Subpixel temporal spectral imaging

• We proposed methodologies to track subpixel targets in hyperspectral images.
• Spectral, spatial and temporal aspects are combined for robust tracking.
• The spectral signatures of endmembers and anomalies present in the images are estimated.
• Linear spectral temporal mixing models are formulated and compared with the data.
• The most consistent results in terms of mixing proportions locally approximate the trajectory of the target.

Hyperspectral and multispectral sensors are becoming more accessible. However, their use is still limited to certain civil and military applications such as satellite surveillance. Real-time methodologies for predicting target tracking combined with spectral data has many potential applications, including surveillance, fast moving object tracking, etc. However, tracking small objects in dense scenes is difficult with the assumption of coarse pixels and often requires the use of subpixel detection algorithms, and in particular the use of the linear mixture model. Here we propose to introduce the dimension of time to the problem of spectral unmixing to identify and track sub-pixel size targets. Results are provided within a particle filter framework for simulated and real scenes and compared with previously proposed methods for endmember extraction and tracking in spectral data.