Nickels and Hutchinson : Model - Based Tracking 101
نویسندگان
چکیده
| In this paper we present methods for tracking complex, articulated objects. We assume that an appearance model and the kinematic structure of the object to be tracked are given, leading to what is termed a model-based object tracker. At each time step, this tracker observes a new monocular grayscale image of the scene and combines information gathered from this image with knowledge of the previous connguration of the object to estimate the conngura-tion of the object at the time the image was acquired. Each degree of freedom in the model has an uncertainty associated with it, indicating the conndence in the current estimate for that degree of freedom. These uncertainty estimates are updated after each observation. An Extended Kalman Filter with appropriate observation and system models is used to implement this updating process. The methods that we describe are potentially beneecial to areas such as automated visual tracking in general, visual servo control, and human computer interaction. Unique aspects of this work include on-line model-based generation of complex features for use as templates, the characterization of uncertainties in point feature motion for use in assimilating feature tracking results, the use of the sum-of-squared-diierences (SSD) image correlation measure as a measurement of the observation error in feature tracking, and the use of complex articulated object models in tracking.
منابع مشابه
Weighting Observations: The Use of Kinematic Models in Object Tracking
We describe a model-based object tracking system that updates the configuration parameters of an object model based upon information gathered from a sequence of monocular images. Realistic object and imaging models are used to determine the expected visibility of object features, and to determine the expected appearance of all visible features. We formulate the tracking problem as one of parame...
متن کاملWeighting Observations : The use of Kinematic Models in Object
We describe a model-based object tracking system that updates the connguration parameters of an object model based upon information gathered from a sequence of monocular images. Realistic object and imaging models are used to determine the expected visibility of object features, and to determine the expected appearance of all visible features. We formulate the tracking problem as one of paramet...
متن کاملIntegrated Object Models for Robust Visual Tracking
The robustness of visual tracking, or following the movement of objects in images, can be improved with an explicit model for the objects being tracked. In this paper, we investigate the use of an object model in this way. An object geometric model can tell us what feature movements to expect, and what those movements reveal about object motion. We characterize the tracking problem as one of pa...
متن کاملModel-based tracking of complex articulated objects
In this paper, we present methods for tracking complex, articulated objects. We assume that an appearance model and the kinematic structure of the object to be tracked are given, leading to what is termed a model-based object tracker. At each time step, this tracker observes a new monocular grayscale image of the scene and combines information gathered from this image with knowledge of the prev...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 1999