Search NASASearch

Engineering topics

Nandhakumar, N.

Publications and source records attributed to Nandhakumar, N..

Determining the 3-D structure and motion of objects using a scanning laser range sensor

In order for the EVAHR robot to autonomously track and grasp objects, its vision system must be able to determine the 3-D structure and motion of an object from a sequence of sensory images. This task is accomplished by the use of a laser radar range sensor which provides dense range maps of the scene. Unfortunately, the currently available laser radar range cameras use a sequential scanning approach which complicates image analysis. Although many algorithms have been developed for recognizing objects from range images, none are suited for use with single beam, scanning, time-of-flight sensors because all previous algorithms assume instantaneous acquisition of the entire image. This assumption is invalid since the EVAHR robot is equipped with a sequential scanning laser range sensor. If an object is moving while being imaged by the device, the apparent structure of the object can be significantly distorted due to the significant non-zero delay time between sampling each image pixel. If an estimate of the motion of the object can be determined, this distortion can be eliminated; but, this leads to the motion-structure paradox - most existing algorithms for 3-D motion estimation use the structure of objects to parameterize their motions. The goal of this research is to design a rigid-body motion recovery technique which overcomes this limitation. The method being developed 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. Once the motion parameters are determined, the structural distortion in the range images is corrected.

Nandhakumar, N.

A phenomenological approach to multisource data integration: Analysing infrared and visible data

A new method is described for combining multisensory data for remote sensing applications. The approach uses phenomenological models which allow the specification of discriminatory features that are based on intrinsic physical properties of imaged surfaces. Thermal and visual images of scenes are analyzed to estimate surface heat fluxes. Such analysis makes available a discriminatory feature that is closely related to the thermal capacitance of the imaged objects. This feature provides a method for labelling image regions based on physical properties of imaged objects. This approach is different from existing approaches which use the signal intensities in each channel (or an arbitrary linear or nonlinear combination of signal intensities) as features - which are then classified by a statistical or evident approach.

Nandhakumar, N.

Positional estimation techniques for an autonomous mobile robot

Techniques for positional estimation of a mobile robot navigation in an indoor environment are described. A comprehensive review of the various positional estimation techniques studied in the literature is first presented. The techniques are divided into four different types and each of them is discussed briefly. Two different kinds of environments are considered for positional estimation; mountainous natural terrain and an urban, man-made environment with polyhedral buildings. In both cases, the robot is assumed to be equipped with single visual camera that can be panned and tilted and also a 3-D description (world model) of the environment is given. Such a description could be obtained from a stereo pair of aerial images or from the architectural plans of the buildings. Techniques for positional estimation using the camera input and the world model are presented.

Nandhakumar, N.