纹理、边缘以及空间等多维特征,并使用加权像素值来表示超像素的特征。再者,将模糊分离度量加入到FRFCM(feature-reduction fuzzy C-means)模型中,构造特征减少分割算法。该算法可以自动选择有用特征。最后对分割算法进行优化,获取最终分割结果。通过遥感图像分割实验表明,提出算法能有效分割遥感图像,在分割准确度、运行时间、消除噪声影响等性能方面优于其他同类算法。     

基于联合约束策略和稀疏表示的图像分割

基于像素级的交互式图像分割算法对初始种子位置和噪声敏感,同时仅基于超像素的分割方法无法保留图像细节经常导致分割结果出现欠分割问题。针对上述问题,提出超像素/像素约束和稀疏表示的图像分割模型。该方法利用高斯函数分别对像素和超像素构造了相互约束的代价函数,引入了稀疏分解对模型进行优化以提升模型对图像噪声的鲁棒性,最后利用联合优化策略对代价函数求解估计出目标和背景标记实现目标提取。实验结果表明,与现有的分割方法相比,提出的方法能获得较好的分割效果,对高斯噪声和椒盐噪声具有较强的鲁棒性。     

一种基于超像素的肿瘤自动攻击交互式分割算法

交互式分割对于选取图像中感兴趣的对象很有意义.在图像处理领域中有着很重要的地位,具有广泛的应用,至今仍然是一个研究的热点问题.然而,逐像素执行交互式分割通常是耗时的.本文提出了一种新的分割方法.在Growcut算法框架下,提出基于超像素的肿瘤自动攻击（TA）分割.其中,超像素可以提供强大的边界信息来引导分割,且可以由过分割算法很容易来获取.TA与细胞自动攻击算法（CA）有着相似的原理,给定少量的用户标记目标的超像素,可以由TA完成目标分割任务,处理速度比Growcut算法快.此外,为获得最佳效果,应用了水平集和多层TA方法来进行边界的调整.在VOC挑战分割数据集上进行的实验表明,所提出的分割算法性能表现优异,高效和精准,且能处理多目标分割任务.     

Image saliency detection using Gabor texture cues

Image saliency analysis plays an important role in various applications such as object detection, image compression, and image retrieval. Traditional methods for saliency detection ignore texture cues. In this paper, we propose a novel method that combines color and texture cues to robustly detect image saliency. Superpixel segmentation and the mean-shift algorithm are adopted to segment an original image into small regions. Then, based on the responses of a Gabor filter, color and texture features are extracted to produce color and texture sub-saliency maps. Finally, the color and texture sub-saliency maps are combined in a nonlinear manner to obtain the final saliency map for detecting salient objects in the image. Experimental results show that the proposed method outperforms other state-of-the-art algorithms for images with complex textures.     

Saliency detection via image sparse representation and color features combination

Saliency detection is a technique to analyze image surroundings to extract relevant regions from the background. In this paper, we propose a simple and effective saliency detection method based on image sparse representation and color features combination. First, the input image is segmented into non-overlapping super-pixels, so as to perform the saliency detection at the region level to reduce computational complexity. Then, a background optimization selection scheme is used to construct an appropriate background template. Based on this, a primary saliency map is obtained by using image sparse representation. Next, through the linear combination of color coefficients we generate an improved saliency map with more prominent salient regions. Finally, the two saliency maps are integrated within Bayesian framework to obtain the final saliency map. Experimental results show that the proposed method has desirable detection performance in terms of detection accuracy and running time.

     

Context based object categorization: A critical survey

The goal of object categorization is to locate and identify instances of an object category within an image. Recognizing an object in an image is difficult when images include occlusion, poor quality, noise or background clutter, and this task becomes even more challenging when many objects are present in the same scene. Several models for object categorization use appearance and context information from objects to improve recognition accuracy. Appearance information, based on visual cues, can successfully identify object classes up to a certain extent. Context information, based on the interaction among objects in the scene or global scene statistics, can help successfully disambiguate appearance inputs in recognition tasks. In this work we address the problem of incorporating different types of contextual information for robust object categorization in computer vision. We review different ways of using contextual information in the field of object categorization, considering the most common levels of extraction of context and the different levels of contextual interactions. We also examine common machine learning models that integrate context information into object recognition frameworks and discuss scalability, optimizations and possible future approaches.     

基于多尺度上下文的图像标注算法

提出了一种在层次化分割框架下,通过结合图像的底层局部特征以及高层的上下文特征,进行图像自动语义标注的新算法. 该算法的核心思想在于对较大的图像区域的识别结果有利于对其包含的较小图像区域进行识别.算法首先对每层分割后的图像区域进行识别, 然后利用贝叶斯定理将各层区域识别的结果通过线性加权的方式进行融合,从而达到对整幅图像进行自动语义标注的目的.与现有的图像标注算法相比,仿真实验表明本文算法获得了最好的标注精度以及最快的标注速度.     

基于超像素的印刷品色差在线检测方法

针对彩色印刷行业中,印刷品色差在线检测准确率低、速度慢的问题,提出一种新的检测方法.基于超像素的思想,采用简单线性迭代聚类(SLIC,simple linear iterative clustering)算法,对具有相似特征的相邻像素进行聚类,形成结构紧凑、近似均匀的像素块,每个像素块即为一个超像素.用超像素代替像素块内多个相似像素,分别提取标准图像和待检测图像的颜色特征.再用CIEDE2000色差公式进行色差计算.实验结果表明,该方法在保证检测结果准确率的基础上,能够有效地减少数据计算量,提高检测效率.     

基于邻域优化机制的图像显著性目标检测

在显著性目标检测中,背景区域和前景区域区分度不高会导致检测结果不理想。针对这一问题,提出一种基于邻域优化机制的图像显著性目标检测算法。首先对图像进行超像素分割;然后在CIELab颜色空间建立对比图和分布图,并通过一种新的合并方式进行融合;最后在空间距离等约束下,建立邻域更新机制,对初始显著性图进行优化。实验对比表明,该算法显著性目标检测效果更好。     

A novel change detection approach based on visual saliency and random forest from multi-temporal high-resolution remote-sensing images

ABSTRACT

This article presents a novel change detection (CD) approach for high-resolution remote-sensing images, which incorporates visual saliency and random forest (RF). First, highly homogeneous and compact image super-pixels are generated using super-pixel segmentation, and the optimal segmentation result is obtained through image superimposition and principal component analysis. Second, saliency detection is used to guide the search of interest regions in the initial difference image obtained via the improved robust change vector analysis algorithm. The salient regions within the difference image that correspond to the binarized saliency map are extracted, and the regions are subject to the fuzzy c-means (FCM) clustering to obtain the pixel-level pre-classification result, which can be used as a prerequisite for super-pixel-based analysis. Third, on the basis of the optimal segmentation and pixel-level pre-classification results, different super-pixel change possibilities are calculated. Furthermore, the changed and unchanged super-pixels that serve as the training samples are automatically selected. The spectral features and Gabor features of each super-pixel are extracted. Finally, super-pixel-based CD is implemented by applying RF based on these samples. Experimental results on Quickbird, Ziyuan 3 (ZY3), and Gaofen 2 (GF2) multi-spectral images show that the proposed method outperforms the compared methods in the accuracy of CD, and also confirm the feasibility and effectiveness of the proposed approach.     

面向多模态交互式融合与渐进式优化的三维视觉理解

三维视觉理解旨在智能地感知和解释三维场景,实现对物体、环境和动态变化的深入理解与分析。三维目标检测作为其核心技术,发挥着不可或缺的作用。针对当前的三维检测算法对于远距离目标和小目标检测精度较低的问题,提出了一种面向多模态交互式融合与渐进式优化的三维目标检测方法MIFPR。在特征提取阶段,首先引入自适应门控信息融合模块。通过把点云的几何特征融入图像特征中,能够获取对光照变化更有辨别力的图像表示。随后提出基于体素质心的可变形跨模态注意力模块,以驱使图像中丰富的语义特征和上下文信息融合到点云特征中。在目标框优化阶段,提出渐进式注意力模块,通过学习、聚合不同阶段的特征,不断增强模型对于精细化特征的提取与建模能力,逐步优化目标框,以提升对于远距离、小目标的检测精度,进而提高对于视觉场景理解的能力。在KITTI数据集上,所提方法对于Pedestrian和Cyclist等小目标的检测精度较最优基线有明显提升,证实了该方法的有效性。     

构建近邻上下文的拷贝图像检索

目的 以词袋模型为基础的拷贝图像检索方法是当前最有效的方法。然而,由于局部特征量化存在信息损失,导致视觉词汇区别能力不足和视觉词汇误匹配增加,从而影响了拷贝图像检索效果。针对视觉词汇的误匹配问题,提出一种基于近邻上下文的拷贝图像检索方法。该方法通过局部特征的上下文关系消除视觉词汇歧义,提高视觉词汇的区分度,进而提高拷贝图像的检索效果。方法 首先,以距离和尺度关系选择图像中某局部特征点周围的特征点作为该特征点的上下文,选取的上下文中的局部特征点称为近邻特征点;再以近邻特征点的信息以及与该局部特征的关系为该局部特征构建上下文描述子;然后,通过计算上下文描述子的相似性对局部特征匹配对进行验证;最后,以正确匹配特征点的个数衡量图像间的相似性,并以此相似性选取若干候选图像作为返回结果。结果 在Copydays图像库进行实验,与Baseline方法进行比较。在干扰图像规模为100 k时,相对于Baseline方法,mAP提高了63%。当干扰图像规模从100 k增加到1 M时,Baseline的mAP值下降9%,而本文方法下降3%。结论 本文拷贝图像检索方法对图像编辑操作,如旋转、图像叠加、尺度变换以及裁剪有较高的鲁棒性。该方法可以有效地应用到图像防伪、图像去重等领域。     

A new image co-segmentation method using saliency detection for surveillance image of coal miners

In this paper, we propose a co-segmentation method using saliency detection. The input image is first over-segmented into super-pixels, in which, their similarities are measured by the Bhattacharyya coefficients. The proposed method uses the combination of detection results of different detection methods on different types of color space to produce the originating regions, in which optimized linear coefficient combination is exploited. Experiments are performed on different image databases and results comparable to that of some current state-of-the-art methods are provided.     

融合区域和边缘特征的水平集水下图像分割

目的 水平集模型是图像分割中的一种先进方法,在陆地环境图像分割中展现出较好效果。特征融合策略被广泛引入到该模型框架,以拉伸目标-背景对比度,进而提高对高噪声、杂乱纹理等多类复杂图像的处理性能。然而,在水下环境中,由于水体高散射、强衰减等多因素的共同作用,使得现有图像特征及水平集模型难以适用于对水下图像的分割任务,分割结果与目标形态间存在较大差异。鉴于此,提出一种适用于水下图像分割的区域-边缘水平集模型,以提高水下图像目标分割的准确性。方法 综合应用图像的区域特征及边缘特征对水下目标进行辨识。对于区域特征,引入水下图像显著性特征;对于边缘特征,创新性地提出了一种基于深度信息的边缘特征提取方法。所提方法在融合区域级和边缘级特征的基础上,引入距离正则项对水平集函数进行规范,以增强水平集函数演化的稳定性。结果 基于YouTube和Bubblevision的水下数据集的实验结果表明,所提方法不仅对高散射强衰减的低对比度水下图像实现较好的分割效果,同时对处理强背景噪声图像也有较好的鲁棒性,与水平集分割方法（local pre-fitting,LPF）相比,分割精确度至少提高11.5%,与显著性检测方法（hierarchical co-salient detection via color names,HCN）相比,精确度提高6.7%左右。结论 实验表明区域-边缘特征融合以及其基础上的水平集模型能够较好地克服水下图像分割中的部分难点,所提方法能够较好分割水下目标区域并拟合目标轮廓,与现有方法对比获得了较好的分割结果。     

Depth-assisted rectification for real-time object detection and pose estimation

RGB-D sensors have become in recent years a product of easy access to general users. They provide both a color image and a depth image of the scene and, besides being used for object modeling, they can also offer important cues for object detection and tracking in real time. In this context, the work presented in this paper investigates the use of consumer RGB-D sensors for object detection and pose estimation from natural features. Two methods based on depth-assisted rectification are proposed, which transform features extracted from the color image to a canonical view using depth data in order to obtain a representation invariant to rotation, scale and perspective distortions. While one method is suitable for textured objects, either planar or non-planar, the other method focuses on texture-less planar objects. Qualitative and quantitative evaluations of the proposed methods are performed, showing that they can obtain better results than some existing methods for object detection and pose estimation, especially when dealing with oblique poses.     

提取目标区域词袋特征的图像分类方法

规则网格是视觉词袋模型中常用的图像检测方法,该方法抽取图像所有区块,获得背景区块和目标区块完整的图像信息。事实上,抽取的背景区块信息对类别的判定往往会有一定的混淆作用。以“摩托车”类和“小汽车”类的图像为例,这两类图像背景特征相似,大多都是道路,一般的分类方法很可能将它们分为相同类别。可见,背景信息会干扰图像分类结果。因此,提出一种提取目标区域词袋特征的图像分类方法。利用图像分割去除背景信息提取目标区域;对目标区域构建视觉词袋模型;使用SVM分类器对图像进行分类。PASCAL VOC2006及PASCAL VOC2010数据集上的实验结果表明,提取目标区域词袋特征的图像分类方法具有较好的分类性能。     

Inference Methods for CRFs with Co-occurrence Statistics

The Markov and Conditional random fields (CRFs) used in computer vision typically model only local interactions between variables, as this is generally thought to be the only case that is computationally tractable. In this paper we consider a class of global potentials defined over all variables in the CRF. We show how they can be readily optimised using standard graph cut algorithms at little extra expense compared to a standard pairwise field. This result can be directly used for the problem of class based image segmentation which has seen increasing recent interest within computer vision. Here the aim is to assign a label to each pixel of a given image from a set of possible object classes. Typically these methods use random fields to model local interactions between pixels or super-pixels. One of the cues that helps recognition is global object co-occurrence statistics, a measure of which classes (such as chair or motorbike) are likely to occur in the same image together. There have been several approaches proposed to exploit this property, but all of them suffer from different limitations and typically carry a high computational cost, preventing their application on large images. We find that the new model we propose produces a significant improvement in the labelling compared to just using a pairwise model and that this improvement increases as the number of labels increases.     

国画的艺术目标分割及深度学习与分类

目的 现有对艺术画进行分类的文献大多对整幅画作直接进行特征提取,但任何图像内容特征的可适应性都存在一定的局限性。画家画不同艺术目标的笔锋和艺术处理往往是不同的,如果不考虑每个笔锋所产生的条件而一味地分析笔锋的走向和力度分布等将会是很盲目的。为此提出一种基于艺术目标的中国画分类算法。方法 首先,基于简单线性迭代聚类算法根据像素间颜色和位置的相差程度来生成超像素;其次,提出针对艺术目标的最大相似度区域合并算法交互式地进行艺术目标分割,将国画分割成一系列的艺术目标,如马、人物等,以提取画家用来表现艺术形式和抒发情感的相对稳定单元;然后利用深度卷积神经网络（O-CNN）来描述这些艺术目标的高级语义特征;最后,引入支持向量机对每幅中国画内的各种艺术目标的分类结果进行最后的融合与分类。结果 本文针对艺术目标进行国画的学习和分类,实现了对样本库中10位画家中国画的识别,平均准确率为89%。实验结果表明,本文算法在平均查全率和查准率上优于现有的MHMM （The 2D multi-resolution hidden Markov model）和Fusion等方法。结论 本文的成果可用于中国画的数字化分析、管理、理解和识别,为中国画传承和鉴赏提供有效的数字工具。