This paper presents a sensing approach where photo-transduction, multi-resolution feature extraction, scale-space integration and edge tracking are performed on a mixed (digital-analog) VLSI architecture in order to generate medium-level scene description. The proposed system is mainly targeted for robot vision applications where feature description is preferred to a set of raw or raster 2D images and edge maps. The Multiport Access photo-Receptor (MAR) is a CMOS sensor and represents the main sensory part of this integrated image acquisition system. VLSI also provides means to integrate analog computing, digital controller and DSP co-processor modules which define a powerful sensory chip set for focal plane image processing. A current version of the MAR sensor which implements 256/spl times/256 pixels includes 16 analog spatial filters which simultaneously compute multiresolution edge maps. This unique 2D hexagonal smart sensor approach which performs up to 8.5/spl times/10/sup 9/ arithmetic Op/sec during the acquisition/filtering phase and 25/spl times/10/sup 9/ Logical Op/sec for scale-space integration allows high resolution image capability. It represents a significant improvement for passive sensory units in a compact assembly for computer vision applications.>

This paper is concerned with the reliability of a shape description recovered from a set of scattered measurements. The recovering process of the description should not introduce a bias that is caused by specific acquisition conditions such as the presence of spurious measurements and the relative position of the sensor with respect to the object. Moreover, the recovered description should be stable for a sampling variation. While the fitting stage is based on a measurement error model which takes into account the sensor's viewpoint, the stability with sampling is tested by perturbing an hypothesized section. The validity of the approach is demonstrated by extracting reliable estimates of polynomial sections (lines, conics) from surface profile range data obtained from one or several viewpoints.

Robust extraction of surface parameters from multiple view scattered and noisy 3-D measurements is a delicate task. It is shown that a 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 these 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.>

Presents a method to compute the inter-frame transformation between two range image views of complex multi-part objects. No exact feature matching is attempted and no initial approximate transformation is provided. The method is naturally decomposed into two stages of initial estimation and final refinement of the transformation. A hierarchical triangulation-based surface representation provides an efficient way to select the control points at which the alignment of the two surfaces is to be evaluated. This representation also permits the selection of a manageable number of initial transformations among which at least one is to be in the parametric neighborhood of the actual transformation. Experimental results show that the computed transformation between two views of a complex multi-part object may provide angles of rotation within a fraction of a degree of the actual ones.>

The complexity of information extraction requires the development of efficient and dedicated hardware systems designed to operate in harmony with robot vision and automation. This paper describes a system which combines optical sensing with integrated focal-plane processing capabilities and integrated image post-processing. It is capable of automatic edge tracking and returns lists of connected pixels. I. INTRODUCTION Autonomous robotic applications require the use of reliable sensors since the capability to extract meaningful information from the surrounding environment is paramount to the accomplishment of any task. Among all sensing modalities, computer vision is the one that is most naturally associated with autonomous robotics. This originates from the fact that visual information can provide a very rich semantic description of the world. Vision operates through a process of successive refinements. The illuminance recorded at each component of the retina is processed, and low-level features such as edges and regions are extracted through relatively simple operations. Higher-level percepts such as depth and motion parameters can then be obtained from these low-level features. A very effective approach to the extraction of edges is based on the convolution of circularly symmetric masks with the illuminance image El). Among the available circularly symmetric masks is the well-known Laplacian of Gaussian (LOG) expressed as:

The Multiport Array Receptor (MAR), a system which combines optical sensing with integrated focal-plane processing capabilities, is described. Its central element is a photosensor array with hexagonal tesselation and complex peripheral selection logic which provides parallel analog readout over prescribed areas. An external computing module performs real-time spatial convolution at multiple resolutions while a closed-loop microprogrammed controller addresses regions of interest and supervises communication between the camera and the host computer. This integrated image sensor and processor implements programmed sequences of instruction primitives and yields a complete state description of each processed pixel. It is capable of automatic edge tracking and returns lists of connected pixels.>

A practical algorithm for subsurface defect extraction (blobs) in infrared or in low spatial content images is proposed. It first locates potential defects by a spatial sorting of the pixels, placed in decreasing order, based on their brightness. Labeling of the pixels is based on the distance. Defect shape is grown by gradually decreasing the threshold until a sudden increase in the number of pixels agglomerates together or an image boundary is encountered.>

An algorithm for extracting edges and plane regions of a polyhedral object in a three-dimensional (3D) range image is described. The object may be Convex or nonconvex. A model of the object is built with the regions extracted. Possible extension to cylindrical objects is also considered. The range images are obtained with a novel range-finder camera that can produce 128 × 256 or 256 × 256 surface element (surfcels) images. The edge detection is accomplished in five steps and yields edges one surfcel wide. The region-finding algorithm relies on the concept of the "hemispheric histogram." The histogram is built with the normals of groups of surfcels (patches) forming the image. Analysis of the hemispheric histogram gives global information on the surface orientation of the visible regions of an object. Once these regions are extracted, they are expanded with a region growing process. Geometric properties of the regions are computed by a simple contour following algorithm. Then, a relational model of the regions is built. The model gathers information that is independent of the position and orientation of the object ill the reference plane and could be Used for object recognition in an unsupervised 3D vision system.