基于显著性区域的图像分割

在经典的Chan-Vese模型中结合显著性分析,提出了一种有效的目标分割方法.即首先利用频谱残差方法提取图像的显著性区域,针对阈值分割方法的缺点使用改进的自适应阈值分割方法获取目标的大致轮廓,并以此轮廓作为Chan-Vese模型中初始曲线.该方法使得活动轮廓可以从靠近目标物体的位置进行演化,去除复杂背景的干扰.这样就解决了背景复杂时无法得到较为准确的边缘的问题;同时,也减少了CV模型的迭代次数.实验结果表明无论是背景复杂的灰度图像还是医学彩色图像,该算法的分割精度和运行效率都优于CV模型.     

一种基于视觉显著图的舰船红外图像目标检测方法

提出了一种基于视觉显著图的红外舰船目标定位方法,即通过改进的Itti模型生成视觉显著图,并基于视觉显著图分割出目标区域,从而实现目标检测。先用小波变换替代Itti模型中的高斯滤波来生成图像多尺度金字塔,然后用center—surround算子提取出多尺度的视觉差异特征,并对生成的视觉特征图进行合成,生成显著图。最后,利用阈值分割方法分割出目标区域,并对原始图像进行标记,从而实现目标检测。实验结果表明,与传统的Otsu阈值分割方法相比,该方法能够准确检测出目标区域。     

融合改进FT显著性与Grabcut的图像目标分割算法

针对目前复杂度较大的图像中目标分割速度较慢、显著性边界分割不明确等问题,提出了一种融合改进的FT（Frequency-tuned）显著性检测与Grabcut的图像分割算法。该算法首先通过改进基于频率调谐的FT显著性检测方法得到图像中显著性较高的区域,并利用SLIC（Simple Linear Iterative Clustering）算法对显著图进行预处理得到超像素图,能够有效改善边界的分割效果,然后通过以图论GraphCut算法为基础改进的Grabcut算法建立高斯混合模型。为了提高算法效率,通过聚类以超像素代替原像素,并反复迭代高斯混合模型（Gaussian Mixed Model,GMM）参数,最后利用最大流最小割算法得到最优目标分割结果。实验结果表明所提算法能够更准确更高效率地分割图像中的显著性目标,对高分辨率图像也有很好的适用效果,相比于其他算法在分割精度上提高10%左右,并具有较高的分割效率。     

局部和全局特征融合的红外图像显著性检测

为了更好地凸显复杂环境的红外目标特征,提出 一种融合局部和全局特征的红外图像 显著性检测方法。在获取图像超像素的基础上,提取每个区域空间距离加权的邻域对比度特 征,并考虑区域大小和位置的影响,构建局部显著图;然后提取每个区域空间距离加权的全 局灰度特征,构建全局显著图;最后融合局部和全局显著图,实现图像显著性检测。实验结 果 表明,本文方法的显著图结果目标区域一致高亮且边缘清晰,同时背景杂波抑制效果好。无 论 主观评价还是客观指标,本文方法都优于当前流行的图像显著性检测方法。     

概率图车载热成像行人检测RoIs提取方法

道路场景复杂、热成像纹理信息较少以及图像品质不稳定,RoIs提取面临挑战.阈值分割RoIs提取更多关注行人局部细节和像素间邻域关系,容易产生行人遗漏、背景粘连和行人断裂,且很难控制RoIs总量.模拟人类视觉,关注图像显著性区域及其位置和大小,提出概率图RoIs提取方法,设计凸-凹形曲线映射像素灰度值增强图像对比度;基于图像签名方法获取显著性图.融合灰度强度和显著性概率图并从中提取图像前景;设计算法搜索路面估计限定的概率图区域生成RoIs.实验表明,相对阈值分割,本文方法能够提高RoIs定位准确度、控制RoIs总量和显著减少非行人RoIs;提取等量单帧RoIs,召回率提高不低于9%.     

基于可区分边界和加权对比度优化的显著度检测算法

针对目前基于先验背景的显著度算法中,把图像的所有边界同等对待带来的误判别问题,本文提出一种基于可区分边界和加权对比度优化的显著度检测算法.为了客观评价显著度,本文首先设计了一种粗略评估显著度的指标,用来选择较好的背景图.以该指标为基础,该算法先利用Hausdorff距离对边界进行区分,再利用测地线距离变换完成可靠的背景检测;然后,构造了一种前景-背景加权的对比度来计算初始显著度;最后,使用加权的优化模型进行显著度的优化.在5个公开数据集上的实验结果表明,本文算法在保持快速、无训练等优点的同时,检测性能优于目前主流算法.     

Spatiotemporal saliency detection and salient region determination for H.264 videos

In this study, a spatiotemporal saliency detection and salient region determination approach for H.264 videos is proposed. After Gaussian filtering in Lab color space, the phase spectrum of Fourier transform is used to generate the spatial saliency map of each video frame. On the other hand, the motion vector fields from each H.264 compressed video bitstream are backward accumulated. After normalization and global motion compensation, the phase spectrum of Fourier transform for the moving parts is used to generate the temporal saliency map of each video frame. Then, the spatial and temporal saliency maps of each video frame are combined to obtain its spatiotemporal saliency map using adaptive fusion. Finally, a modified salient region determination scheme is used to determine salient regions (SRs) of each video frame. Based on the experimental results obtained in this study, the performance of the proposed approach is better than those of two comparison approaches.     

A depth perception and visual comfort guided computational model for stereoscopic 3D visual saliency

With the emerging development of three-dimensional (3D) related technologies, 3D visual saliency modeling is becoming particularly important and challenging. This paper presents a new depth perception and visual comfort guided saliency computational model for stereoscopic 3D images. The prominent advantage of the proposed model is that we incorporate the influence of depth perception and visual comfort on 3D visual saliency computation. The proposed saliency model is composed of three components: 2D image saliency, depth saliency and visual comfort based saliency. In the model, color saliency, texture saliency and spatial compactness are computed respectively and fused to derive 2D image saliency. Global disparity contrast is considered to compute depth saliency. Particularly, we train a visual comfort prediction function to distinguish stereoscopic image pair as high comfortable stereo viewing (HCSV) or low comfortable stereo viewing (LCSV), and devise different computational rules to generate a visual comfort based saliency map. The final 3D saliency map is obtained by using a linear combination and enhanced by a “saliency-center bias” model. Experimental results show that the proposed 3D saliency model outperforms the state-of-the-art models on predicting human eye fixations and visual comfort assessment.     

Video saliency detection incorporating temporal information in compressed domain

Saliency detection is widely used to pick out relevant parts of a scene as visual attention regions for various image/video applications. Since video is increasingly being captured, moved and stored in compressed form, there is a need for detecting video saliency directly in compressed domain. In this study, a compressed video saliency detection algorithm is proposed based on discrete cosine transformation (DCT) coefficients and motion information within a visual window. Firstly, DCT coefficients and motion information are extracted from H.264 video bitstream without full decoding. Due to a high quantization parameter setting in encoder, skip/intra is easily chosen as the best prediction mode, resulting in a large number of blocks with zero motion vector and no residual existing in video bitstream. To address these problems, the motion vectors of skip/intra coded blocks are calculated by interpolating its surroundings. In addition, a visual window is constructed to enhance the contrast of features and to avoid being affected by encoder. Secondly, after spatial and temporal saliency maps being generated by the normalized entropy, a motion importance factor is imposed to refine the temporal saliency map. Finally, a variance-like fusion method is proposed to dynamically combine these maps to yield the final video saliency map. Experimental results show that the proposed approach significantly outperforms other state-of-the-art video saliency detection models.     

视频对象分割与两种面向对象的视频编码器

在基于对象的视频编码中,视频对象的分割是重要的任务.本文研究一种利用位移帧差(DFD)的高阶统计特性和数学形态学算子的视频对象自动分割方法.这种方法首先根据一组转移帧差的高阶矩来得到一个大体覆盖运动对象的区域(模板),接着用形态学的腐蚀算子从模板的边沿向内腐蚀,直到对象的边沿.提出一种简单而高效的基于查找人头肩像轮廓最大转折点的头肩分离算法.在分割的基础上,用软件实现了一种基于MPEG-4的视频编码系统.提出一种面向对象分配带宽(OOBA——object-oriented bandwidth allocation)的极低比特率视频编码器.该编码器与传统基于帧的视频编码器相比,在低比特率环境下,PSNR略为下降,但图像的主观视觉质量得到提高.     

基于相位谱的红外小目标搜索算法研究

针对红外小目标搜索阶段中图像背景稀疏的特点,提出了一种利用图像相位谱计算显著图和定位目标的新方法。与传统的利用海天线和海岸线对目标进行搜索的方法相比,本文算法的计算复杂度大大降低,并弥补了其受气温影响而不能准确定位海天线和海岸线的不足;与利用Itti模型的方法相比,该算法克服了其不能有效分离目标和背景的缺点。阐述了利用离散傅里叶变换(Discrete Fourier Transform,DFT)和离散余弦变换(Discrete Cosine Transform,DCT)计算相位谱的两种方法及它们之间的一致性。构建了利用图像相位谱计算显著图的数学模型,明确了模型参数选择的作用和意义。通过理论和实例证明了本文算法对于稀疏背景下小目标定位的可行性和高效性。     

一种基于立体视觉显著性的多视点视频比特分配方法

针对多视点立体视频压缩编码,提出了一种基于立 体视觉显著性的比 特分配方法。研究综合利用多视点立体视频数据中场景的运动、深度以及深度边缘信息提取 人眼感兴趣区 域(ROI)的方法;然后根据ROI的划分结果优化区域比特分配。实验结果表 明,本文提出的算法能有效提 高ROI区域的编码性能,同时整体视频的率失真性能有一定程度的提高。     

一种显著图分割的遥感油库检测方法

针对遥感影像中油罐检测识别率低、难度大的问题,提出了一种基于显著图分割分布式的目标检测识别方法,利用视觉显著模型得到油库疑似候选区域,采用多阀值Otsu方法分割出目标,以及利用油罐的似圆特征和分布式的空间分布规律对油库进行检测识别,通过油库场景分布的先验知识,提高检测识别效率、降低虚警率。大量实验表明,文中方法可有效实现对遥感影像中油库的检测识别。     

一种基于视觉显著度模型的无线视频码率控制算法(英文)

In order to further improve the efficiency of video compression, we introduce a perceptual characteristics of Human Visual System (HVS) to video coding, and propose a novel video coding rate control algorithm based on human visual saliency model in H.264/AVC. Firstly, we modifie Itti's saliency model. Secondly, target bits of each frame are allocated through the correlation of saliency region between the current and previous frame, and the complexity of each MB is modified through the saliency value and its...     

Image saliency detection based on geodesic‐like and boundary contrast maps

Image saliency detection is the basis of perceptual image processing, which is significant to subsequent image processing methods. Most saliency detection methods can detect only a single object with a high‐contrast background, but they have no effect on the extraction of a salient object from images with complex low‐contrast backgrounds. With the prior knowledge, this paper proposes a method for detecting salient objects by combining the boundary contrast map and the geodesics‐like maps. This method can highlight the foreground uniformly and extract the salient objects efficiently in images with low‐contrast backgrounds. The classical receiver operating characteristics (ROC) curve, which compares the salient map with the ground truth map, does not reflect the human perception. An ROC curve with distance (distance receiver operating characteristic, DROC) is proposed in this paper, which takes the ROC curve closer to the human subjective perception. Experiments on three benchmark datasets and three low‐contrast image datasets, with four evaluation methods including DROC, show that on comparing the eight state‐of‐the‐art approaches, the proposed approach performs well.     

基于显著区域提取的红外图像舰船目标检测

针对复杂海面背景下红外图像舰船目标由于灰度不均匀、海杂波干扰大等因素造成的自动检测虚警率高、准确率低的问题,提出了一种显著区域提取和目标精确分割相结合的红外舰船目标检测方法。首先,利用基于图论的视觉显著性(Graph-based Visual Saliency ,GBVS)模型计算待检测图像的显著图,使得目标区域信息增强;其次,结合舰船目标先验信息（长短轴、面积等）,利用多级阈值划分算法提取关注的显著区域,并确定原图中候选目标区域;最后,利用空间约束模糊C均值(Fuzzy C-Means,FCM)算法对候选区域进行分割,结合目标先验知识对分割区域筛选并输出目标位置。所提方法在公开数据集IRShips上与相关方法进行比较,结果表明,相比直接进行全图目标搜索的方法,所提方法不仅准确率高、执行速度快,且检测目标的位置更加精确。     

融合显著图和保真图的全参考图像质量评价

提出一种融合显著图(SM)和保真图(FM)的全参考图 像质量 评价算法,用于评价质降图像的失真度。利用亮度和色度的相似度提取质降图像相对于 参考图像的FM;对参考图像进行区域划分、全局显著性提取和纹理边缘补充得到SM,将SM与 质降图像的FM融合得到基 于感知的显著保真图(PSM),计算质降图像的客观评价得分。在标准数据库上的实验结果表 明,本文方法与主观评价能够很好保持一致,并对LIVE图像库中的5种失真图像均有很好的 表现。     

Saliency-based content-aware lifestyle image mosaics

In this paper, a novel content-aware lifestyle image mosaic technique is proposed based on image saliency. The image saliency is used in the whole process of creating mosaics. Firstly, a novel energy map for variable-size tile decomposition is proposed by combining Neighborhood Inhomogeneity Factor and Graph-Based Visual Saliency. The target image is divided into small tiles with variable sizes based on the energy map. Secondly, saliency-weighted image retrieval is introduced to choose the tile images from a certain image database. Different aspect ratio between the tile and the corresponding tile image may lead to obvious distortion. Therefore, before filled into the tile, the chosen tile image is resized by seam carving to change its aspect ratio. At last, color correction is done on the mosaic result to improve the color similarity. Compared with other mosaic methods, the proposed technique creates much better mosaics in visual aspect.     

Residential area extraction based on saliency analysis for high spatial resolution remote sensing images

Traditional residential area extraction methods for remote sensing image depend on classification, segmentation and prior knowledge which are time-consuming and difficult to build. In this paper, an efficient, saliency analysis-based residential area extraction method is proposed. In the proposed model, an adaptive directional prediction-based lifting wavelet transform (ADP-LWT) is introduced to obtain the orientation feature. A logarithm co-occurrence histogram is employed to compute the intensity feature. The color opponency and diagram objection based on the information are proposed to extract color feature from the contrast in the red–green opponent channel. The saliency map is obtained through a weighted combination based on the feature competition and the residential area is extracted by saliency map threshold segmentation. The experimental results reveal that the residential area extracted by our model has more demarcated boundaries and better performance in background subtraction.     

基于流形排名与迟滞阈值法的视觉显著性检测

视觉显著性检测是机器视觉领域的关键技术之一.提出一种基于流形排名与迟滞阈值的检测方法,首先将图像划分成超像素集合,以之作为结点形成闭环图;再按照基于图的流形排名方法计算各个结点的显著值,形成图像的显著图;然后利用显著图直方图统计出高、低两个阈值,将显著图划分为三个部分,使用伽马校正技术分别进行处理,最终整合校正结果得到输出显著图.实验结果表明,相对于现有算法,本文算法得到的显著图能够更好地区分背景区域和显著目标,同时也更具稳健性.