Moving target detection in thermal infrared imagery using spatiotemporal information

Area of Science:

• Computer Vision
• Signal Processing
• Infrared Imaging

Background:

• Detecting moving targets in infrared imagery is crucial for surveillance and defense applications.
• Existing methods often struggle with achieving both high detection rates and low false alarm rates.

Purpose of the Study:

• To develop an efficient target detection algorithm for infrared imagery.
• To leverage spatiotemporal information for improved moving target detection.

Main Methods:

• A layered approach processing spatial information first, then temporal.
• Spatial information extracted using joint space-spatial-frequency distribution and Rényi entropy.
• Temporal information incorporated via background subtraction.

Main Results:

• The algorithm effectively utilizes both spatial and temporal features.
• Achieved a high detection rate and a low false alarm rate.
• Demonstrated a high F-measure value on experimentally generated data.

Conclusions:

• The proposed spatiotemporal algorithm offers an efficient solution for moving target detection in infrared imagery.
• The combination of spatial and temporal processing significantly enhances detection performance.
• The method shows promise for real-world applications requiring reliable target identification.