Peter F. Symosek

The imaging issue in an automatic face/disguise detection system

Automatic face recognition systems have made great strides. They still, however cannot cope with changes due to lighting and cannot detect disguises, Both of these issues are critical for the employment of face recognition systems in high security applications, such as embassy perimeters, federal plazas, mid the like. We propose novel imaging solutions that address these difficult problems. We demonstrate with theoretical and experimental arguments that a dual-band fusion system in the near infrared can segment human faces much more accurately than traditional visible band face detection systems. Face detection is useful by itself as an early warning method in certain surveillance applications. Accurate face delineation can also improve the performance of face recognition systems in certain difficult scenarios, particularly in outside environments. We also demonstrate with theoretical and experimental arguments that the upper band of the near infrared (1.4-2.4 /spl mu/m) is particularly advantageous for disguise detection purposes. This is attributable to the unique and universal properties of the human skin in this sub-band. We conclude the paper with a description of our ongoing and future efforts.

Automatic detection of vehicle occupants: the imaging problem and its solution

Abstract. The automatic detection and counting of vehicle occupants is a challenging research problem that was given little attention until recently. An automated vehicle-occupant-counting system would greatly facilitate the operation of freeway lanes reserved for car pools (high occupancy vehicle lanes or HOV lanes). There are three major aspects of this problem: (a) the imaging aspect (sensor phenomenology), (b) the pattern recognition aspect, and (c) the system architecture aspect. In this paper, we present a solution to the imaging aspect of the problem. We propose a novel system based on fusion of near-infrared imaging signals and we demonstrate its adequacy with theoretical and experimental arguments. We also compare our solution to other possible solutions across the electromagnetic spectrum, particularly in the thermal infrared and visible regions.

A near-infrared fusion scheme for automatic detection of vehicle passengers

We undertook a study to determine if the automatic detection and counting of vehicle passengers is feasible. An automated passenger counting system would greatly facilitate the operation of freeway lanes reserved for car-pools (HOV lanes). In the present paper we report our findings regarding the appropriate sensor phenomenology and arrangement for the task. We propose a novel system based on fusion of near-infrared imaging signals and we demonstrate its adequacy with theoretical and experimental arguments.

Automatic detection of vehicle passengers through near-infrared fusion

We undertook a study to determine if the automatic detection and counting of vehicle passengers is feasible. An automated passenger counting system would greatly facilitate the operation of freeway lanes reserved for buses, car-pools, and emergency vehicles (HOV lanes). In the present paper we report our findings regarding the appropriate sensor phenomenology and arrangement for the task. We propose a novel system based on fusion of near-infrared imaging signals and we demonstrate its adequacy with theoretical and experimental arguments.

PMMW/DGPS/GPS integrated situation awareness system

Integrating Passive Millimeter Wave camera (PMMW), Global Positioning System (GPS), and Differential Global Positioning System (DGPS) provides a pilot with a visual precision approach and landing in inclement weather conditions conceivably down to CAT III conditions. A DARPA funded, NASA Langley managed Technology Reinvestment Program (TRP) consortium consisting of Honeywell, TRW, Boeing, and Composite Optics Corporations is demonstrating the PMMW camera. The TRW developed PMMW camera displays the runway through fog, smoke, and clouds in day or night conditions. The Global Air Traffic Program Office entered into a Cooperative Research and Development Agreement (CRDA) with Honeywell to demonstrate DGPS. The Honeywell developed DGPS provides precision navigational data to within 1 m error where GPS has 100 m of error. In inclement weather the runway approach is initiated using GPS data until a range where DGPS data can be received. The runway is presented to the pilot using the PMMW image viewed via a Heads Up Display (HUD) or Head Mounted Display (HMD). At a range where DGPS data is available, a precise runway and horizon symbology is computed in the Flight Display Computer and overlaid on the PMMW image. Image processing algorithms operate on the PMMW image to identify and highlight obstacles on the runway. The integrated system provides the pilot with an enhanced situation awareness of the runway approach in inclement weather. When a DGPS ground station is not available at the landing area, image processing algorithms (again operating on the PMMW image) generate the runway and horizon symbology. GPS provides the algorithm with initial conditions for runway location and perspective. The algorithm then locates and highlights the runway and any obstacles on the runway. Honeywell Technology Center is performing research in the area of integrating the PMMW, DGPS, and GPS technologies to provide the pilot with the most necessary features of each system; namely: visibility, accuracy, obstacle detection, runway overlay, horizon symbology and availability.

Processor design optimization methodology for synthetic vision systems

Architecture optimization requires numerous inputs from hardware to software specifications. The task of varying these input parameters to obtain an optimal system architecture with regard to cost, specified performance and method of upgrade considerably increases the development cost due to the infinitude of events, most of which cannot even be defined by any simple enumeration or set of inequalities. We shall address the use of a PC-based tool using genetic algorithms to optimize the architecture for an avionics synthetic vision system, specifically passive millimeter wave system implementation.

Automated adaptation for ATR algorithms

For an automatic target recognition (ATR) technology contract, sponsored by the US Marine Corps Systems Command, and by Coastal Systems Station, Honeywell designed, mapped to Khoros, and evaluated state-of-the-art algorithms for target discrimination from an airborne platform. Honeywells baseline approach to improve traditional algorithm robustness is to use a functional maximization approach for representations of algorithm performance as a function of image metrics and algorithm parameters. Revised ATR parameter values are established by a hillclimbing algorithm that revises the ATR algorithm parameter values in the direction of the largest gradient of the function, thus attaining improved performance for a greater variety of scenarios than those for which the system was trained. The baseline ATR algorithms implemented for this program are designed to effectively exploit spectral features to enhance target cueing reliability. An innovative approach for the mapping of three of the individual waveband images from an array of multispectral images into a feature map which obtains high target versus background contrast is discussed. Experimental results are shown for flight test imagery.

Image processing for flight crew enhanced situation awareness

Maximum utilization of national airspace resources requires the development of systems which provide adverse weather landing guidance and allow for continued operations in low visibility conditions. The overall system, known as an enhanced situation awareness system (ESAS), encompasses a broad range of functions including a forward vision system (FVS). The FVS, the part of ESAS on which the paper focuses, consists of forward-looking, imaging sensors, and associated processors which collectively penetrate the atmospheric conditions. The FVS provides a spectrum of services to the flight crew and the aircraft in general. A series of image processing techniques crucial to FVS operation have been developed and implemented at Honeywell. The techniques fall into three core categories: image enhancement, feature extraction, and object recognition and tracking. In this paper, the issues involved in each category of processing are described, the most promising algorithms are described, and preliminary results of the image processing are presented. The sensor types explored to date include visible band TV, FLIR, and 35 GHz radar; results are shown on data from the visible band and 35 GHz radar imaging sensors.