Amit Banerjee
Johns Hopkins University
43 Papers
320 Citations
Amit Banerjee is an academic researcher from Johns Hopkins University. The author has contributed to research in topics: Hyperspectral imaging & Kernel method. The author has an hindex of 17, co-authored 42 publications. Previous affiliations of Amit Banerjee include University of Maryland, College Park & Johns Hopkins University Applied Physics Laboratory.
Chat about Author
Papers
A support vector method for anomaly detection in hyperspectral imagery
TL;DR: Results are reported that demonstrate the improved performance and reduction in the false-alarm rate when using the SVDD-based detector on wide-area airborne mine detection and hyperspectral digital imagery collection experiment (HYDICE) imagery.
444
Tracking via object reflectance using a hyperspectral video camera
Hien M. Nguyen,Amit Banerjee,Rama Chellappa +2 more
- 13 Jun 2010
TL;DR: A new framework that incorporates radiative transfer theory to estimate object reflectance and the mean shift algorithm to simultaneously track the object based on its reflectance spectra is proposed and the combination of spectral detection and motion prediction enables the tracker to be robust against abrupt motions, and facilitate fast convergence of themean shift tracker.
204
Kernel fully constrained least squares abundance estimates
Joshua Broadwater,Rama Chellappa,Amit Banerjee,Philippe Burlina +3 more
- 23 Jul 2007
TL;DR: This paper presents such an algorithm that estimates the abundances in the kernel feature space while maintaining the non-negativity and sum-to-one constraints.
118
Scheduling an active camera to observe people
Cash Costello,Christopher P. Diehl,Amit Banerjee,Hesky Fisher +3 more
- 15 Oct 2004
TL;DR: The challenges involved in scheduling an active camera to observe multiple people to be discussed and some candidate scheduling policies are presented to address these challenges and evaluated.
82
Adaptive target detection in foliage-penetrating SAR images using alpha-stable models
TL;DR: A new target detection algorithm is proposed that incorporates symmetric alpha-stable (SalphaS) distributions for accurate clutter modeling, constructs a two-dimensional (2-D) site models for deriving local context, and exploits the site model for region-adaptive target detection.
81