基于深度学习的图像显著对象检测

显著区域检测可应用在对象识别、图像分割、视 频/图像压缩中,是计算机视觉领域的重要研究主题。然而,基于不 同视觉显著特征的显著区域检测法常常不能准确地探测出显著对象且计算费时。近来,卷积 神经网络模型在图像分析和处理 领域取得了极大成功。为提高图像显著区域检测性能,本文提出了一种基于监督式生成对抗 网络的图像显著性检测方法。它 利用深度卷积神经网络构建监督式生成对抗网络,经生成器网络与鉴别器网络的不断相互对 抗训练,使卷积网络准确学习到 图像显著区域的特征,进而使生成器输出精确的显著对象分布图。同时,本文将网络自身误 差和生成器输出与真值图间的 L1距离相结合,来定义监督式生成对抗网络的损失函数,提升了显著区域检测精度。在MSRA 10K与ECSSD数据库上的实 验结果表明,本文方法 分别获得了94.19%与96.24%的准确率和93.99%与90.13%的召回率,F -Measure值也高达94.15%与94.76%,优于先 前常用的显著性检测模型。     

Finding spatio-temporal salient paths for video objects discovery

Many videos capture and follow salient objects in a scene. Detecting such salient objects is thus of great interests to video analytics and search. However, the discovery of salient objects in an unsupervised way is a challenging problem as there is no prior knowledge of the salient objects provided. Different from existing salient object detection methods, we propose to detect and track salient object by finding a spatio-temporal path which has the largest accumulated saliency density in the video. Inspired by the observation that salient video objects usually appear in consecutive frames, we leverage the motion coherence of videos into the path discovery and make the salient object detection more robust. Without any prior knowledge of the salient objects, our method can detect salient objects of various shapes and sizes, and is able to handle noisy saliency maps and moving cameras. Experimental results on two public datasets validate the effectiveness of the proposed method in both qualitative and quantitative terms. Comparisons with the state-of-the-art methods further demonstrate the superiority of our method on salient object detection in videos.     

Bayesian salient object detection based on saliency driven clustering

Salient object detection is essential for applications, such as image classification, object recognition and image retrieval. In this paper, we design a new approach to detect salient objects from an image by describing what does salient objects and backgrounds look like using statistic of the image. First, we introduce a saliency driven clustering method to reveal distinct visual patterns of images by generating image clusters. The Gaussian Mixture Model (GMM) is applied to represent the statistic of each cluster, which is used to compute the color spatial distribution. Second, three kinds of regional saliency measures, i.e, regional color contrast saliency, regional boundary prior saliency and regional color spatial distribution, are computed and combined. Then, a region selection strategy integrating color contrast prior, boundary prior and visual patterns information of images is presented. The pixels of an image are divided into either potential salient region or background region adaptively based on the combined regional saliency measures. Finally, a Bayesian framework is employed to compute the saliency value for each pixel taking the regional saliency values as priority. Our approach has been extensively evaluated on two popular image databases. Experimental results show that our approach can achieve considerable performance improvement in terms of commonly adopted performance measures in salient object detection.     

夜视图像彩色融合中基于谱残差的显著目标增强算法

根据人类视觉系统的特点,提出了一种基于谱残差、可在夜视图像彩色融合中的增强显著目标的算法.该方法在彩色融合过程中,利用谱残差确定显著目标范围,用5×5的像素大小窗口对显著目标进行定位.当像素邻域均值大于图像整体均值时,此像素位于显著目标,用红色凸显目标可达到增强彩色融合图像的目的.实验结果表明,该方法具有较强的稳定性和实用性,增强显著目标的效果较好.     

基于结构标签学习的显著性目标检测

提出了一种基于结构标签学习的显著性目标检测算法,将结构化学习方法应用到显著性目标检测中。首先从含有标记的图像中随机采集固定大小的矩形区域,并记录其结构标签;然后使用含结构标签的区域特征构建决策树集合;最后采用监督学习的方法对图像进行优化预测,得到最终的显著图。实验结果表明,本文方法能较准确地检测出图像库中图像的显著性区域,在数据库MSRA5000和BSD300的AUC值分别为0.891 8、0.705 2,说明本文方法具有较好的显著性检测效果。     

Color object detection using spatial-color joint probability functions.

Object detection in unconstrained images is an important image understanding problem with many potential applications. There has been little success in creating a single algorithm that can detect arbitrary objects in unconstrained images; instead, algorithms typically must be customized for each specific object. Consequently, it typically requires a large number of exemplars (for rigid objects) or a large amount of human intuition (for nonrigid objects) to develop a robust algorithm. We present a robust algorithm designed to detect a class of compound color objects given a single model image. A compound color object is defined as having a set of multiple, particular colors arranged spatially in a particular way, including flags, logos, cartoon characters, people in uniforms, etc. Our approach is based on a particular type of spatial-color joint probability function called the color edge co-occurrence histogram. In addition, our algorithm employs perceptual color naming to handle color variation, and prescreening to limit the search scope (i.e., size and location) for the object. Experimental results demonstrated that the proposed algorithm is insensitive to object rotation, scaling, partial occlusion, and folding, outperforming a closely related algorithm based on color co-occurrence histograms by a decisive margin.     

Tracklet clustering for robust multiple object tracking using distance dependent Chinese restaurant processes

To contrive an accurate and efficient strategy for object detection–object track assignment problem, we present a tracklet clustering approach using distance dependent Chinese restaurant processes (ddCRPs), which employ a two-level robust object tracker. The first level is an ordinary tracklet generator that obtains short yet reliable tracklets. In the second level, we cluster the tracklets over time based on color, spatial and temporal attributes, where the nonparametric process of clustering with ddCRPs allows us to maintain an unknown number of objects. Unlike the previously proposed Chinese restaurant processes and Dirichlet process mixture models, our ddCRPs method does not require prescribed complex cluster models to be initialized and updated, and thus, we can cluster complex tracklets by only computing similarities between them. Our comparative evaluations on tracking different object types demonstrate the generality of our approach.     

超像素内容感知先验的多尺度贝叶斯显著性检测方法

针对复杂背景下显著性检测方法不能够有效地抑制背景,进而准确地检测目标这一问题,提出了超像素内容感知先验的多尺度贝叶斯显著性检测方法.首先,将目标图像分割为多尺度的超像素图,在每个尺度上引入内容感知的对比度先验、中心位置先验、边界连通背景先验来计算单一尺度上的目标显著值;其次,融合多个尺度的内容感知先验显著值生成一个粗略的显著图;然后,将粗略显著图值作为先验概率,根据颜色直方图和凸包中心先验计算观测似然概率,再使用多尺度贝叶斯模型来获取最终显著目标;最后,使用了3个公开的数据集、5种评估指标、7种现有的方法进行对比实验,结果表明本文方法在显著性目标检测方面具有更好的表现.     

A CMA-ES-Based Adversarial Attack Against Black-Box Object Detectors

Object detection is one of the essential tasks of computer vision. Object detectors based on the deep neural network have been used more and more widely in safe-sensitive applications, like face recognition, video surveillance, autonomous driving, and other tasks. It has been proved that object detectors are vulnerable to adversarial attacks. We propose a novel black-box attack method, which can successfully attack regression-based and region-based object detectors. We introduce methods to reduce search dimensions, reduce the dimension of optimization problems and reduce the number of queries by using the Covariance matrix adaptation Evolution strategy (CMA-ES) as the primary method to generate adversarial examples. Our method only adds adversarial perturbations in the object box to achieve a precise attack. Our proposed attack can hide the specified object with an attack success rate of 86％ and an average number of queries of 5, 124, and hide all objects with a success rate of 74％and an average number of queries of 6, 154. Our work illustrates the effectiveness of the CMA-ES method to generate adversarial examples and proves the vulnerability of the object detectors against the adversarial attacks.     

融合颜色信息与深度信息的运动目标检测方法

基于颜色信息的运动目标检测易受光照、阴影等影响,基于深度信息的运动目标检测存在目标边缘噪声大,无法检测距离背景较近的目标等问题。针对上述问题,该文利用CCD相机获取的颜色信息及TOF相机获取的深度信息分别为每个像素建立颜色与深度信息的分类器,根据像素点的深度特征及前一帧的检测结果,自适应地为每个分类器的输出分配不同的权值,实现运动目标的检测。该文采集多组视频序列进行实验,实验结果表明该方法能有效解决单独利用颜色或深度信息进行运动目标检测时出现的问题。     

基于区域特征融合的RGBD显著目标检测

为了对各类自然场景中的显著目标进行检测,本文提出了一种将图像的深度信息引入区域显著性计算的方法,用于目标检测。首先对图像进行多尺度分割得到若干区域,然后对区域多类特征学习构建回归随机森林,采用监督学习的方法赋予每个区域特征显著值,最后采用最小二乘法对多尺度的显著值融合,得到最终的显著图。实验结果表明,本文算法能较准确地定位RGBD图像库中每幅图的显著目标。     

Depth-based detection with region comparison features

Most object detection approaches proposed over the years rely on visual features that help to segregate objects from their backgrounds. For instance, segregation may be facilitated by depth features because they provide direct access to the third dimension. Such access enables accurate object-background segregation. Although they provide a rich source of information, depth images are sensitive to background noise. This paper addresses the issue of handling background noise for accurate foreground–background segregation. It presents and evaluates the Region Comparison (RC) features for fast and accurate body part detection. RC features are depth features inspired by the well-known Viola–Jones detector. Their performances are compared to the recently proposed Pixel Comparison (PC) features, which were designed for fast and accurate object detection from Kinect-generated depth images. The results of our evaluation reveal that RC features outperform PC features in detection accuracy and computational efficiency. From these results we may conclude that RC features are to be preferred over PC features to achieve accurate and fast object detection in noisy depth images.     

SRI-Net: Similarity retrieval-based inference network for light field salient object detection

The cutting-edge RGB saliency models are prone to fail for some complex scenes, while RGB-D saliency models are often affected by inaccurate depth maps. Fortunately, light field images can provide a sufficient spatial layout depiction of 3D scenes. Therefore, this paper focuses on salient object detection of light field images, where a Similarity Retrieval-based Inference Network (SRI-Net) is proposed. Due to various focus points, not all focal slices extracted from light field images are beneficial for salient object detection, thus, the key point of our model lies in that we attempt to select the most valuable focal slice, which can contribute more complementary information for the RGB image. Specifically, firstly, we design a focal slice retrieval module (FSRM) to choose an appropriate focal slice by measuring the foreground similarity between the focal slice and RGB image. Secondly, in order to combine the original RGB image and the selected focal slice, we design a U-shaped saliency inference module (SIM), where the two-stream encoder is used to extract multi-level features, and the decoder is employed to aggregate multi-level deep features. Extensive experiments are conducted on two widely used light field datasets, and the results firmly demonstrate the superiority and effectiveness of the proposed SRI-Net.     

一种生成对抗网络用于图像修复的方法

近年来基于深度学习的图像修复方法相比于传统方法,表现出明显优势,前者能更好的生成视觉上合理的图像结构和纹理.但现有的标准卷积神经网络方法,通常会造成颜色差异过大和图像纹理缺失与失真的问题.本文提出了一种新型图像修复深度网络模型,该模型由两个相互独立的生成对抗式网络模块组成.其中,图像修复网络模块旨在解决图像缺失区域的修复问题,其生成器基于部分卷积网络;图像优化网络模块旨在解决修复后图像存在局部色差的问题,其生成器基于深度残差网络.通过两个网络模块的协同作用,图像的视觉效果与图像质量得到提高.与其他先进方法进行定性和定量比较的实验结果表明,本文提出的方法在图像修复质量上表现更好.     

Natural and Seamless Image Composition With Color Control

While the state-of-the-art image composition algorithms subtly handle the object boundary to achieve seamless image copy-and-paste, it is observed that they are unable to preserve the color fidelity of the source object, often require quite an amount of user interactions, and often fail to achieve realism when there exists salient discrepancy between the background textures in the source and destination images. These observations motivate our research towards color controlled natural and seamless image composition with least user interactions. In particular, based on the Poisson image editing framework, we first propose a variational model that considers both the gradient constraint and the color fidelity. The proposed model allows users to control the coloring effect caused by gradient domain fusion. Second, to have less user interactions, we propose a distance-enhanced random walks algorithm, through which we avoid the necessity of accurate image segmentation while still able to highlight the foreground object. Third, we propose a multiresolution framework to perform image compositions at different subbands so as to separate the texture and color components to simultaneously achieve smooth texture transition and desired color control. The experimental results demonstrate that our proposed framework achieves better and more realistic results for images with salient background color or texture differences, while providing comparable results as the state-of-the-art algorithms for images without the need of preserving the object color fidelity and without significant background texture discrepancy.     

Single image deraining with dual U-Net generative adversarial network

Most of the existing deraining methods cannot preserve the details of the image while removing the rain streaks. To solve this problem, we propose a single image de-raining method with dual U-Net generative adversarial network (DU-GAN). By using two U-Net with stronger learning ability as our generator DU-GAN can not only accurately remove more rain streaks but also preserve image details. The network can make full use of image information and extract complete image features. The adversarial loss function using the proposed dual U-Net generator is utilized to generate de-rained images which are close to the ground truth. Furthermore, to obtain the better visual effects of the generated image, The L1 and structure similarity loss functions which are consistent with the human visual effect are applied to generate the final output. The synthetic rainy image datasets and real rainy image datasets are used to evaluate the effectiveness of the proposed network in the experiments. The quantitative and visual experimental results show that the proposed single image deraining method achieves state-of-the-art compared with the other single image deraining methods. The source code can be found at https://github.com/LuBei-design/DU-GAN.

     

基于OpenCV的目标物体颜色及轮廓的识别方法

针对机器人视觉中对目标物体的拾取问题,提出一种基于Open CV函数对从摄像头输入的目标物体的颜色及轮廓进行有效识别的方法。首先利用摄像头读取目标物体及周围环境,经一系列图像处理后进行目标物体的颜色识别,在此基础上进行Canny边缘检测并查找轮廓,最后将轮廓显示。结果表明,该实验程序可以很好地完成对目标物体的颜色及轮廓提取,且有效地避免了目标物体周围相近颜色的干扰。     

面向显著性目标检测的SSD改进模型

传统显著性目标检测方法常假设只有单个显著性目标,其效果依赖显著性阈值的选取,并不符合实际应用需求。近来利用目标检测方法得到显著性目标检测框成为一种新的解决思路。SSD模型可同时精确检测多个不同尺度的目标对象,但小尺寸目标检测精度不佳。为此,该文引入去卷积模块与注意力残差模块,构建了面向多显著性目标检测的DAR-SSD模型。实验结果表明,DAR-SSD检测精度显著高于SOD模型;相比原始SSD模型,在小尺度和多显著性目标情形下性能提升明显;相比MDF和DCL等深度学习框架下的方法,也体现了复杂背景情形下的良好检测性能。     

属性一致的物体轮廓划分模型

该文提出一种基于全卷积深度残差网络、结合生成式对抗网络思想的基于属性一致的物体轮廓划分模型。采用物体轮廓划分网络作为生成器进行物体轮廓划分;该网络运用结构相似性作为区域划分的重构损失,从视觉系统的角度监督指导模型学习;使用全局和局部上下文判别网络作为双路判别器,对区域划分结果进行真伪判别的同时,结合对抗式损失提出一种联合损失用于监督模型的训练,使区域划分内容真实、自然且具有属性一致性。通过实例验证了该方法的实时性、有效性。