基于距离比上下文的形状描述与识别方法

基于形状轮廓上的采样点到形状质心的距离,提出了一种距离比上下文形状描述符,用于形状识别和检索。该描述符计算简单,能有效区分不同形状,本质上具有平移、缩放不变性,且在一定程度上能杭部分遮挡和形变。用动态规划算法度量形状比上下文之间的距离,解决了对起始轮廓点的选择问题。在kimia' s-99形状图像数据库中的实验结果表明,该方法在单目标封闭轮廓的形状图像检索中取得了良好的效果。     

From Images to Shape Models for Object Detection

We present an object class detection approach which fully integrates the complementary strengths offered by shape matchers. Like an object detector, it can learn class models directly from images, and can localize novel instances in the presence of intra-class variations, clutter, and scale changes. Like a shape matcher, it finds the boundaries of objects, rather than just their bounding-boxes. This is achieved by a novel technique for learning a shape model of an object class given images of example instances. Furthermore, we also integrate Hough-style voting with a non-rigid point matching algorithm to localize the model in cluttered images. As demonstrated by an extensive evaluation, our method can localize object boundaries accurately and does not need segmented examples for training (only bounding-boxes).     

基于轮廓的形状射线描述模型

提出一种新的基于轮廓的形状描述和匹配方法。提取物体的轮廓并在轮廓上进行等间隔采样,利用参考点到采样点的距离、采样点处的轮廓方向及采样点间的空间关系来直观地表达目标的形状特征;通过在不同尺度、方向和位置进行最大表决来获得形状匹配的尺度、旋转和平移不变性;提出了结合局部和整体特征的相似度评分机制来实现目标的匹配和检测。实验表明,形状的射线描述模型不仅能对具有清晰轮廓的目标进行有效的检索和匹配,也可在复杂的图像背景中检测目标。     

Contour based object detection using part bundles

In this paper we propose a novel framework for contour based object detection from cluttered environments. Given a contour model for a class of objects, it is first decomposed into fragments hierarchically. Then, we group these fragments into part bundles, where a part bundle can contain overlapping fragments. Given a new image with set of edge fragments we develop an efficient voting method using local shape similarity between part bundles and edge fragments that generates high quality candidate part configurations. We then use global shape similarity between the part configurations and the model contour to find optimal configuration. Furthermore, we show that appearance information can be used for improving detection for objects with distinctive texture when model contour does not sufficiently capture deformation of the objects.     

Tracking non-rigid objects using probabilistic Hausdorff distance matching

This paper proposes a new method of extracting and tracking a non-rigid object moving against a cluttered background while allowing camera movement. For object extraction we first detect an object using watershed segmentation technique and then extract its contour points by approximating the boundary using the idea of feature point weighting. For object tracking we take the contour to estimate its motion in the next frame by the maximum likelihood method. The position of the object is estimated using a probabilistic Hausdorff measurement while the shape variation is modelled using a modified active contour model. The proposed method is highly tolerant to occlusion. Unless an object is fully occluded during tracking, the result is stable and the method is robust enough for practical application.     

<Emphasis Type="Italic">Skeleton Search</Emphasis>: Category-Specific Object Recognition and Segmentation Using a Skeletal Shape Model

We describe a top-down object detection and segmentation approach that uses a skeleton-based shape model and that works directly on real images. The approach is based on three components. First, we propose a fragment-based generative model for shape that is based on the shock graph and has minimal dependency among its shape fragments. The model is capable of generating a wide variation of shapes as instances of a given object category. Second, we develop a progressive selection mechanism to search among the generated shapes for the category instances that are present in the image. The search begins with a large pool of candidates identified by a dynamic programming (DP) algorithm and progressively reduces it in size by applying series of criteria, namely, local minimum criterion, extent of shape overlap, and thresholding of the objective function to select the final object candidates. Third, we propose the Partitioned Chamfer Matching (PCM) measure to capture the support of image edges for a hypothesized shape. This measure overcomes the shortcomings of the Oriented Chamfer Matching and is robust against spurious edges, missing edges, and accidental alignment between the image edges and the shape boundary contour. We have evaluated our approach on the ETHZ dataset and found it to perform well in both object detection and object segmentation tasks.     

一种新的无监督前景目标检测方法

针对基于无监督特征提取的目标检测方法效率不高的问题,提出一种在无标记数据集中准确检测前景目标的方法.其基本出发点是:正确的特征聚类结果可以指导目标特征提取,同时准确提取的目标特征可以提高特征聚类的精度.该方法首先对无标记样本图像进行局部特征提取,然后根据最小化特征距离进行无监督特征聚类.将同一个聚类内的图像两两匹配,将特征匹配的重现程度作为特征权重,最后根据更新后的特征权重指导下一次迭代的特征聚类.多次迭代后同时得到聚类结果和前景目标.实验结果表明,该方法有效地提高Caltech-256数据集和Google车辆图像的检测精度.此外,针对目前绝大部分无监督目标检测方法不具备增量学习能力这一缺点,提出了增量学习方法实现,实验结果表明,增量学习方法有效地提高了计算速度.     

字典重建和空间分布关系约束下的特征选择与图像拼接

目的 针对大型图像检索领域中,复杂图像中SIFT特征描述子的冗余和高维问题,提出了一种基于字典重建和空间分布关系约束的特征选择的方法,来消除冗余特征并保留最具表现力的、保留原始空间结构性的SIFT特征描述子。方法 首先,实验发现了特征选择和字典学习方法在稀疏表示方面的内在联系,将特征选择问题转化为字典重构任务;其次,在SIFT特征选择问题中,为了保证特征空间中特征的鲁棒性,设计了新型的字典学习模型,并采用模拟退火算法进行迭代求解;最后,在字典学习的过程中,加入熵理论来约束特征的空间分布,使学习到的特征描述子能最大限度保持原始SIFT特征空间的空间拓扑关系。结果 在公开数据集Holiday大型场景图片检索数据库上,通过与国际公认的特征选择方法进行实验对比,本文提出的特征选择方法在节省内存空间和提高时间效率（30%~ 50%）的同时,还能保证所筛选的特征描述子的检索准确率比同类特征提高8%~ 14.1%;在国际通用的大型场景图片拼接数据库IPM上,验证本文方法在图像拼接应用中特征提取和特征匹配上的有效性,实验表明本文方法能节省（50% ~70%）图像拼接时间。结论 与已有的方法比较,本文的特征选择方法既不依赖训练数据集,也不丢失重要的空间结构和纹理信息,在大型图像检索、图像拼接领域和3D检索领域中,能够精简特征,提高特征匹配效率和准确率。     

Contour-based object detection as dominant set computation

Contour-based object detection can be formulated as a matching problem between model contour parts and image edge fragments. We propose a novel solution by treating this problem as the problem of finding dominant sets in weighted graphs. The nodes of the graph are pairs composed of model contour parts and image edge fragments, and the weights between nodes are based on shape similarity. Because of high consistency between correct correspondences, the correct matching corresponds to a dominant set of the graph. Consequently, when a dominant set is determined, it provides a selection of correct correspondences. As the proposed method is able to get all the dominant sets, we can detect multiple objects in an image in one pass. Moreover, since our approach is purely based on shape, we also determine an optimal scale of target object without a common enumeration of all possible scales. Both theoretic analysis and extensive experimental evaluation illustrate the benefits of our approach.     

基于生物视觉特征的目标轮廓提取算法

自然场景中的目标轮廓提取是计算机视觉中的一个重要研究问题。其难点在于场景中大量的纹理边缘严重地干扰了轮廓提取的完整性。近年来,一些研究工作将生物视觉特征引入图像边缘轮廓提取,取得了一定的效果。其中通过引入视觉外区抑制特征可以在提取物体轮廓边缘的同时抑制一定量的纹理边缘,从而得到轮廓边缘集合。然而在整合轮廓边缘时,传统模型仅仅采用求交并集的简单合并方法,使得强响应的细小纹理残留。基于此,提出了一种改进的基于生物视觉特征的自然场景目标轮廓提取算法。首先采用多水平抑制方法得到候选轮廓边缘集合。接着将一种基于生物视觉特征的边缘组合方法用于将候选边缘整合成为一个完整的目标轮廓。与传统的外区抑制算法相比,基于视觉特征的轮廓提取算法提高了自然场景中目标轮廓提取的准确性和完整性。     

OPTIMOL: Automatic Online Picture Collection via Incremental Model Learning

The explosion of the Internet provides us with a tremendous resource of images shared online. It also confronts vision researchers the problem of finding effective methods to navigate the vast amount of visual information. Semantic image understanding plays a vital role towards solving this problem. One important task in image understanding is object recognition, in particular, generic object categorization. Critical to this problem are the issues of learning and dataset. Abundant data helps to train a robust recognition system, while a good object classifier can help to collect a large amount of images. This paper presents a novel object recognition algorithm that performs automatic dataset collecting and incremental model learning simultaneously. The goal of this work is to use the tremendous resources of the web to learn robust object category models for detecting and searching for objects in real-world cluttered scenes. Humans contiguously update the knowledge of objects when new examples are observed. Our framework emulates this human learning process by iteratively accumulating model knowledge and image examples. We adapt a non-parametric latent topic model and propose an incremental learning framework. Our algorithm is capable of automatically collecting much larger object category datasets for 22 randomly selected classes from the Caltech 101 dataset. Furthermore, our system offers not only more images in each object category but also a robust object category model and meaningful image annotation. Our experiments show that OPTIMOL is capable of collecting image datasets that are superior to the well known manually collected object datasets Caltech 101 and LabelMe.