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。     

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。     

基于注意模型的视觉替代方法

现有的视觉替代方法均是在特定环境中,通过目标识别获得映射特征,缺少普遍的适用性.针对这一问题,提出了一种基于注意模型的视觉替代方法.利用人眼的视觉特性,提取图像的感兴趣区域,并根据听觉显示的基本原理,提出了将感兴趣区域的位置、尺寸和颜色映射为音符响度、音长和音调的PSC映射方法.实验结果表明:将图像中引起视觉注意的区域映射为电子音符,符合人类视觉认知过程,有利于盲人获得外部环境的重要信息,降低了盲人训练和学习的难度,并且听感良好,不会造成听觉疲劳.     

基于灰度概率统计的视觉注意改进算法

分析了基于自底向上的视觉注意计算模型的感兴趣区域检测方法;它分别提取颜色、灰度、纹理三个特征图像,然后进行线性融合得到综合显著图。而显著目标通常自身灰度相近,但与背景灰度不同,根据这个特性结合灰度概率统计方法对视觉注意计算模型进行改进。实验结果验证了,该模型能够更好的模拟视觉注意的过程,而且计算复杂度较低。     

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。     

基于视觉注意机制的遥感图像船只检测

针对视觉注意机制中Itti模型在显著性区域提取中提取颜色、方向和亮度3种特征,应用到遥感图像中容易造成错检的问题,在Itti模型基础上提出了改进的显著性模型,用纹理特征代替Itti模型中的颜色特征和亮度特征,同时考虑了图像在频域中的显著性。对改进后的算法进行仿真,仿真结果表明,改进算法检测精度高、实时性好,显著区域与目标基本一致,能够有效地检测遥感图像中船只目标。     

一种基于ROI的红外舰船目标定位方法

提出了一种基于感兴趣区域ROI(Regions of Interest)的红外舰船目标定位方法,通过改进的Itti模型提取包含目标的感兴趣区域,实现目标定位。首先应用小波变换代替Itti模型的高斯滤波生成图像多尺度金字塔,并用center-surround算子提取多尺度的视觉差异,再将生成的视觉特征图进行归一化并线性组合,生成显著图,最后运用交替式有效子窗口搜索算法A-ESS(Alternating Efficient Subwindow Search)定位目标区域。实验结果表明:该方法能准确定位出目标区域。     

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。     

基于生物激励计算模型在图像显著性提取中的研

提出一种生物激励的显著性特征计算模型。首先通过注意块学习从眼动数据库中选择与视觉响应一致的稀疏基；然后基于稀疏基表达原理对图像建立计算模型并提取显著性特征:包括全局连续性、区域颜色对比以及局部复杂度对比特征；再仿照细胞调节原理，提出新的特征组合方法进行特征融合。最后将该算法在多个典型的场景中对感兴趣区进行提取实验，证明比其他算法具有优越性。并提出将此算法应用于虚拟与现实场景融合中，能良好地提取出真实场景中的有效区域和剔除虚景区域。     

动态金字塔模型的红外图像SR重建

无人机在复杂飞行过程中,因大气气流及光学设备成像等影响造成采集到的红外图像分辨率过低;另外,因各帧图像分辨率不同,基于固定层数分解的金字塔模型在同一区域下的显著图提取结果存在差异,无法借助视觉技术实现无人机目标定位及自主导航。提出一种改进Itti模型下的红外图像感兴趣区域提取及SR重建算法。算法首先引入多特征对红外图像序列进行金字塔动态分层模型构建;然后,针对不同分辨率下的多帧红外图像进行感兴趣区域的动态提取来克服传统Itti算法的不足;最后,提出基于共轭梯度法的目标函数最小化红外图像超分辨率重建算法,对感兴趣区域进行空间SR重建,提高感兴趣区域目标的空间分辨率。实验验证了提出算法的有效性及准确性。     

高分辨率遥感影像感兴趣区域快速检测

传统高分辨率遥感影像感兴趣区域的检测方法通常要利用先验知识库对整幅影像进行全局分析与搜索,具有很高计算复杂度。从人眼视觉特性出发,提出一种新的高分辨率遥感影像感兴趣区域快速检测算法。基于视觉关注模型对高分辨率遥感影像进行空间降维,确定视觉关注焦点;根据关注焦点位置在原始遥感影像中描述出相应的感兴趣区域。实验结果表明,新方法不仅具有较低计算复杂度,而且有效避免了影像分割、特征检测等计算复杂度较高的全图搜索方法,提高了高分辨率遥感影像感兴趣区域的检测效率。     

Visual‐Attention‐Aware Progressive RoI Trick Mode Streaming in Interactive Panoramic Video Service

In the near future, traditional narrow and fixed viewpoint video services will be replaced by high‐quality panorama video services. This paper proposes a visual‐attention‐aware progressive region of interest (RoI) trick mode streaming service (VA‐PRTS) that prioritizes video data to transmit according to the visual attention and transmits prioritized video data progressively. VA‐PRTS enables the receiver to speed up the time to display without degrading the perceptual quality. For the proposed VA‐PRTS, this paper defines a cutoff visual attention metric algorithm to determine the quality of the encoded video slice based on the capability of visual attention and the progressive streaming method based on the priority of RoI video data. Compared to conventional methods, VA‐PRTS increases the bitrate saving by over 57% and decreases the interactive delay by over 66%, while maintaining a level of perceptual video quality. The experiment results show that the proposed VA‐PRTS improves the quality of the viewer experience for interactive panoramic video streaming services. The development results show that the VA‐PRTS has highly practical real‐field feasibility.     

Exploring visual attention using random walks based eye tracking protocols

Identifying visual attention plays an important role in understanding human behavior and optimizing relevant multimedia applications. In this paper, we propose a visual attention identification method based on random walks. In the proposed method, fixations recorded by the eye tracker are partitioned into clusters where each cluster presents a particular area of interest (AOI). In each cluster, we estimate the transition probabilities of the fixations based on their point-to-point adjacency in their spatial positions. We obtain the initial coefficients for the fixations according to their density. We utilizing random walks to iteratively update the coefficients until their convergency. Finally, the center of the AOI is calculated according to the convergent coefficients of the fixations. Experimental results demonstrate that our proposed method which combines the fixations’ spatial and temporal relations, highlights the fixations of higher densities and eliminates the errors inside the cluster. It is more robust and accurate than traditional 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.     

基于一种视觉注意力机制的图像描述方法

为了提高由图像生成文字描述的准确率,文中提出了一种基于传统的编码解码框架,分别在编码端和解码端融入视觉注意力机制的方法,即在编码端加入空间注意力机制和图像通道级注意力机制相结合的方法。在解码端运用自适应视觉注意力机制的方法,即在传统的解码端上加入一个额外的“视觉哨兵”模块。文中提出的方法在生成文字描述的过程中自动决定是依赖图像特征还是依赖语义特征,并传递给相应的注意力机制。实验证明,相比较单一的视觉注意力机制,文中方法取得了较高的图像描述语句的正确率,具有更好的图像描述性能。     

Efficient visual attention based framework for extracting key frames from videos

The huge amount of video data on the internet requires efficient video browsing and retrieval strategies. One of the viable solutions is to provide summaries of the videos in the form of key frames. The video summarization using visual attention modeling has been used of late. In such schemes, the visually salient frames are extracted as key frames on the basis of theories of human attention modeling. The visual attention modeling schemes have proved to be effective in video summarization. However, the high computational costs incurred by these techniques limit their applicability in practical scenarios. In this context, this paper proposes an efficient visual attention model based key frame extraction method. The computational cost is reduced by using the temporal gradient based dynamic visual saliency detection instead of the traditional optical flow methods. Moreover, for static visual saliency, an effective method employing discrete cosine transform has been used. The static and dynamic visual attention measures are fused by using a non-linear weighted fusion method. The experimental results indicate that the proposed method is not only efficient, but also yields high quality video summaries.     

Discriminative two-level feature selection for realistic human action recognition

Constructing the bag-of-features model from Space–time interest points (STIPs) has been successfully utilized for human action recognition. However, how to eliminate a large number of irrelevant STIPs for representing a specific action in realistic scenarios as well as how to select discriminative codewords for effective bag-of-features model still need to be further investigated. In this paper, we propose to select more representative codewords based on our pruned interest points algorithm so as to reduce computational cost as well as improve recognition performance. By taking human perception into account, attention based saliency map is employed to choose salient interest points which fall into salient regions, since visual saliency can provide strong evidence for the location of acting subjects. After salient interest points are identified, each human action is represented with the bag-of-features model. In order to obtain more discriminative codewords, an unsupervised codeword selection algorithm is utilized. Finally, the Support Vector Machine (SVM) method is employed to perform human action recognition. Comprehensive experimental results on the widely used and challenging Hollywood-2 Human Action (HOHA-2) dataset and YouTube dataset demonstrate that our proposed method is computationally efficient while achieving improved performance in recognizing realistic human actions.