Most shape estimation algorithms assume images of smooth surfaces with constant surface reflectance and often require knowledge of illuminant positions. These two requirements limit the applicability of such approaches to a small subset of imaged objects. In this paper a variational approach to the shape-from-color problem is presented that requires no knowledge of scene illuminants, and makes no assumptions regarding an object’s reflectance properties. Using a surface smoothness constraint, this technique can accurately reconstruct the shape of any continuous Lambertian surface given only a single color image. The capabilities of this algorithm are demonstrated using synthetic and real imagery.

This paper describes the design of an automated image segmentation system that provides high-resolution measurements of non-lint material, or trash, in cotton samples. Unlike previous trash analysis systems, this platform is able to accurately and precisely quantify the amount of foreign matter present in a sample in the presence of both illuminant degradation and fiber color variations by employing a new Bayesian Weighted K-Means (BWKM) approach to image segmentation. The design of the BWKM algorithm is presented in detail and its performance is verified and compared with other clustering techniques using both synthetic and real imagery.

Wide-Angle lenses are not often used for 3D reconstruction tasks, in spite of the potential advantages offered by their increased field-of-view, because (1) existing algorithms for high-distortion lens compensation perform poorly at image extremities and (2) procedures for the reconstruction of recti-linear images place a large burden on system resources. In this paper, a projection model based on quadric surfaces is presented which accurately characterizes the effect of wide-angle lenses across the entire image and allows for the use of novel feature matching strategies that do not require nonlinear distortion compensation.

Projective multi-sensor imagery and range data can be integrated to create visually coherent scene models via texture mapping if they can be properly registered before display. Presented in the paper is a novel stereo-based method for registering color and LIDAR images acquired from externally uncalibrated sensors for use in a such a visualization system. In the registration approach presented, corresponding features are extracted from LIDAR intensity/color image pairs and employed by a novel registration algorithm which recovers the relative pose between the two sensors by minimizing the difference between stereo and LIDAR estimated ranges.

Most current techniques for the robotic manipulation of nonrigid objects require the acquisition of detailed physical models prior to manipulation. In an effort to avoid the problems caused by such modeling, a three-phase paradigm based on human coordination studies has recently been reported. However, the vision-based model used to predict object motion depends on the the object's current shape, making manipulation planning difficult. In this paper, an alternative motion model for use in the three-phase framework is presented. Based on the novel concept of the cardinal spatial Jacobian, this new model is shape-independent while still requiring the use of no a priori physical object models.

Although many algorithms have been developed for motion estimation from range images, none are suited for use with scanning laser sensors. In this paper, the feature-based motion transformation model is restated to incorporate the nonzero pixel sampling rate of laser range cameras and a novel iterative, linear, feature-based technique for determining the 3D motion transformation of moving objects is developed using this new model. A technique is then presented which employs the motion recovered using the iterative algorithm to remove the structural distortion of the object in the range map. The performance of the motion recovery method is verified using simulated and experimental data.

Since the analytical expressions for the representation of nonrigid object structure and motion are severely underconstrained, current techniques for nonrigid object manipulation employ physical object models known prior to sensing. Recently, however, psychophysical studies have revealed that humans are able to discover proper motor coordination skills through sensory input without the use of previously known physical models. In this paper, a robust, discovery-driven, vision-based robotic manipulation algorithm for nonrigid objects, based on the novel concept of relative elasticity, is developed which requires the use of no a priori physical models. The manipulation technique is also experimentally verified on different flexible linear objects.

This paper analyses the performance of cepstral approaches for solving the stereo correspondence problem. A quantitative analysis of the effects of noise, foreshortening differences, and photometric variations on existing cepstral correspondence techniques is presented. A modified approach that is less sensitive to these effects is developed for textured scenes, and analytical arguments for its robustness are developed. The results of a comparative study of the new cepstral technique, the original cepstral algorithm and the cross-correlation approach are shown and discussed. The performance of the new method is experimentally verified on textured surfaces.

An innovative technique for rigid body motion estimation for use with sequential, time-of-flight laser radar scanners is presented. The method is an iterative, linear, feature-based approach which uses the non-zero image acquisition time constraint to accurately recover the motion parameters from the distorted structure of the 3-D range maps. The performance of the technique is experimentally verified using computer simulations.>

This paper describes the design of a binocular stereo system called CCLPS (Computerized Coal Profiling System) that provides dense, accurate disparity maps of coal as it is being transported in open rail cars. After a quantitative analysis of previously developed cepstral correspondence techniques which highlights the shortcomings of the cepstrum's matching ability in the presence of random noise and severe foreshortening distortion, we present a modified power cepstral approach that is less sensitive to these effects, along with analytical arguments verifying its robustness. The design of the CCLPS system is then discussed in detail and its performance is verified.>

A qualitative analysis of the effects of noise, foreshortening, and photometric variations on cepstral correspondence methods is presented. A modified approach that is less sensitive to these effects is developed, and analytical arguments for its robustness are given. The performance of the improved method is experimentally verified on real data.>