Learning to generate novel views of objects for class recognition

Multi-view object class recognition can be achieved using existing approaches for single-view object class recognition, by treating different views as entirely independent classes. This strategy requires a large amount of training data for many viewpoints, which can be costly to obtain. We describe a method for constructing a weak three-dimensional model from as few as two views of an object of the target class, and using that model to transform images of objects from one view to several other views, effectively multiplying their value for class recognition. Our approach can be coupled with any 2D image-based recognition system. We show that automatically transformed images dramatically decrease the data requirements for multi-view object class recognition.     

A new method for representing and matching shapes of natural objects

A new method for the representation and comparison of irregular two-dimensional shapes is presented. This method uses a polar transformation of the contour points about the geometric centre of the object. The distinctive vertices of the shape are extracted and used as comparative parameters to minimize the difference of contour distance from the centre. Experiments are performed, more than 39 000 comparisons of database shapes, provided by Sebastian et al. (ICCV (2001) 755), are made and the results are compared to those obtained therein. In addition, 450 comparisons of leaf shape are made and leaves of very similar shape are accurately distinguished. The method is shown to be invariant to translation, rotation and scaling and highly accurate in shape distinction. The method shows more tolerance to scale variation than that of Sebastian et al. (ICCV (2001) 755) and is less computationally intense.     

Planar shape matching based on binary tree shape representation

In this paper we suggest a new way of representing planar two-dimensional shapes and a shape matching method which utilizes the new representation. Through merging of the neighboring boundary runs, a shape can be partitioned into a set of triangles. These triangles are inherently connected according to a binary tree structure. Here we use the binary tree with the triangles as its nodes to represent the shape. This representation is found to be insensitive to shape translation, rotation, scaling and skewing changes due to viewer's location changes (or the object's pose changes). Furthermore, the representation is of multiresolution.

In shape matching we compare the two trees representing two given shapes node by node according to the breadth-first tree traversing sequence. The comparison is done from top of the tree and moving downward, which means that we first compare the lower resolution approximations of the two shapes. If the two approximations are different, the comparison stops. Otherwise, it goes on and compares the finer details of the two shapes. Only when the two shapes are very similar, will the two corresponding trees be compared entirely. Thus, the matching algorithm utilizes the multiresolution characteristic of the tree representation and appears to be very efficient.     

Appearance-based recognition of 3-D objects by cluttered background and occlusions

In this article we present a new appearance-based approach for the classification and the localization of 3-D objects in complex scenes. A main problem for object recognition is that the size and the appearance of the objects in the image vary for 3-D transformations. For this reason, we model the region of the object in the image as well as the object features themselves as functions of these transformations. We integrate the model into a statistical framework, and so we can deal with noise and illumination changes. To handle heterogeneous background and occlusions, we introduce a background model and an assignment function. Thus, the object recognition system becomes robust, and a reliable distinction, which features belong to the object and which to the background, is possible. Experiments on three large data sets that contain rotations orthogonal to the image plane and scaling with together more than 100 000 images show that the approach is well suited for this task.     

Hypercolumn-array based image representation and its application to shape-based object detection

Biological and psychological evidence increasingly reveals that high-level geometrical and topological features are the keys to shape-based object recognition in the brain. Attracted by the excellent performance of neural visual systems, we simulate the mechanism of hypercolumns in the mammalian cortical area V1 that selectively responds to oriented bar stimuli. We design an orderly-arranged hypercolumn array to extract and represent linear or near-linear stimuli in an image. Each unit of this array covers stimuli of various orientations in a small area, and multiple units together produce a low-dimensional vector to describe shape. Based on the neighborhood of units in the array, we construct a graph whose node represents a short line segment with a certain position and slope. Therefore, a contour segment in the image can be represented with a route in this graph. The graph converts an image, comprised of typically unstructured raw data, into structured and semantic-enriched data. We search along the routes in the graph and compare them with a shape template for object detection. The graph greatly upgrades the level of image representation, remarkably reduces the load of combinations, significantly improves the efficiency of object searching, and facilitates the intervening of high-level knowledge. This work provides a systematic infrastructure for shape-based object recognition.     

全自动实时人脸图像变形技术研究与实现

提出了一种新的人脸图像变形方法——自适应网格方法(AMM)。该方法可以全自动产生实时的人脸变形效果。ASM(主动形状模型)技术的使用消除了其他人脸变形算法中所必须的手工标定人脸关键点工作;提出一种将人脸矩形区域自动划分成数个特征矩形的方法,使得复杂的图像变形计算被化简为简单高效的图像插值计算。该工作有助于将人脸变形技术运用于桌面实时应用中。     

Handling inheritance in a system integrating logic in objects

The inheritance mechanism of SILO, a system integrating a many-sorted logic within an object-based framework, is presented. In order to be adequate for knowledge representation, it comprises two components, a hardwired and a user-definable. Due to use of typed (sorted) terms, a variety of specialisation types between logical formulas (axioms) are introduced and defined. Thus, the hardwired component is able to represent a variety of inheritance/specialisation relations between objects. The notion of a conflict is defined and conflict detection theorems are introduced. Also, consequence retraction is introduced and used alongside attribute/predicate overriding to resolve conflicts. The user-definable component consists of a number of user definable functions, called meta-functions, which are able to implement both global and local inheritance control. It is based on a partial reflection meta-level architecture.     

数据库多媒体数据对象的处理

用Power Builder6.5在解决多媒体数据输入数据库问题的基础上，实现了图像，声音，视频等多媒体信息的查询，修改，播放等操作，并给出具体实现代码。     

二值图象边界平滑跟踪的一个算法

开发了一个用于二值图象边界平滑跟踪的一个算法。使用这个算法能去掉或修正某些可能是虚假的干扰点。这些点是二值图象边界一个或一组沿特定链码方向的凸点或凹点。重复地使用这个算法，直到边界不含有这些点。这个算法能有效地使用在二值图象的模式识别与机器人视觉的预处理中。     

A blocking model for reactive objects

Objects can be viewed as entities reacting concurrently with their environment through the sending and receiving of messages. In this paper a model for such reactive objects is constructed where messages may be blocked either by the object or by the environment. This model differentiates between output messages controlled by the object, and input messages controlled by the environment. The model is applied to define an object compatibility lattice structure enabling the construction of objects satisfying best possible compatibility requirements.     

Distributed environment: A conceptual framework using objects

We present a conceptual framework for a distributed office system using concepts inherent to object-oriented formalism. The functions of the active object and the procedure servers are described. So are the attributes of the objects stored in these two servers. In order to endow the individual workstations with as much autonomy as possible, we develop a coarse-grained algorithm for active and procedural object distribution. An office model should have a high level of evolvability. To accommodate this phenomenon we devise a mechanism to enable the model to transit one state to another with a minimum level of perturbation.     

Efficient morphological shape representation by varying overlapping levels among representative disks

The morphological skeleton transform, the morphological shape decomposition, and the overlapped morphological shape decomposition are three basic morphological shape representation schemes. In this paper, we propose a new way of generalizing these basic representation algorithms to improve representational efficiency. In all three basic algorithms, a fixed overlapping policy is used to control the overlapping relationships among representative disks of different sizes. In our new algorithm, different overlapping policies are used to generate shape components that have different overlapping relationships among themselves. The overlapping policy is selected dynamically according to local shape features. Experiments show that compared to the three basic algorithms, our algorithm produces more efficient representations with lower numbers of representative points.     

临近特征点类型匹配的多边形渐变表达模型

提出一种基于Morphing技术的多边形连续尺度地图表达模型。依据多边形的凸壳多叉树建立了多边形特征点的层次结构;基于临近性原则及特征点前后弧段形状的对照关系实现两个关键尺度的同一多边形要素各层次特征点的匹配;在多边形的对应特征点间利用Morphing内插技术得到两个关键尺度间任意尺度的多边形表达。实验表明,对于两个关键尺度下的同一多边形,使用该模型能获取任意中间尺度下的多边形表达,在尺度变化时,多边形图形的过渡自然平稳。     

Learning search heuristics for finding objects in structured environments

We consider the problem of efficiently finding an object with a mobile robot in an initially unknown, structured environment. The overall goal is to allow the robot to improve upon a standard exploration technique by utilizing background knowledge from previously seen, similar environments. We present two conceptually different approaches. Whereas the first method, which is the focus of this article, is a reactive search technique that decides where to search next only based on local information about the objects in the robot’s vicinity, the second algorithm is a more global and inference-based approach that explicitly reasons about the location of the target object given all observations made so far. While the model underlying the first approach can be learned from data of optimal search paths, we learn the model of the second method from object arrangements of example environments. Our application scenario is the search for a product in a supermarket. We present simulation and real-world experiments in which we compare our strategies to alternative methods and also to the performance of humans.     

用SuperMap Object开发基于GIS的连锁店配送信息系统

支撑整个连锁店运营过程的是基于GIS的连锁店配送信息系统。在明确了业务流程的基础上,研究了基于GIS的连锁店配送信息系统的功能、GIS平台、空间数据模型、道路数据模型和最优路径分析,探讨了以Super Map Objects作为GIS平台,采用Microsoft Visual Basic作为开发工具实现基于GIS的连锁店配送信息系统的方案。     

A general shape context framework for object identification

A general shape context framework is proposed for object/image retrieval in occluded and cluttered environment with hundreds of models as the potential matches of an input. The approach is general since it does not require separation of input objects from complex background. It works by first extracting consistent and structurally unique local neighborhood information from inputs or models, and then voting on the optimal matches. Its performance degrades gracefully with respect to the amount of structural information that is being occluded or lost. The local neighborhood information applicable to the system can be shape, color, texture feature, etc. Currently, we employ shape information only. The mechanism of voting is based on a novel hyper cube based indexing structure, and driven by dynamic programming. The proposed concepts have been tested on database with thousands of images. Very encouraging results have been obtained.