Narrow Results

Many tasks, such as pose determination, object recognition and model building rely on a geometrical description of the visible surfaces derived from scene measurements. Even though much effort has been invested in surface description, robust extraction of surface parameters from scattered and noisy 3-D measurements is still a delicate task. For a given visible surface section, the extracted parameters should not depend on the sensor position in the scene nor on a particular measurement set on this surface. In this work, we show that a viewpoint invariant and stable local surface description can be extracted on sections where measurement constraints are redundant with respect to a polynomial model. A segmentation approach is developed to identify such stable sections. The approach is based on a measurement error model which takes into account the sensor’s viewpoint. An application of the approach to the extraction of straight line sections from single scan 3-D surface profiles is presented. The extracted stable linear sections are stored in a list that includes the estimated descriptive parameters for each section and indices of reliability for each description. The descriptive parameters obtained from images of the objects is compared with pre-measured parameters.

Active or deformable models have emerged as a popular modeling paradigm in computer vision. These models have the flexibility to adapt themselves to the image data, offering the potential for both generic object recognition and non-rigid object tracking. Because these active models are underconstrained, however, deformable shape recovery often requires manual segmentation or good model initialization, while active contour trackers have been able to track only an object's translation in the image. In this paper, we report our current progress in using a part-based aspect graph representation of an object¹⁴ to provide the missing constraints on data-driven deformable model recovery and tracking processes.

Butterfly-shaped features (with sizes from about 6 to 90 μm) were found on the surface of a shape-memory polymer (SMP) after a process of 50% stretching, slightly polishing, and then heating for shape recovery. We identified the underline mechanism, which is evidenced by the switching of butterflies by 90° from the previous direction after stretching. The case discussed here demonstrates the feasibility of using SMPs for patterning up to nanoscale for different shapes.

We demonstrate a simple and cost-effective approach to realize two combined surface features of different scales together, namely submillimeter-sized protrusion array and microwrinkles, atop a polystyrene shape-memory polymer. Two different types of protrusions, namely flat-top protrusion and crown-shaped protrusion, were studied. The array of protrusions was produced by the Indentation-Polishing-Heating (IPH) process. Compactly packed steel balls were used for making array of indents. A thin gold layer was sputter deposited atop the polymer surface right after polishing. After heating for shape recovery, array of protrusions with wrinkles on the top due to the buckling of gold layer was produced.

Active or deformable models have emerged as a popular modeling paradigm in computer vision. These models have the flexibility to adapt themselves to the image data, offering the potential for both generic object recognition and non-rigid object tracking. Because these active models are underconstrained, however, deformable shape recovery often requires manual segmentation or good model initialization, while active contour trackers have been able to track only an object's translation in the image. In this paper, we report our current progress in using a part-based aspect graph representation of an object¹⁴ to provide the missing constraints on data-driven deformable model recovery and tracking processes.

Many tasks, such as pose determination, object recognition and model building rely on a geometrical description of the visible surfaces derived from scene measurements. Even though much effort has been invested in surface description, robust extraction of surface parameters from scattered and noisy 3-D measurements is still a delicate task. For a given visible surface section, the extracted parameters should not depend on the sensor position in the scene nor on a particular measurement set on this surface. In this work, we show that a viewpoint invariant and stable local surface description can be extracted on sections where measurement constraints are redundant with respect to a polynomial model. A segmentation approach is developed to identify such stable sections. The approach is based on a measurement error model which takes into account the sensor's viewpoint. An application of the approach to the extraction of straight line sections from single scan 3-D surface profiles is presented. The extracted stable linear sections are stored in a list that includes the estimated descriptive parameters for each section and indices of reliability for each description. The descriptive parameters obtained from images of the objects is compared with pre-measured parameters.