Feature Extraction of Low Dimensional Sensor Returns for Autonomous Target Identification

Lum, Christopher W.; Rysdyk, Rolf

doi:10.2514/6.2008-7236

Cited by 4 publications

(2 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As shown in Figure 11, the flagging tape was highlighted in red, indicated the algorithm was able to successfully detect of the artificial fire despite the more difficult conditions [10]. Lastly, another artificial fire created at SERF is tested for detection.…”

Section: Image Processing Resultsmentioning

confidence: 99%

Automatic Wildfire Detection and Simulation using Optical Information from Unmanned Aerial Systems

Lum

Summers

Carpenter

et al. 2015

SAE Technical Paper Series

View full text Add to dashboard Cite

In many parts of the world, uncontrolled fires in sparsely populated areas are a major concern as they can quickly grow into large and destructive conflagrations in short time spans. Detecting these fires has traditionally been a job for trained humans on the ground, or in the air. In many cases, these manned solutions are simply not able to survey the amount of area necessary to maintain sufficient vigilance and coverage. This paper investigates the use of unmanned aerial systems (UAS) for automated wildfire detection. The proposed system uses low-cost, consumer-grade electronics and sensors combined with various airframes to create a system suitable for automatic detection of wildfires. The system employs automatic image processing techniques to analyze captured images and autonomously detect fire-related features such as fire lines, burnt regions, and flammable material. This image recognition algorithm is designed to cope with environmental occlusions such as shadows, smoke and obstructions. Once the fire is identified and classified, it is used to initialize a spatial/temporal fire simulation. This simulation is based on occupancy maps whose fidelity can be varied to include stochastic elements, various types of vegetation, weather conditions, and unique terrain. The simulations can be used to predict the effects of optimized firefighting methods to prevent the future propagation of the fires and greatly reduce time to detection of wildfires, thereby greatly minimizing the ensuing damage. This paper also documents experimental flight tests using a SenseFly Swinglet UAS conducted in Brisbane, Australia as well as modifications for custom UAS.

show abstract

Section: Image Processing Resultsmentioning

confidence: 99%

Automatic Wildfire Detection and Simulation using Optical Information from Unmanned Aerial Systems

Lum

Summers

Carpenter

et al. 2015

SAE Technical Paper Series

View full text Add to dashboard Cite

show abstract

“…One desired behavior is that the agent is to converge on regions of high score (a high probability that the target is located in a given location). Once an agent locates an anomaly, it should loiter there until a positive identification [30] can be made. While this occurs, other agents who are farther away will continue searching.…”

Section: A Algorithm Overviewmentioning

confidence: 99%

Search Algorithm for Teams of Heterogeneous Agents with Coverage Guarantees

Lum

Vagners

Rysdyk³

2010

Journal of Aerospace Computing, Information, and Communication

View full text Add to dashboard Cite

Among common intelligence, reconnaissance, and surveillance tasks, searching for a target in a complex environment is a problem for which autonomous systems are well suited. This work considers the problem of searching for targets using a team of heterogeneous agents. The system maintains a grid-based world model which contains information about the probability that a target is located in a given cell of the map. Agents formulate control decisions for a fixed number of time steps using a modular algorithm that allows parameterizations of agent capabilities. This paper investigates a solution that guarantees total map coverage. The control law for each agent does not require explicit knowledge of other agents. This yields a system which is scalable to a large number of vehicles. The resulting search patterns guarantee an exhaustive search of the map in the sense that all cells will be searched sufficiently to ensure that the probability of a target going unnoticed is driven to zero. Modifications to this algorithm for explicit cooperation between agents is also investigated. Nomenclature Bset ofz values defining spatial domain of occupancy based map B R locations reachable by agent in d steps Bset ofz values defining center of occupancy based map cells B R cell centers reachable by agent in d steps d prediction horizon, number of waypoints in path d i minimum distance from generator i to setB max f χ ( ) reward function for course deviation in (℘ 2 ) f d ( ) reward function for distance in (℘ 2 ) f h ( ) reward function for high score cell in (℘ 2 ) h sensor reliability factor in range [0, 1] I index of agent closer toB max than any other agent In (m) indices corresponding to runs where at least m agents find the target J 0 ( ) total reward function for (℘ 2 )

show abstract

A Modular Algorithm for Exhaustive Map Searching Using Occupancy Based Maps

Lum

Vagners

2009

AIAA Infotech@Aerospace Conference

View full text Add to dashboard Cite

Feature Extraction of Low Dimensional Sensor Returns for Autonomous Target Identification

Cited by 4 publications

References 10 publications

Automatic Wildfire Detection and Simulation using Optical Information from Unmanned Aerial Systems

Automatic Wildfire Detection and Simulation using Optical Information from Unmanned Aerial Systems

Search Algorithm for Teams of Heterogeneous Agents with Coverage Guarantees

A Modular Algorithm for Exhaustive Map Searching Using Occupancy Based Maps

Contact Info

Product

Resources

About