Object Recognition Using Feature-and Color-Based Methods

NASA’s Jet Propulsion Laboratory

An improved adaptive method of processing image data in an artificial neural network has been developed to enable automated, real-time recognition of possibly moving objects under changing (including suddenly changing) conditions of illumination and perspective. The method involves a combination of two prior object-recognition methods — one based on adaptive detection of shape features and one based on adaptive color segmentation — to enable recognition in situations in which either prior method by itself may be inadequate.

This Optimal Adaptive Architecture involves interaction between a shape-feature-based and a color-segmentation-based method in a cyclic computation. Using shape adaptive features and color adaptive features from the previous cycle, an object and region of interest containing the object are identified in the present image by means of feature detection and color segmentation. The region of interest is then used for sampling data to adapt a new shape and color features for the image during the next cycle.

The chosen prior feature-based method is known as adaptive principal-component analysis (APCA); the chosen prior color-based method is known as adaptive color segmentation (ACOSE). These methods are made to interact with each other in a closed-loop system (see figure) to obtain an optimal solution of the object-recognition problem in a dynamic environment.

One of the results of the interaction is to increase, beyond what would otherwise be possible, the accuracy of the determination of a region of interest (containing an object that one seeks to recognize) within an image. Another result is to provide a minimized adaptive step that can be used to update the results obtained by the two component methods when changes of color and apparent shape occur. The net effect is to enable the neural network to update its recognition output and improve its recognition capability via an adaptive learning sequence.

In principle, the improved method could readily be implemented in integrated circuitry to make a compact, low-power, real-time object-recognition system. It has been proposed to demonstrate the feasibility of such a system by integrating a 256-by-256 active-pixel sensor with APCA, ACOSE, and neural processing circuitry on a single chip. It has been estimated that such a system on a chip would have a volume no larger than a few cubic centimeters, could operate at a rate as high as 1,000 frames per second, and would consume in the order of milliwatts of power.

This work was done by Tuan Duong, Vu Duong, and Allen Stubberud of Caltech for NASA's Jet Propulsion Laboratory.

In accordance with Public Law 96-517, the contractor has elected to retain title to this invention. Inquiries concerning rights for its commercial use should be addressed to:

Innovative Technology Assets

Management

JPL

Mail Stop 202-233

4800 Oak Grove Drive

Pasadena, CA 91109-8099

(818) 354-2240

E-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.

Refer to NPO-41370, volume and number of this NASA Tech Briefs issue, and the page number.