Near-infrared Image Filtering For Pedestrian Surveillance


An image processing approach is investigated which has low computational complexity and which uses near-infrared imaging. The target application is a surveillance system for pedestrian traffic. Near-infrared light has potential benefits including non-visible illumination requirements. An image-processing algorithm for monitoring pedestrians is implemented in outdoor and indoor environments with frequent traffic. The image sets consist of persons walking in the presence of foreground as well as background objects at different times during the day. The complex, cluttered environments are highly variable, e.g. shadows and moving foliage. The approach consists of thresholding an image and creating a silhouette of selected objects in the scene. Filtering is used to eliminate noise. The computational results using MATLAB© show that the algorithm can effectively manipulate near-infrared images and that effective filtering is possible even in the presence of system noise and environmental clutter. The potential for automated surveillance based on near-infrared imaging and neural-network based feature processing is discussed. © 2012 SPIE.


Electrical and Computer Engineering

Keywords and Phrases

Image processing; Near-infrared imaging; Pedestrian detection; Surveillance

International Standard Book Number (ISBN)


International Standard Serial Number (ISSN)


Document Type

Article - Conference proceedings

Document Version

Final Version

File Type





© 2023 Society of Photo-optical Instrumentation Engineers, All rights reserved.

Publication Date

15 May 2012