Object Model Construction Research Articles

Latent mixture vocabularies for object categorization and segmentation

The visual vocabulary is an intermediate level representation which has been proved to be very powerful for addressing object categorization problems. It is generally built by vector quantizing a set of local image descriptors, independently of the object model used for categorizing images. We propose here to embed the visual vocabulary creation within the object model construction, allowing to make it more suited for object class discrimination and therefore for object categorization. We also show that the model can be adapted to perform object level segmentation task, without needing any shape model, making the approach very adapted to high intra-class varying objects.

Video object matching across multiple independent views using local descriptors and adaptive learning

Object detection and tracking is an essential preliminary task in event analysis systems (e.g. visual surveillance). Typically objects are extracted and tagged, forming representative tracks of their activity. Tagging is usually performed by probabilistic data association, however, in systems capturing disjoint areas it is often not possible to establish such associations, as data may have been collected at different times or in different locations. In this case, appearance matching is a valuable aid. We propose using bag-of-visterms, i.e. an histogram of quantized local feature descriptors, to represent and match tracked objects. This method has proven to be effective for object matching and classification in image retrieval applications, where descriptors can be extracted a priori. An important difference in event analysis systems is that relevant information is typically restricted to the foreground. Descriptors can, therefore, be extracted faster, approaching real-time requirements. Also, unlike image retrieval, objects can change over time and therefore their model needs to be updated continuously. Incremental or adaptive learning is used to tackle this problem. Using independent tracks of 30 different persons, we show that the bag-of-visterms representation effectively discriminates visual object tracks and that it presents high resilience to incorrect object segmentation. Additionally, this methodology allows the construction of scalable object models that can be used to match tracks across independent views.

Multi-epipolar lines matching-based ray-space interpolation for Free Viewpoint Video system

Ray-space based arbitrary viewpoint rendering without complex object segmentation or model construction is the main technology to realize Free Viewpoint Video (FVV) system for complex scenes. Ray-space interpolation and compression are two key techniques for the solution. In this paper, correlation among multiple epipolar lines in ray-space data is analyzed, and a new method of ray-space interpolation with multi-epipolar lines matching is proposed. Comparing with the pixel-based matching interpolation method and the block-based matching interpolation method, the proposed method can achieve higher Peak Signal to Noise Ratio (PSNR) in interpolating ray-space data and rendering arbitrary viewpoint images.

Adaptation to change of lighting conditions for interactive object recognition

AbstractThis paper discusses the learning of color transformations for object recognition in various lighting conditions, a function which is needed in systems for object recognition by interaction with the user. The system first constructs a model of the target object under the reference lighting conditions. Since the lighting conditions in actual object recognition differ from those of object model construction, the system must transform the color of the object model according to the lighting conditions at the time of recognition. The color of a reference object observed in the recognition stage is used to estimate the color transformation. The system learns the relation between the color transformation and the color of the reference object by using the color of the object model and also the pair of colors of the target object and the reference object observed under various lighting conditions. In a new environment, such a set of colors is not stored, and the color transformation is applied by assuming a reasonable relation. Object recognition may fail when such a color transformation is applied. In such a case, the correct object is selected by interaction with the user. The relation is updated by using the obtained correctly matched pair. By improving the estimation accuracy of the color transformation at each instance of object recognition, the burden on the user in the interaction is reduced. Finally, the effectiveness of the proposed method is demonstrated through an experiment on a scene inside a refrigerator. © 2007 Wiley Periodicals, Inc. Syst Comp Jpn, 38(4): 52– 62, 2007; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/scj.20228

色情報処理手法の自動選択による複数物体追跡

In order to achieve the applications using vision sensors, it is impotrant to extract and track the moving objects from image sequences. Some tracking systems often prepare the models of the objects in advance. It is difficult to adopt this model based tracking in the general environment where many kinds of objects exist. On the other hand, model based tracking is efficient for the tracking in the crowded environment. We propose the color histogram based tracking system including the object model construction and object correspondence between frames by the fusion of the bottom-up process and top-down process.In this paper, two processes that configure the tracking sysytem are described. Then, process selection method in the proposed tracking system is explained. Finally, experimental results of objects are shown and effect of the proposed tracking system is also explained.

Euclidean Geometric Objects in the Clifford Geometric Algebra of {Origin, 3-Space, Infinity}

This paper concentrates on the homogeneous (conformal) model of Euclidean space (Horosphere) with subspaces that intuitively correspond to Euclidean geometric objects in three dimensions. Mathematical details of the construction and (useful) parametrizations of the 3D Euclidean object models are explicitly demonstrated in order to show how 3D Euclidean information on positions, orientations and radii can be extracted.

Looking to build a model world: automatic construction of static object models using computer vision

Interest in virtual reality and multimedia has provided a great impetus to the development of automatic techniques for building graphical CAD/CAM models of objects and environments by sensing reality itself. The learning of models in this way is essential, particularly in terms of production times and attaining the required high fidelity needed for many applications. Research has produced techniques for extracting full 3D shape models using a variety of sensors and a spectrum of techniques. These include the use of static video cameras, mobile video cameras (e.g. walk through video), multiple camera platforms and/or specialist active range sensors (typically based on laser striping or sonar). This paper introduces the principles and methodologies underlying several of these methods and presents algorithms and examples from systems representative of three major approaches: models from silhouettes, models from active range sensors and, finally, models from passive uncalibrated video sequences.

Automatic model construction and pose estimation from photographs using triangular splines

This paper addresses the automatic construction of complex spline object models from a few photographs. Our approach combines silhouettes from registered images to construct a G/sup 1/-continuous triangular spline approximation of an object with unknown topology. We apply a similar optimization procedure to estimate the pose of a modeled object from a single image. Experimental examples of model construction and pose estimation are presented for several complex objects.

Registration and integration of multiple object views for 3D model construction

Automatic 3D object model construction is important in applications ranging from manufacturing to entertainment, since CAD models of existing objects may be either unavailable or unusable. We describe a prototype system for automatically registering and integrating multiple views of objects from range data. The results can then be used to construct geometric models of the objects. New techniques for handling key problems such as robust estimation of transformations relating multiple views and seamless integration of registered data to form an unbroken surface have been proposed and implemented in the system. Experimental results on real surface data acquired using a digital interferometric sensor as well as a laser range scanner demonstrate the good performance of our system.

Practicing vision: Integration, evaluation and applications

Computer vision has emerged as a challenging and important area of research, both as an engineering and a scientific discipline. The growing importance of computer vision is evident from the fact that it was identified as one of the ″Grand Challenges″ and also from its prominent role in the National Information Infrastructure. While the design of a general purpose vision system continues to be elusive, machine vision systems are being used successfully in specific application domains. Building a practical vision system requires a careful selection of appropriate sensors, extraction and integration of information from available cues in the sensed data, and evaluation of system robustness and performance. We discuss and demonstrate advantages of (i) multi-sensor fusion, (ii) combination of features and classifiers, (iii) integration of visual modules, and (iv) admissibility and goal-directed evaluation of vision algorithms. The requirements of several prominent real world applications such as biometry, document image analysis, image and video database retrieval, and automatic object model construction offer exciting problems and new opportunities to design and evaluate vision algorithms.

A CAD Model Based System for Object Recognition

3D object recognition is a difficult and yet an important problem in computer vision. A 3D object recognition system has two major components, namely: an object modeller and a system that performs the matching of stored representations to those derived from the sensed image. The performance of systems wherein the construction of object models is done by training from one or more images of the objects, has not been very satisfactory. Although objects used in a robotic workcell or in assembly processes have been designed using a CAD system, the vision systems used for recognition of these objects are independent of the CAD database. This paper proposes a scheme for interfacing the CAD database of objects and the computer vision processes used for recognising these objects. CAD models of objects are processed to generate vision oriented features that appear in the different views of the object and the same features are extracted from images of the object to identify the object and its pose.

Optimal registration of object views using range data

This paper deals with robust registration of object views in the presence of uncertainties and noise in depth data. Errors in registration of multiple views of a 3D object severely affect view integration during automatic construction of object models. We derive a minimum variance estimator (MVE) for computing the view transformation parameters accurately from range data of two views of a 3D object. The results of our experiments show that view transformation estimates obtained using MVE are significantly more accurate than those computed with an unweighted error criterion for registration.

Matching 3-D line segments with applications to multiple-object motion estimation

A two-stage algorithm for matching line segments using three-dimensional data is presented. In the first stage, a tree-search based on the orientation of the line segments is applied to establish potential matches. the sign ambiguity of line segments is fixed by a simple congruency constraint. In the second stage, a Hough clustering technique based on the position of line segments is applied to verify potential matches. Any paired line segments of a match that cannot be brought to overlap by the translation determined by the clustering are removed from the match. Unlike previous methods, this algorithm combats noise more effectively, and ensures the global consistency of a match. While the original motivation for the algorithm is multiple-object motion estimation from stereo image sequences, the algorithm can also be applied to other domains, such as object recognition and object model construction from multiple views. >