Mr. Stephen O'Hara Profile

Stephen O'Hara

Senior Scientist

SPIE Involvement:

Author

Websites:

Company Website

Publications (5)

Proceedings Article | 13 April 2009 Paper

Detecting people in IR border surveillance video using scale invariant image moments

Stephen O'Hara, Amber Fischer

Proceedings Volume 7340, 73400L (2009) https://doi.org/10.1117/12.818905

KEYWORDS: Video surveillance, Video, Cameras, Surveillance, Infrared imaging, Data analysis, Neural networks, Infrared cameras, Infrared detectors, Detection and tracking algorithms

Read Abstract +

Proceedings Article | 14 May 2007 Paper

Towards distributed ATR using subjective logic combination rules with a swarm of UAVs

Stephen O'Hara, Michael Simon, Qiuming Zhu

Proceedings Volume 6561, 65611G (2007) https://doi.org/10.1117/12.718321

KEYWORDS: Unmanned aerial vehicles, Automatic target recognition, Logic, Video, Cameras, Video processing, Video surveillance, Sensors, Surveillance, Target recognition

Read Abstract +

In this paper, we present our initial findings demonstrating a cost-effective approach to Aided Target Recognition (ATR) employing a swarm of inexpensive Unmanned Aerial Vehicles (UAVs). We call our approach Distributed ATR (DATR). Our paper describes the utility of DATR for autonomous UAV operations, provides an overview of our methods, and the results of our initial simulation-based implementation and feasibility study. Our technology is aimed towards small and micro UAVs where platform restrictions allow only a modest quality camera and limited on-board computational capabilities. It is understood that an inexpensive sensor coupled with limited processing capability would be challenged in deriving a high probability of detection (P_d) while maintaining a low probability of false alarms (P_fa). Our hypothesis is that an evidential reasoning approach to fusing the observations of multiple UAVs observing approximately the same scene can raise the P_d and lower the P_fa sufficiently in order to provide a cost-effective ATR capability. This capability can lead to practical implementations of autonomous, coordinated, multi-UAV operations. In our system, the live video feed from a UAV is processed by a lightweight real-time ATR algorithm. This algorithm provides a set of possible classifications for each detected object over a possibility space defined by a set of exemplars. The classifications for each frame within a short observation interval (a few seconds) are used to generate a belief statement. Our system considers how many frames in the observation interval support each potential classification. A definable function transforms the observational data into a belief value. The belief value, or opinion, represents the UAV's belief that an object of the particular class exists in the area covered during the observation interval. The opinion is submitted as evidence in an evidential reasoning system. Opinions from observations over the same spatial area will have similar index values in the evidence cache. The evidential reasoning system combines observations of similar spatial indexes, discounting older observations based upon a parameterized information aging function. We employ Subjective Logic operations in the discounting and combination of opinions. The result is the consensus opinion from all observations that an object of a given class exists in a given region.

Proceedings Article | 2 May 2007 Paper

An agent-based approach to decluttering the interfaces of multi-UAV command and control systems

Stephen O'Hara, Nathan Dwyer

Proceedings Volume 6561, 65610W (2007) https://doi.org/10.1117/12.718388

KEYWORDS: Unmanned aerial vehicles, Human-machine interfaces, Logic, Intelligence systems, Situational awareness sensors, Transparency, Control systems, Calculus, Fuzzy logic, Prototyping

Read Abstract +

Information overload and cluttered user interfaces can lead to decreased situational awareness and lowered performance of human operators. Irrelevant data increases searching times for tasks requiring the identification of threats, causing delayed decisions. Cognitive burden on the user increases as displays become more cluttered, which results in increased operator stress leading to poor decision-making ability. To address this issue, we have designed an intelligent agentbased system for the automatic de-cluttering of a representative net-centric interface designed for controlling multiple unmanned aerial vehicles (UAVs) by a single operator. Our concept is called ARID, for Agent-based Reduction of Information Density. The ARID hypothesis is that intelligent agents can improve operator performance by deemphasizing those aspects of a display that can be inferred as less-important to the mission goals. ARID agents receive information about the world via data feeds provided by various net-centric sources. Each agent has an understanding of the user interface symbols that are used to represent various entities, terrain features, and zones. The agent also is provided with a mission goal which is used for inferring the relevance of a given symbol to the success of the mission goal. First level facts, such as spatial relationships, are calculated by supporting agents and assigned a BDU (belief/disbelief/uncertainty) value. A dynamic set of rules provides an inference mechanism by which an agent can infer new facts from the given assertions. We have developed a Subjective Logic-based Evidential Reasoning Network that explicitly deals with belief and uncertainty in the knowledge base, and is used to derive a relevancy belief for every UI symbol in the map display. Subjective Logic is used to combine values when different sources provide different results for the same symbol. User Interface agents apply the results of the relevancy beliefs and transform the display to minimize the apparent clutter caused by less relevant elements. Two transformations, transparency and grouping, are used in the current implementation.

Proceedings Article | 27 April 2007 Paper

Towards an inexpensive computer-vision based automated landing system for small unmanned aerial vehicles

Kevin Blenkhorn, Stephen O'Hara

Proceedings Volume 6559, 65590B (2007) https://doi.org/10.1117/12.721245

KEYWORDS: Unmanned aerial vehicles, Cameras, Target detection, Video, Visualization, Machine vision, Computing systems, Computer vision technology, Imaging systems, Video processing

Read Abstract +

Proceedings Article | 9 April 2007 Paper

Collective agents interpolative integral (CAII) for asymmetric threat detection

Qiuming Zhu, Stephen O'Hara, Michael Simon, Eric Lindahl, Plamen Petrov

Proceedings Volume 6571, 65710I (2007) https://doi.org/10.1117/12.718322

KEYWORDS: Data modeling, Data fusion, Probability theory, Information fusion, Systems modeling, Computing systems, Computer architecture, Logic, Mathematical modeling, Prototyping

Read Abstract +

View contact details

UPDATE YOUR PROFILE

Is this your profile? Update it now.

Sign into your SPIE.org account

Don’t have a profile and want one?

Create an account on SPIE.org

Keywords/Phrases

Search In:

Publication Years