基于立体全景漫游中深度图获取技术的研究

近年来,随着硬件技术的进步和计算机视觉理论的发展,为了增强用户的沉浸感和体验,立体全景技术被广泛应用于生产和生活中。针对多视点立体全景三维重建中深度图的获取问题,提出了一种新的深度图生成方法。首先将前后摄像机拍摄的图像进行配准,然后通过线性变换矩阵得到对应像素点与中心像素的距离,最后利用提出的算法求得深度图。     

Visual comfort prediction for stereoscopic image using stereoscopic visual saliency

Perceptually salient regions of stereoscopic images significantly affect visual comfort (VC). In this paper, we propose a new objective approach for predicting VC of stereoscopic images according to visual saliency. The proposed approach includes two stages. The first stage involves the extraction of foreground saliency and depth contrast from a disparity map to generate a depth saliency map, which in turn is combined with 2D saliency to obtain a stereoscopic visual saliency map. The second stage involves the extraction of saliency-weighted VC features, and feeding them into a prediction metric to produce VC scores of the stereoscopic images. We demonstrate the effectiveness of the proposed approach compared with the conventional prediction methods on the IVY Lab database, with performance gain ranging from 0.016 to 0.198 in terms of correlation coefficients.     

Content-aware disparity adjustment for different stereo displays

In this paper, we present an effective disparity mapping method for binocular stereoscopic image. It is inspired by the observation that its displayed depth would change, when a stereoscopic image is displayed on different size screens. The phenomenon may bring an uncomfortable experience for viewers. To make a comfortable stereoscopic image for viewers, moreover to adapt a stereoscopic image to a target display screen, we propose a content-aware disparity adjustment method. Firstly, the disparity mapping is established to control and retarget the depth of a stereoscopic scene. Then, the relationship between the disparity editing and image content editing is established to guide the proposed warping model. At last, to implement the disparity mapping operator, we propose a content-aware stereoscopic mesh warping model, which can simultaneously avoid the salient region distortion and adjust disparity to a target range by establishing the relationship. Experimental results show that the proposed method can effectively adjust disparity of stereoscopic image, which not only avoids the salient region distortion and adjusts disparity to a target range.     

自动巡线小车的图像采集系统开发与优化

为了实现自动巡线小车的路径精确识别,同时不牺牲系统的运行速度,开发了一种由CMOS数字摄像头OV6620和飞思卡尔MC9S12XS128微控制器组成的图像采集系统.采用双口静态存储器IDT7008作为数据缓存实现系统的优化,引入分割最佳阀值的迭代算法和中值滤波快速算法,提高了图像边缘检测的抗干扰能力和边缘定位的精确性,增强了图像的平滑性,边缘定位精确度可达80%以上.实验结果表明,该图像采集系统简单可靠,性价比高,便于调试,大大减少了图像采集和处理的时间,应用在自动巡线小车上取得了良好效果.     

用于岩心扫描的彩色线阵CCD图像采集系统

针对岩心资源数字化的需求,设计并实现了一种用于岩心图像扫描仪的彩色线阵CCD图像采集系统。实际应用表明，该系统能很好地解决现有系统的分辨率低、成本高的问题。可为后继的岩心图像分析工作提供可靠的依据。     

An automatic adjustment procedure for rational splines

This paper presents the development of an adjustment method for the rational spline. The adjustment of the spline is completed by tensioning each internal section until the spline conforms to user defined data in a way which is both accurate and esthetically pleasing. The tensioning rationale for the rational spline is developed for use in an interactive mode with minicomputer and graphics terminal, but may also be used in a batch environment.     

Methods for automatic and assisted image annotation

Personal memories composed of digital pictures are very popular at the moment. To retrieve these media items annotation is required. During the last years, several approaches have been proposed in order to overcome the image annotation problem. This paper presents our proposals to address this problem. Automatic and semi-automatic learning methods for semantic concepts are presented. The automatic method is based on semantic concepts estimated using visual content, context metadata and audio information. The semi-automatic method is based on results provided by a computer game. The paper describes our proposals and presents their evaluations.     

Neural ranking for automatic image annotation

Automatic image annotation aims to predict labels for images according to their semantic contents and has become a research focus in computer vision, as it helps people to edit, retrieve and understand large image collections. In the last decades, researchers have proposed many approaches to solve this task and achieved remarkable performance on several standard image datasets. In this paper, we propose a novel learning to rank approach to address image auto-annotation problem. Unlike typical learning to rank algorithms for image auto-annotation which directly rank annotations for image, our approach consists of two phases. In the first phase, neural ranking models are trained to rank image’s semantic neighbors. Then nearest-neighbor based models propagate annotations from these semantic neighbors to the image. Thus our approach integrates learning to rank algorithms and nearest-neighbor based models, including TagProp and 2PKNN, and inherits their advantages. Experimental results show that our method achieves better or comparable performance compared with the state-of-the-art methods on four challenging benchmarks including Corel5K, ESP Games, IAPR TC-12 and NUS-WIDE.

     

一种新的自动图像配准技术*

提出了一种自动图像配准方法.该方法首先使用模板匹配获得图像间的粗匹配点,然后利用这些粗匹配点估计图像之间的变换参数,并通过统计这些变换参数的适用情况,选取出一组最佳的图像变换参数,从而实现了图像间的自动配准.实验验证,该方法在两幅图像间存在平移、转动且重叠区域较少时,仍能准确得匹配这两幅图像.     

Fingerprint image analysis for automatic identification

Most of the papers on fingerprints deal with classification of fingerprint images. Fingerprint databases being large (in the range of millions), the effort in matching of fingerprints within a class or when the class is unknown, is very significant. This requires fingerprint image analysis and extraction of the “minutiae” features, which are used for matching FPs. In this paper a scheme of preprocessing and feature extraction of fingerprint images for automatic identification is presented, which works even if the pattern class is unknown. The identification of fingerprints is based on matching the minutiae features of a given finger-print against those stored in the database. The core and delta information is used for classification and for registration while matching. These algorithms have been tested for more than 10,000 fingerprint images of different qualities. The results are manually verified and found to be very good for practical application. A few sample results are presented.     

An automatic procedure for image segmentation

A procedure for image segmentation involving no image-dependent thresholds is described. The method involves not only detection of edges but also production of closed region boundaries. The method has been developed and tested on head and shoulder images.     

A Java program for stereo retinal image visualization

Stereo imaging of the optic-disc is a gold standard examination of glaucoma, and progression of glaucoma can be detected from temporal stereo images. A Java-based software system is reported here which automatically aligns the left and right stereo retinal images and presents the aligned images side by side, along with the anaglyph computed from the aligned images. Moreover, the disparity between two aligned images is computed and used as the depth cue to render the optic-disc images, which can be interactively edited, panned, zoomed, rotated, and animated, allowing one to examine the surface of the optic-nerve head from different view angles. Measurement including length, area, and volume of regions of interest can also be performed interactively.     

Deformed cross-dissolves for image interpolation in scientific visualization

Deformed cross-dissolves are methods for inconspicuous interpolation between images. We describe methods for deformation based on scattered data interpolation methods using correspondence points in the images to be interpolated and an algorithm for automatic establishment of these correspondence points. We also describe efficient cross-dissolve algorithms for the computation of intermediate images. Results for interpolation in the field of medical visualization are presented.     

Incorporating multiple SVMs for automatic image annotation

In this paper, a novel automatic image annotation system is proposed, which integrates two sets of support vector machines (SVMs), namely the multiple instance learning (MIL)-based and global-feature-based SVMs, for annotation. The MIL-based bag features are obtained by applying MIL on the image blocks, where the enhanced diversity density (DD) algorithm and a faster searching algorithm are applied to improve the efficiency and accuracy. They are further input to a set of SVMs for finding the optimum hyperplanes to annotate training images. Similarly, global color and texture features, including color histogram and modified edge histogram, are fed into another set of SVMs for categorizing training images. Consequently, two sets of image features are constructed for each test image and are, respectively, sent to the two sets of SVMs, whose outputs are incorporated by an automatic weight estimation method to obtain the final annotation results. Our proposed annotation approach demonstrates a promising performance for an image database of 12 000 general-purpose images from COREL, as compared with some current peer systems in the literature.     

A two-level model for automatic image annotation

Image automatic annotation is a significant and challenging problem in pattern recognition and computer vision. Current image annotation models almost used all the training images to estimate joint generation probabilities between images and keywords, which would inevitably bring a lot of irrelevant images. To solve the above problem, we propose a hierarchical image annotation model which combines advantages of discriminative model and generative model. In first annotation layer, discriminative model is used to assign topic annotations to unlabeled images, and then relevant image set corresponding to each unlabeled image is obtained. In second annotation layer, we propose a keywords-oriented method to establish links between images and keywords, and then our iterative algorithm is used to expand relevant image sets. Candidate labels will be given higher weights by using our method based on visual keywords. Finally, generative model is used to assign detailed annotations to unlabeled images on expanded relevant image sets. Experiments conducted on Corel 5K datasets verify the effectiveness of our hierarchical image annotation model.     

基于视差图的未知环境下农田障碍物检测方法

针对智能农业机器人作业环境中障碍物不规则和背景受自然光照等外界环境干扰大的问题,提出一种基于视差图的未知环境下障碍物检测方法.采用价格低廉的网络摄像头采集左右场景图并计算对应的视差图;用视差阂值过滤掉远处的景物,再通过区域连通,得到独立的潜在障碍物;最终经面积闽值和高度阈值的过滤,检测出障碍物并定位.实验结果表明,该检测算法不需要障碍物和背景的先验知识,在距离摄像头5m视野内,障碍物距离和尺寸测量的相对偏差绝对值分别控制在4.37％和3.81％以内.