Detection and tracking of gas plumes in LWIR hyperspectral video sequence data

TL;DR

This paper presents an effective method of visualizing hyperspectral video sequences containing chemical plumes and compares the ability of various clustering techniques to properly segment the chemical plume including K-means, spectral clustering, and the Ginzburg-Landau functional.

Abstract

Automated detection of chemical plumes presents a segmentation challenge. The segmentation problem for gas plumes is difficult due to the diffusive nature of the cloud. The advantage of considering hyperspectral images in the gas plume detection problem over the conventional RGB imagery is the presence of non-visual data, allowing for a richer representation of information. In this paper we present an effective method of visualizing hyperspectral video sequences containing chemical plumes and investigate the effectiveness of segmentation techniques on these post-processed videos. Our approach uses a combination of dimension reduction and histogram equalization to prepare the hyperspectral videos for segmentation. First, Principal Components Analysis (PCA) is used to reduce the dimension of the entire video sequence. This is done by projecting each pixel onto the first few Principal Components resulting in a type of spectral filter. Next, a Midway method for histogram equalization is used. These methods redistribute the intensity values in order to reduce flicker between frames. This properly prepares these high-dimensional video sequences for more traditional segmentation techniques. We compare the ability of various clustering techniques to properly segment the chemical plume. These include K-means, spectral clustering, and the Ginzburg-Landau functional.

Figures (13)

• Figure 1: The locations of the Romeo, Victory, and Tango cameras, and the location of the chemical plume release.
• Figure 2: A resulting frame after applying the AMSD. Red indicates higher probability of being target signature. Note the numerous areas outside of the gas plume that could be miscatergorized as gas.
• Figure 3: The first five principal components resulting from PCA. The first image is the first principal component, second image is second component, etc. Note how the first, third, and fifth components provide the most contrast between the background and gas plume.
• Figure 4: Results of the Midway equalization on the false color video sequence. Colors are created using false color mapped from the first, second, and third principal components. Each frame is at a different time step, illustrating the color fluctuations and gas plume release. The left column has the images with the color variance. The right column has the images resulting from applying the Midway equalization algorithm.
• Figure 5: Midway equalized false color video sequence utilizing first, third, and fifth principal components. This is the video with the principal components that provided the most contrast between gas plume and background.