The detection of humans under a wide variety of conditions
is a pre-requisite for significant improvements in such fields as urban warfare,
counter-terrorism, and protection of vulnerable road users (pedestrians,
cyclists). This problem can be broken initially into two parts: detecting
exposed humans, and detecting hidden (i.e., behind a solid object) humans.
Although certain types of electronic sensors have shown limited capabilities
under controlled conditions, no current sensing system can detecting even
exposed humans under all conditions. To advance the state-of-the-art in human
detection, integration—or fusing—of several different types of sensors will be
necessary. Research activity is needed in all aspects of the problem: studying
human electronic signatures, developing improved standalone sensors, fusing
sensors together, and establishing testing protocols and evaluation techniques
for the final sensor systems.
A closely related field is pre-crash sensing. The future of vehicle safety will benefit greatly from precrash detection – the ability of automobile to predict the occurrence of an accident before it occurs. There are many different sensor technologies currently available for pre-crash detection. However no single sensor technology has a demonstrated enough information gathering capability within the cost constraints of vehicle manufacturers to be used as a stand alone device. A proposed solution consists of combining information from multiple sensors in an intelligent computer algorithm to determine accurate precrash information. In this project, a list of sensors currently available on automobiles and those that show promise for future development is investigated. These sensors are then evaluated based on cost, information gathering capability and other factors. This work forms the basis for ongoing research in developing an integrated object detection and avoidance, precrash detection system.
The proposed project will rely on completed research on human signatures and standalone sensors to develop and test a compact ‘sensor fusion’ system. After collecting and evaluating data from existing studies, we will develop a new test protocol, obtain sensor samples, and test individual components. Comparing sensor outputs, we will develop algorithms to take advantage of the strengths of each sensor while plugging the ‘gaps’ in performance, resulting in sensor fusion. The resulting system will utilize at least two different types of sensors and will be small enough to be mounted on a vehicle or possibly hand-carried in the field. In this project we propose to develop and test a system for detection of exposed humans in a selection of positions under a multitude of conditions. This will enable the detection of most humans in the automotive environment as well as disguised humans for counter-terrorism or urban warfare use.
