<title>Evaluation of SAR ATR algorithm performance sensitivity to MSTAR extended operating conditions</title>

Abstract

Testing a SAR Automatic Target Recognition (ATR) algorithm at or very near its training conditions often yields near perfect results as we commonly see in the literature. This paper describes a series of experiments near and not so near to ATR algorithm training conditions. Experiments are setup to isolate individual Extended Operating Conditions (EOCs) and performance is reported at these points. Additional experiments are setup to isolate specific combinations of EOCs and the SAR ATR algorithm's performance is measured here also. The experiments presented here are a by-product of a DARPA/AFRL Moving and Stationary Target Acquisition and Recognition (MSTAR) program evaluation conducted in November of 1 997. Although the tests conducted here are in the domain of EOCs, these tests do not encompass the "real world" (i.e., what you might see on the battlefield) problem. In addition to performance results this paper describes an evaluation methodology including the Extended Operating Condition concept, as well as, data; algorithm; and figures of merit. In summary, this paper highlights the sensitivity that a baseline Mean Squared Error (MSE) ATR algorithm has to various operating conditions both near and varying degrees away from the training conditions.

Support subspaces method for synthetic aperture radar automatic target recognition

“…For two specified class indices, k, l are formed as an initial pair of support subspaces (X k;i ; X l;j are matrices of sizes N Â d). Then, in algorithm, decision is made, distinguishing the test vectors to one of the classes in accordance with equations (2) to (5). The value of the correctly recognized vectors is saved.…”

“…As a result of excluding vectors that have a maximum of conjugacy index, the remaining vectors form borders between classes. Therefore, recognition is implemented using equation (5), as it is evident that vectors within this border will be recognized successfully. In many cases, the vectors located close to this border will also be recognized.…”

“…[1][2][3] For example, Defense Advanced Research Projects Agency (DARPA) obtained SAR images of ground targets in different poses, which contain the moving and stationary target acquisition and recognition (MSTAR) public release data set, 4 which many researchers use. [5][6][7][8][9][10][11][12][13][14][15] In the majority of cases, they apply a double-stage approach for object recognition.…”

SAR Automatic Target Recognition Based on Deep Convolutional Neural Networks

“…The collection was jointly sponsored by Defense Advanced Research Projects Agency (DARPA) and Air Force Research Laboratory as part of the Moving and Stationary Target Acquisition and recognition (MSTAR) program [29][30]. The public released datasets include 10 different types of ground military targets (BMP2, BTR70, T72, BTR60, 2S1, BRDM2, D7, T62, ZIL131, ZSU23/4).…”

Radar Automatic Target Recognition Based on Sequential Vanishing Component Analysis

“…The MSATR database contains X-band SAR images captured at depression angles 15 deg and 17 deg over the full aspect angles with 1 ft × 1 ft resolution for 10 ground vehicle targets. A detailed description about MSATR database is given in [17]. HRRPs are extracted from SAR images, and the creation process is illustrated in Figure 6 [18].…”