基于视觉注意模型和进化规划的感兴趣区检测方法

根据生物注意机制,该文提出了一种基于视觉注意模型和进化规划的感兴趣区检测方法。采用进化规划方法分割图像候选区域;区域兴趣度由视觉注意模型产生的局部显著和进化规划计算的全局显著共同度量。在视觉注意模型中,图像经过小波多尺度变换和计算中央周边差得到局部显著度。注意焦点在显著度增强因子的作用下,选取候选区域得到感兴趣区。实验结果表明,所提方法检测的感兴趣区更接近人眼的视觉注意机制,并取得了较为满意的对象检测和兴趣度量结果。     

基于兴趣点检测的视觉关键词提取新方法研究

基于内容的图像检索的一个突出问题是提取整幅图像的全局特征,而用户通常只关注一幅图像中的局部区域。对于如今海量的数据库,提取图像的全局特征使得数据库的信息量变得非常大。这样,从巨大的图像特征库中查找匹配的图像特征时检索准确率将大大降低。针对用户感兴趣的局部区域,提出视觉关键词的概念。一幅图像用若干个视觉关键词替代,这样一幅图像的特征量将大大减小。视觉关键词是用户感兴趣的图像区域,这样使得检索更加具有针对性。实验结果表明检索准确率有明显提高。     

航天遥感图像感兴趣区域的自动提取方法

感兴趣区域提取是航天遥感图像分析的重要前提。随着图像空间分辨率的提高,场景内显著目标以及背景变得愈加复杂。利用传统的特征提取技术将会耗费大量计算空间和时间。提出了基于改进视觉注意方法的感兴趣区域自动提取,在HSV空间将目标与背景在颜色和亮度上的差异作为显著特征,利用高斯金字塔和中心-周边求差算子计算图像的显著特征图,并对特征图进行归一化和线性融合,设计注意焦点的转移步骤,完成感兴趣区域的自动提取。通过仿真和实验可以看出,本方法能有效地实现航天遥感图像感兴趣区域的自动提取。     

一种图像的感兴趣区域提取方法

感兴趣区域(Region of interests,ROI)是图像中可能引起人眼视觉关注的区域。根据视觉注意机制的经典模型Itti模型来提取图像的低层特征,利用局部迭代的特征合并策略并在此基础上综合自动阈值分割和种子点的区域生长方法得到感兴趣区域的提取方法。实验结果表明该方法符合生物的视觉注意机制,具有良好的鲁棒性。     

基于人眼视觉灰阶特性的红外图像映射显示研究

基于红外图像灰度分布集中、对比度低的特点,结合人眼视觉特性,对人眼视觉特性的灰度特性进行了分析,寻求将有限的红外图像信息映射到最有利于人眼观察的灰度分布区域,提出了红外图像灰度级映射显示的方法.采用本文方法处理后的图像质量的主观评价结果表明,方法得到了符合人眼视觉特性的显示最佳灰度范围.     

融合深度信息的室内RGB图像视觉显著物体快速检测方法

针对传统视觉注意机制在室内三原色(RGB)图像视觉显著物体检测中存在的运算复杂、检测精度低等缺点,提出了一种融合深度信息的室内RGB图像视觉显著物体快速检测方法。对室内RGB图像进行降采样和金字塔量化处理,从而降低图片的空间分辨率和计算复杂度。利用亮度、红绿以及黄蓝三通道的多特征视觉注意机制显著性检测模型以获得室内RGB图像的显著图。在显著图分析中提出显著区域生长策略,从而获得视觉显著区域的精确轮廓。融合深度信息获取视觉显著区域内显著物体数目以及显著物体相互之间的位置关系。通过室内场景实验,验证了方法的可行性和有效性。     

一种权值可发育的视觉选择性注意模型研究

针对Itti视觉选择性注意模型不具有子特征图显著图归一化过程中权值随任务改变而改变的问题,借鉴自主发育在视觉选择性注意学习的研究成果,提出一种权值可发育视觉选择性注意模型作为图像特征提取的学习机制。该算法采用三层自组织神经网络和Itti视觉选择性注意模型相结合的决策进行寻优,通过对模型的训练学习获取最优权值更新。这样既可以保证在初期特征提取内容的完整性,又降低了系统对不同任务条件的约束性,提高了模型特征提取能力。利用权值可发育视觉选择性注意模型对图像进行感兴趣区域特征提取实验,结果表明,该方法能够提高特征提取准确性、减少运算时间,获得了良好的动态性能。     

融入视觉常识和注意力的图像描述

图像描述任务是使计算机自动生成给定图像的自然语言描述文本,它涉及计算机视觉与自然语言处理两个领域,可应用于检索系统、盲人导航和医学报告生成等领域.针对现有的图像描述模型对视觉语义关系挖掘不充分,及多层注意力机制建模特征存在注意偏差的问题,提出一种融入视觉常识和注意力的图像描述模型.在编解码器结构框架下,编码部分引入了视...     

基于尺度空间表示的视觉注意区域选择

针对现有视觉注意计算模型中视觉特征图多尺度表示存在的问题,研究了基于非线性尺度空间的视觉特征图表示方法,通过建立视觉特征图的非线性尺度空间表示,在实现中央一外周计算策略的同时,可以有效保留边缘等局部细节信息.同时,在视觉注意特征图尺度空间表示基础上,提出了一种视觉注意区域的最佳尺度选择算法.实际图像显著区域选择的实验结果表明,该算法是有效的,在认知上是合理的.     

基于人眼视觉特性的红外图像增强技术研究

基于红外图像灰度分布集中、对比度低的特点,结合人眼视觉特性,提出了基于人眼视觉特性的非线性变换方法.基于人眼灰度分辨能力随灰度变化的线性关系,推导了人眼的可分辨率灰度函数和基于人眼视觉的非线性变换函数,建立了人眼的非线性变换模型,实现了将有限的红外图像信息映射到有利于人眼观察的灰度分布区域.实验结果表明,该方法处理的图像反差适中、纹理明晰、细节部分对比明显,有效解决了红外图像低对比度和细节模糊的问题.     

Blind tone mapped image quality assessment with image segmentation and visual perception

With tone mapping, high dynamic range (HDR) image contents can be displayed on low dynamic range (LDR) display devices, in which some important visual information may be distorted. Thus, the tone mapped image (TMI) quality assessment is one of important issues in HDR image/video processing fields. Considering the difference of visual distortion degrees between the flat and complex regions in TMI, and considering that high-quality TMI should preserve as much information as possible of its original HDR image especially in the high/low luminance regions, this paper proposes a new blind TMI quality assessment method with image segmentation and visual perception. First, we design different features to describe the distortion of TMI’s different regions with two kinds of TMI segmentation. Then, considering that there lacks an efficient algorithm to quantify the importance of features, a feature clustering scheme is designed to eliminate the poor effect feature components in the extracted features to improve the effectiveness of the selected features. Finally, considering the diversity of tone mapping operator (TMO), which may cause global and local distortion of TMI, some other global features are also combined. At last, a final feature vector is formed to synthetically describe the distortion in TMI and used to blindly predict the TMI’s quality. Experimental results in the public ESPL-LIVE HDR database show that the Pearson linear correlation coefficient and Spearman rank order correlation coefficient of the proposed method reach 0.8302 and 0.7887, respectively, which is superior to the state-of-the-art blind TMI quality assessment methods, and it means that the proposed method is highly consistent with human visual perception.     

Acuity-matching resolution degradation through wavelet coefficientscaling

A wavelet-based multiresolution image representation method is developed matching human visual system (HVS) spatial acuity within multiple regions of interest (ROIs). ROIs are maintained at high (original) resolution while peripheral areas are gracefully degraded. Variable resolution images are generated by selectively scaling wavelet (detail) coefficients prior to reconstruction. The technique is equivalent to linear interpolation MIP-mapping which involves smooth subsampling (decomposition) prior to texture mapping (reconstruction). Multiple ROI degradation is achieved through wavelet coefficient scaling following Voronoi partitioning of the image plane.     

基于多角度照片的真实感三维人脸建模的研究

为了提高重构的三维人脸的真实感,提出了以Candide-3模型作为通用的人脸模型的一种改进的利用多角度照片进行合成的方法。首先利用改进的双目立体视觉系统,将获取的二维信息映射到三维空间上,测定特征点的深度信息;然后采用自动和交互的方式对Candide-3模型进行校准,合成三维人脸模型。最后采用改进的多角度映射方法对皮肤纹理进行映射贴图,合成具有真实感的三维人脸模型。验证表明,该方法能够更好的生成一个具有较好逼真度的真实感的三维人脸模型。     

基于全卷积网络的语义显著性区域检测方法研究

基于底层视觉特征和先验知识的显著性区域检测算法难以检测一些复杂的显著性目标,人的视觉系统能分辨这些目标是由于其中包含丰富的语义知识.本文构建了一个基于全卷积结构的语义显著性区域检测网络,用数据驱动的方式构建从图像底层特征到人类语义认知的映射,提取语义显著性区域.针对网络提取的语义显著性区域的缺点,本文进一步引入颜色信息、目标边界信息、空间一致性信息获得准确的超像素级前景和背景概率.最后提出一个优化模型融合前景和背景概率信息、语义信息、空间一致性信息得到最终的显著性区域图.在6个数据集上与15种最新算法的比较实验证明了本文算法的有效性和鲁棒性.     

Perceptual visual quality assessment using deeply-learned gaze shifting kernel

Image quality assessment (IQA) is a useful technique in computer vision and machine intelligence. It is widely applied in image retrieval, image clustering and image recognition. IQA algorithms generally rely on human visual system (HVS), which can reflect how human perceive salient regions in the image. In this paper, we leverage both low-level features and high-level semantic features to select salient regions, which will be concatenated to form GSPs by the designed saliency-constraint algorithm to mimic human visual system. We design an enhanced IQA index based on the GSPs to calculate the simialrity between reference image and test image to achieve image quality assessment. Experiments demonstrate that our IQA method can achieve satisfactory performance.     

HDR tone mapping algorithm based on difference compression with adaptive reference values

Tone mapping remains a challenging problem since tone mapping operators need to produce high perceptual quality under all conditions. In this paper, we propose a new local tone mapping method based on difference compression with adaptive reference values, which can effectively reproduce the details of bright and shadow regions. We also use a global tone mapping method and blend the output images produced by the global and local methods based on objective quality metrics. To quantitatively measure output images, we developed a new objective quality metric for the tone mapped images. The proposed detailness metric measures detail loss in the bright and shadow regions, and shows good correlations with subjective quality. We combined this metric with the recently proposed tone mapped image quality index (TMQI) that may not sufficiently reflect the amount of local detail loss. The experiments show that the proposed algorithm provides better perceptual quality than existing methods.     

Hot spot detection based on feature space representation of visual search

This paper presents a new framework for capturing intrinsic visual search behavior of different observers in image understanding by analysing saccadic eye movements in feature space. The method is based on the information theory for identifying salient image features based on which visual search is performed. We demonstrate how to obtain feature space fixation density functions that are normalized to the image content along the scan paths. This allows a reliable identification of salient image features that can be mapped back to spatial space for highlighting regions of interest and attention selection. A two-color conjunction search experiment has been implemented to illustrate the theoretical framework of the proposed method including feature selection, hot spot detection, and back-projection. The practical value of the method is demonstrated with computed tomography image of centrilobular emphysema, and we discuss how the proposed framework can be used as a basis for decision support in medical image understanding.     

基于视觉、LiDAR与IMU的实时无人车里程计研究

视觉/LiDAR里程计可以根据传感器数据对无人车在多个自由度上运动的过程进行估计,是无人车定位建图系统的重要组成部分。文中提出了一种使用视觉、LiDAR和IMU进行信息融合的里程计,支持多种运行模式和初始化方式。前端部分采用了改进后的ICP CUDA算法进行激光点云配准,利用光流法对视觉特征进行跟踪,并利用激光点云数据对视觉特征的深度进行估计。后端部分采用了基于滑动窗口的图优化模型,并为视觉和LiDAR关键帧创建状态节点,以前端结果作为量测,将相邻状态节点通过预积分因子关联。文中方案实验结果表明:在城市场景系统平均相对位移精度为0.2%~0.5%,系统全量传感器运行模式（VLIO模式）整体要比关闭视觉的模式（LIO模式）和关闭LiDAR的模式（VIO模式）精度高。文中提出的方法对于提高无人车定位建图系统的精度有着积极意义。