Photon counting passive 3D image sensing for automatic target recognition

Abstract

In this paper, we propose photon counting three-dimensional (3D) passive sensing and object recognition using integral imaging. The application of this approach to 3D automatic target recognition (ATR) is investigated using both linear and nonlinear matched filters. We find there is significant potential of the proposed system for 3D sensing and recognition with a low number of photons. The discrimination capability of the proposed system is quantified in terms of discrimination ratio, Fisher ratio, and receiver operating characteristic (ROC) curves. To the best of our knowledge, this is the first report on photon counting 3D passive sensing and ATR with integral imaging.

Photon-counting double-random-phase encoding for secure image verification and retrieval

“…Photon-counting imaging techniques have been applied in many fields and in different spectral bandwidths [5,[7][8][9][10][11]. 2D image recognition using photon-limited distributions has also been demonstrated [7][8].…”

“…2D image recognition using photon-limited distributions has also been demonstrated [7][8]. The photon-counting approach on 3D object recognition has recently been investigated [5,11].…”

Three-Dimensional Visualization of Long Range Scenes by Photon Counting Mid-Wave Infrared Integral Imaging

“…Photon counting integral imaging has been proposed to perform 3D image reconstruction [7] and 3D target recognition [8]- [10] in photon starved conditions. In this paper we apply the maximum likelihood estimation (MLE) method for 3D visualization purposes on Mid-Wave Infrared (MWIR) images where photon starved conditions have been simulated by applying a photon counting process on the corresponding elemental images.…”

Photon Counting Linear Discriminant Analysis with Integral Imaging for Occluded Target Recognition

“…Photon-counting imaging has a broad range of applications such as night vision, laser radar imaging, and stellar imaging [9][10][11][12][13]. Automatic target recognition (ATR) at a low light level has been researched in [9][10][11][14][15][16]. Photon-counting nonlinear matched filtering and photon-counting linear discriminant analysis (LDA) have been proposed in [14] and [15], respectively.…”

“…Automatic target recognition (ATR) at a low light level has been researched in [9][10][11][14][15][16]. Photon-counting nonlinear matched filtering and photon-counting linear discriminant analysis (LDA) have been proposed in [14] and [15], respectively. Photon-counting scene reconstruction by maximum likelihood estimation (MLE) has been proposed in [16].…”