The Visual Looming Navigation Cue: A Unified Approach

Visual looming is related to an increasing projected size of an object on a viewer's retina as the relative distance between the viewer and the object decreases. It is an indication for threat that may be used along with visual fixation to accomplish navigation tasks. This paper defines visual looming as the time derivative of the relative distance (range) between the observer and the object divided by the relative distance itself. It introduces a unified approach to visual looming by showing how visual looming can be calculated from the relative temporal change in the following attributes of a 2D image sequence: (i) image area, (ii) image brightness, (iii) texture density in the image, and (iv) image blur. It is shown that a closed-form unified expression can be adopted in all these methods. Experimental results illustrate how the measured values of looming are related to the actual values. Finally, looming is used in the sense of a threat of collision, along with visual fixation, to navigate in an unknown environment.     

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.     

一种自然场景图像的目标材质视觉特征映射算法

针对自然场景图像目标材质视觉特征映射中,尚存在特征提取困难、图像无对应标签等问题,本文提出了一种自然场景图像的目标材质视觉特征映射算法.首先,从图像中获取能表征材质视觉重要特征的反射层图像;然后,对获取的反射层图像进行前景、背景分割,得到目标图像;最后,利用循环生成对抗网络对材质视觉特征进行无监督学习,获得对图像目标材质视觉特征空间的高阶表达,实现了目标材质视觉特征的映射.实验结果表明,所提算法能够有效地获取自然场景图像目标的材质视觉特征,并进行材质视觉特征映射;与同类算法相比,具有更好的主、客观效果.     

三角形约束下的词袋模型图像分类方法

视觉词袋模型广泛地应用于图像分类与图像检索等领域.在传统词袋模型中,视觉单词统计方法忽略了视觉词之间的空间信息以及分类对象形状信息,导致图像特征表示区分能力不足.本文提出了一种改进的视觉词袋方法,结合显著区域提取和视觉单词拓扑结构,不仅能够产生更具代表性的视觉单词,而且能够在一定程度上避免复杂背景信息和位置变化带来的干扰.首先,通过对训练图像进行显著区域提取,在得到的显著区域上构建视觉词袋模型.其次,为了更精确的描述图像的特征,抵抗多变的位置和背景信息的影响,该方法采用视觉单词拓扑结构策略和三角剖分方法,融入全局信息和局部信息.通过仿真实验,并与传统的词袋模型及其他模型进行比较,结果表明本文提出的方法获得了更高的分类准确率.     

基于多特征融合的图像主体显著性判断

从视觉角度来说,视觉显著性图像是指主体突出的图像,比起内容散乱的图像,此类图像往往更能吸引用户的关注,也更符合用户对图片检索的使用需求。提出了一种图像主体视觉显著性判断方法,采用“中心围绕”计算原则在多特征融合的基础上应用支持向量机训练,建立了一个分类模型,并且可以给出表征图像显著程度的得分。实验表明,该模型有较高的分类正确率,并且将该模型应用于图像检索重排序、图像上传自动审核等应用时,可以得到更接近人工操作的结果,降低人力资源成本。     

基于灰度直方图的运动目标特征检测算法

为提高运动目标的检测效果和指导性，提出一种基于灰度直方图分析的运动目标特征检测算法。采用视觉成像技术进行运动目标图像采集和视觉特征分析，提取运动目标的动态视觉特征量。根据运动目标边缘差分变换和空间位置关系进行运动图像的特征分离，提取运动目标图像的边缘轮廓特征量。采用统计形状模型进行运动目标图像的二值化分离，构建运动目标图像的灰度直方图。根据灰度直方图中的统计信息进行目标特征检测和动态特征提取，实现运动目标图像的视觉检测和动态识别，有效提取运动目标的关键特征，实现目标特征检测。仿真结果表明，采用该方法进行运动目标图像的特征检测性能较好，对运动目标的动态识别能力较强。     

一种基于本体的图像检索方法

提出一种基于本体的图像检索方法。该方法结合特定领域专家知识和对象例图,采用视觉对象本体来描述图像内特定对象的视觉特征,从而构建该领域包含视觉描述的知识库。在检索过程中,利用知识库内的对象的视觉本体描述和目标图像库内的图像低层特征相匹配执行图像检索任务,从而实现在高层次语义上的图像检索。实验结果表明了该方法的有效性和可行性,并在一定程度上缩小了视觉低层特征同图像高层语义的鸿沟。     

A psychophysical approach to assessing the quality of antialiasedimages

The assumption that antialiasing destroys useful visual information about object features is challenged in three experiments that examine the effects of antialiasing on the visual information for object location and motion. The results show that proper antialiasing eliminates the spurious visual information produced by sampling processes in image synthesis and allows the viewer's visual system to produce a precise representation of object location and a continuous representation of object motion. This suggests that in designing imagery systems, simply increasing the spatial and temporal addressability and resolution beyond limits set by the human visual system will have a negligible impact on image quality, but that effective use of antialiasing techniques could allow visual information about object features to be presented with great fidelity     

带时延补偿的视觉跟踪控制

在实际的视觉伺服系统中, 由于摄像机到图像处理设备的传输延迟和图像处理本身占用的时间, 视觉信息的获取会产生时延. 对此, 给出了一个带有时延补偿的视觉跟踪控制方法. 通过实时拟合图像雅可比矩阵, 实现了对机械手末端执行器图像特征信息的实时预测, 从而减小了估计误差. 在此基础上, 设计了一个带有时延补偿的控制方案. 通过对运动目标进行跟踪的仿真实验, 验证了本文时延补偿方法的有效性.     

Superimposition, symbology, visual attention, and the head-up display

In two experiments we examined a number of related factors postulated to influence head-up display (HUD) performance. We addressed the benefit of reduced scanning and the cost of increasing the number of elements in the visual field by comparing a superimposed HUD with an identical display in a head-down position in varying visibility conditions. We explored the extent to which the characteristics of HUD symbology support a division of attention by contrasting conformal symbology (which links elements of the display image to elements of the far domain) with traditional instrument landing system (ILS) symbology. Together the two experiments provide strong evidence that minimizing scanning between flight instruments and the far domain contributes substantially to the observed HUD performance advantage. Experiment 1 provides little evidence for a performance cost attributable to visual clutter. In Experiment 2 the pattern of differences in lateral tracking error between conformal and traditional ILS symbology supports the hypothesis that, to the extent that the symbology forms an object with the far domain, attention may be divided between the superimposed image and its counterpart in the far domain.     

Hierarchical salient object detection model using contrast-based saliency and color spatial distribution

Visual saliency is an important cue in human visual system to detect salient objects in natural scenes. It has attracted a lot of research focus in computer vision, and has been widely used in many applications including image retrieval, object recognition, image segmentation, and etc. However, the accuracy of salient object detection model remains a challenge. Accordingly, a hierarchical salient object detection model is presented in this paper. In order to accurately interpret object saliency in image, we propose to investigate distinctive features from a global perspective. Image contrast and color distribution are calculated to generate saliency maps respectively, which are then fused using the principal component analysis. Compared with state-of-the-art models, the proposed model can accurately detect the salient object which conform with the human visual principle. The experimental results from the MSRA database validate the effectiveness of our proposed model.     

Mobile multi-view object image search

High user interaction capability of mobile devices can help improve the accuracy of mobile visual search systems. At query time, it is possible to capture multiple views of an object from different viewing angles and at different scales with the mobile device camera to obtain richer information about the object compared to a single view and hence return more accurate results. Motivated by this, we propose a new multi-view visual query model on multi-view object image databases for mobile visual search. Multi-view images of objects acquired by the mobile clients are processed and local features are sent to a server, which combines the query image representations with early/late fusion methods and returns the query results. We performed a comprehensive analysis of early and late fusion approaches using various similarity functions, on an existing single view and a new multi-view object image database. The experimental results show that multi-view search provides significantly better retrieval accuracy compared to traditional single view search.     

Adaptive image segmentation for region-based object retrieval using generalized Hough transform

Finding an object inside a target image by querying multimedia data is desirable, but remains a challenge. The effectiveness of region-based representation for content-based image retrieval is extensively studied in the literature. One common weakness of region-based approaches is that perform detection using low level visual features within the region and the homogeneous image regions have little correspondence to the semantic objects. Thus, the retrieval results are often far from satisfactory. In addition, the performance is significantly affected by consistency in the segmented regions of the target object from the query and database images. Instead of solving these problems independently, this paper proposes region-based object retrieval using the generalized Hough transform (GHT) and adaptive image segmentation. The proposed approach has two phases. First, a learning phase identifies and stores stable parameters for segmenting each database image. In the retrieval phase, the adaptive image segmentation process is also performed to segment a query image into regions for retrieving visual objects inside database images through the GHT with a modified voting scheme to locate the target visual object under a certain affine transformation. The learned parameters make the segmentation results of query and database images more stable and consistent. Computer simulation results show that the proposed method gives good performance in terms of retrieval accuracy, robustness, and execution speed.     

The possible mechanism underlying visual anti-camouflage: a modeland its real-time simulation

Visual camouflage and anti-camouflage may be of widespread relevance throughout the animal kingdom. A question arises as to the possible mechanism underlying visual anti-camouflage. A computational model of visual moving image filtering is proposed in which Reichardt's elementary motion detectors are employed for detecting motion information. Afterimages may play an important role in filtering motion object image. An electronic neural network setup was developed for real-time examination of the computational model. Thus, the separation of the moving object image from its background is realized in real-time, while the detected moving image is in high resolution with lower level noise     

Learning group-based dictionaries for discriminative image representation

Dictionary learning is a critical issue for achieving discriminative image representation in many computer vision tasks such as object detection and image classification. In this paper, a new algorithm is developed for learning discriminative group-based dictionaries, where the inter-concept (category) visual correlations are leveraged to enhance both the reconstruction quality and the discrimination power of the group-based discriminative dictionaries. A visual concept network is first constructed for determining the groups of visually similar object classes and image concepts automatically. For each group of such visually similar object classes and image concepts, a group-based dictionary is learned for achieving discriminative image representation. A structural learning approach is developed to take advantage of our group-based discriminative dictionaries for classifier training and image classification. The effectiveness and the discrimination power of our group-based discriminative dictionaries have been evaluated on multiple popular visual benchmarks.     

Visual object retrieval via block-based visual-pattern matching

This paper presents an object-based image retrieval using a method based on visual-pattern matching. A visual pattern is obtained by detecting the line edge from a square block using the moment-preserving edge detector. It is desirable and yet remains as a challenge for querying multimedia data by finding an object inside a target image. Given an object model, an added difficulty is that the object might be translated, rotated, and scaled inside a target image. Object segmentation and recognition is the primary step of computer vision for applying to image retrieval of higher-level image analysis. However, automatic segmentation and recognition of objects via object models is a difficult task without a priori knowledge about the shape of objects. Instead of segmentation and detailed object representation, the objective of this research is to develop and apply computer vision methods that explore the structure of an image object by visual-pattern detection to retrieve images from a database. A voting scheme based on generalized Hough transform is proposed to provide object search method, which is invariant to the translation, rotation, scaling of image data, and hence, invariant to orientation and position. Computer simulation results show that the proposed method gives good performance in terms of retrieval accuracy and robustness.     

自然图像中的感兴趣目标检测技术

基于显著图的目标检测方法不能精确地找到感兴趣目标的位置,或在同一感兴趣目标上检测出多个感兴趣区域。为此,提出一种视觉注意机制和模糊支持向量机(FSVM)相结合的算法。根据显著度和角点分布信息,从图像中获得包括单个目标的视觉窗口,并在窗口中采用FSVM算法分割目标和背景。实验结果表明,该方法符合生物的视觉注意机制,分割效果较好。     

基于遮挡区域建模和目标运动估计的动态遮挡规避方法

对于运动视觉目标，如何对遮挡区域进行规避是视觉领域一个具有挑战性的问题.本文提出了一种新颖的基于运动视觉目标深度图像利用遮挡信息实现动态遮挡规避的方法.该方法主要利用遮挡区域最佳观测方位模型和视觉目标运动估计方程，通过合理规划摄像机的观测方位逐渐完成对遮挡区域的观测.主要贡献在于:1）提出了深度图像遮挡边界中关键点的概念，利用其构建关键线段对遮挡区域进行快速建模；2）基于关键线段和遮挡区域建模结果，提出了一种构建遮挡区域最佳观测方位模型的方法；3）提出一种混合曲率特征，通过计算深度图像对应的混合曲率矩阵，增加了图像匹配过程中提取特征点的数量，有利于准确估计视觉目标的运动.实验结果验证了所提方法的可行性和有效性.     

Automatic Lighting Design using a Perceptual Quality Metric

Lighting has a crucial impact on the appearance of 3D objects and on the ability of an image to communicate information about a 3D scene to a human observer. This paper presents a new automatic lighting design approach for comprehensible rendering of 3D objects. Given a geometric model of a 3D object or scene, the material properties of the surfaces in the model, and the desired viewing parameters, our approach automatically determines the values of various lighting parameters by optimizing a perception-based image quality objective function. This objective function is designed to quantify the extent to which an image of a 3D scene succeeds in communicating scene information, such as the 3D shapes of the objects, fine geometric details, and the spatial relationships between the objects.
Our results demonstrate that the proposed approach is an effective lighting design tool, suitable for users without expertise or knowledge in visual perception or in lighting design.