By Topic

Computational Intelligence for Visual Intelligence, 2009. CIVI '09. IEEE Workshop on

Date March 30 2009-April 2 2009

Filter Results

Displaying Results 1 - 13 of 13
  • [Front cover]

    Page(s): c1
    Save to Project icon | Request Permissions | PDF file iconPDF (270 KB)  
    Freely Available from IEEE
  • [Copyright notice]

    Page(s): ii
    Save to Project icon | Request Permissions | PDF file iconPDF (67 KB)  
    Freely Available from IEEE
  • Table of contents

    Page(s): iii
    Save to Project icon | Request Permissions | PDF file iconPDF (112 KB)  
    Freely Available from IEEE
  • Welcome message

    Page(s): iv - v
    Save to Project icon | Request Permissions | PDF file iconPDF (104 KB)  
    Freely Available from IEEE
  • Tutorial CIVI-T Understanding the spatial organization of image regions

    Page(s): vi
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (68 KB)  

    Space plays a fundamental role in human cognition. In everyday situations, it is often viewed as a construct induced by spatial relationships, rather than as a container that exists independently of the objects located in it. Spatial relationships, therefore, have been thoroughly investigated in many disciplines, including cognitive science, psychology, linguistics, geography and artificial intelligence. In computer vision and related fields, understanding the spatial organization of regions in images is an important task. The need to handle imprecision and uncertainty when processing spatial data has long been recognized, and spatial relationships often find good models in fuzzy relations, whether they are naturally loaded with ambiguity or associated with crisp mathematical definitions. The tutorial gives a summary on the subject and focuses on two fundamental questions: How to identify the spatial relationships between two given objects? How to identify the object that best satisfies a given relationship to a reference object? Applications in various domains, such as scene description, human-robot communication, object classification and retrieval, are presented. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Real-time tracking and pose-estimation of walking human from silhouette images

    Page(s): 1 - 7
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (734 KB) |  | HTML iconHTML  

    A reliable model-based human motion tracking scheme is presented. In this approach, silhouette image sequences from a top-view camera and a side-view camera work together to track human motion in 3D space in real time. The adoption of one top view camera introduces many attractive characteristics. A convenient calibration scheme is presented by decoupling different camera parameters to the largest extent. Point features that are easy to extract and robust to noise are used to track human motion and resolve ambiguity reliably for challenging motions such as an orientation-free walking. In addition, the framework is able to perform quick and satisfactory pose estimation with a real-time optimization processing. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Recognition of temporal events using multiscale bags of features

    Page(s): 8 - 13
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (763 KB) |  | HTML iconHTML  

    This paper presents a novel method for learning classes of temporal sequences using a bag-of-features approach. We define a temporal sequence as a bag of temporal features and show how this representation can be used for the recognition and segmentation of temporal events. A codebook of temporal descriptors, representing the local temporal texture, is automatically constructed from a set of sample sequences at multiple time scales. Temporal sequences are then encoded using accumulated histograms of parts from this codebook. This representation, though simple, proves to be surprisingly powerful and able to implicitly learn the sequence dynamics. Based on this representation, a multi-class classifier, treating the bag of features as the feature vector, is applied to estimate the corresponding class of the temporal sequence. Finally, extensive experiments are performed on two datasets to compare our method against state-of-the-art algorithms. The results show that our algorithm performs better and requires less training data than competing techniques. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A new hierarchical particle filtering for markerless human motion capture

    Page(s): 14 - 21
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1674 KB) |  | HTML iconHTML  

    Particle filtering (also known as the condensation algorithm) has been widely applied to model-based human motion capture. However, the number of particles required for the algorithm to work increases exponentially with the dimensionality of the model. In order to alleviate this computational explosion, we propose a two-level hierarchical framework. At the coarse level, the configuration space is discretized into large partitions and a suboptimal estimation is calculated. At the fine level, new particles in the vicinity of the suboptimal estimation are created using a more likely and narrow configuration space, allowing the original coarse estimate to be refined more efficiently. Our preliminary results demonstrates that this hierarchical framework achieves accurate estimation of the human posture with significantly reduction in the number of particles. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Contour tracking of human exercises

    Page(s): 22 - 28
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (5624 KB) |  | HTML iconHTML  

    We developed a novel markerless motion capture system and explored its use in documenting elder exercise routines in a health club. This system uses image contour tracking and swarm intelligence methods to track the location of the spine and shoulders during three exercises - treadmill, exercise bike, and overhead lateral pull-down. Preliminary results of our qualitative study demonstrate that our system is capable of providing important feedback about the posture and stability of elders while they are performing exercises. Study participants indicated that feedback from this system would add value to their exercise routines. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Image data mining and classification with DTree ensembles for linguistic tagging

    Page(s): 29 - 36
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (728 KB) |  | HTML iconHTML  

    Linguistic tagging of images require proper detection of language concepts from pictures, which is a challenging issue. Preparation of representative samples to demonstrate concepts is the first step; learning parameters from those training samples and setting up a classifier is the next step; proper tag set definition, extraction of relative contextual concepts, filtering and inference drawing for output tag set generation is the last step. A system based on a variant of an ensemble of decision trees classifier is developed which achieves promising results in classifying images targeted for linguistic tagging. A simple tag reconstruction strategy from classification voting information has been proposed. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Accurate planar image registration for an integrated video surveillance system

    Page(s): 37 - 43
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (3974 KB) |  | HTML iconHTML  

    Large-scale video surveillance systems typically deploy many video cameras over a wide area and display video streams on separate screens. Operators of this kind of systems have difficulties perceiving the whole pictures of intermixed views and are prone to losing track of targets. This paper presents a surveillance system which integrates videos from multiple cameras into a single comprehensive view. Operators can monitor the guarded area from any 3-D viewpoint. For integrated surveillance systems, the accuracy of image registration significantly affects the appearance of stitched views. This paper also presents a new planar image registration method in which the transformation parameters are decomposed from the homography matrix and are optimized according to a similarity measure between corresponding regions. The proposed registration method is practical and accurate, as demonstrated in our integrated surveillance system. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Semantic-driven context-aware visual information indexing and retrieval: Applied in the film post-production domain

    Page(s): 44 - 51
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (473 KB) |  | HTML iconHTML  

    A large volume of visual content is inaccessible until effective and efficient indexing and retrieval of such data is achieved. In this paper, we introduce the dream system, which is a knowledge-assisted semantic-driven context-aware visual information retrieval system applied in the film post production domain. We mainly focus on the automatic labelling and topic map related aspects of the framework. The use of the context-related collateral knowledge, represented by a novel probabilistic based visual keyword co-occurrence matrix, had been proven effective via the experiments conducted during system evaluation. The automatically generated semantic labels were fed into the topic map engine which can automatically construct ontological networks using topic maps technology, which dramatically enhances the indexing and retrieval performance of the system towards an even higher semantic level. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Author index

    Page(s): 52
    Save to Project icon | Request Permissions | PDF file iconPDF (54 KB)  
    Freely Available from IEEE