Discriminative sparsity for Sonar ATR

Abstract

Advancements in Sonar image capture have enabled researchers to apply sophisticated object identification algorithms in order to locate targets of interest in images such as mines [1] [2]. Despite progress in this field, modern sonar automatic target recognition (ATR) approaches lack robustness to the amount of noise one would expect in real-world scenarios, the capability to handle blurring incurred from the physics of image capture, and the ability to excel with relatively few training samples. We address these challenges by adapting modern sparsity-based techniques with dictionaries comprising of training from each class. We develop new discriminative (as opposed to generative) sparse representations which can help automatically classify targets in Sonar imaging. Using a simulated SAS data set from the Naval Surface Warfare Center (NSWC), we obtained compelling classification rates for multi-class problems even in cases with considerable noise and sparsity in training samples.

Localized dictionary design for geometrically robust sonar ATR

“…Next, we present how well SRC with LPM performs when compared to a popular image classification technique, SIFT feature SVM. In [11] and [2] the authors implemented SIFT feature SVMs towards Sonar ATR, the former of which in to handle pose-diversity. For this reason, we used this algorithm on our test images to provide context for SRC with LPM.…”

“…We found a L1LS method to produce the most satisfactory results for our work. [2] showed that it is possible produce compelling classification rates on consistently-posed test images of Sonar image using SRC. That said, in real-world cases the ability to collect targets all arranged in geometrically ideal positions is difficult if not infeasible.…”

“…Additionally, it is within reason to believe that there is redundancy within each class' blocks. In [2], the authors found that SRC can work in Sonar even when the dictionary lacks such redundancy so these essentially repeated blocks are unnecessary. For these reasons, we look at a dictionary learning procedure as a justifiable strategy to condense D.…”

“…SRC has been widely popular in computer vision circles since its introduction with [4] in 2009 because of its ability to perform even when pressed with occlusion and noise. The authors of [2] show how this characteristic makes SRC particularly attractive to Sonar ATR given how common * Supported by Office of Naval Research, Arlington, VA, Grant 0401531 noise is in this setting. In addition to this, they show that SRC can thrive even when under significantly constrained training settings making it even more fitting given how large the training sample has to be in Sonar ATR to incorporate the different looks objects have at different angles.…”

“…One issue with SRC methods are their ability to handle images whose targets are not aligned in the same manner as the training images. In the manner [4] and [2] execute their SRC scheme, targets need to have the same location and dimension, reducing flexibility in real-world scenarios. We look to address this issue of inconsistently-posed test images via localized pose management (LPM) which exploits localized geometric information present in the image by sampling the global image with multiple sub windows and uses these to initialize the input to a well-known dictionary learning algorithm.…”