The rise of in situ plankton imaging systems, particularly high-volume imagers such as the In Situ Ichthyoplankton Imaging System, has increased the need for fast processing and accurate classification tools that can identify a high diversity of organisms and nonliving particles of biological origin. Previous methods for automated classification have yielded moderate results that either can resolve few groups at high accuracy or many groups at relatively low accuracy. However, with the advent of new deep learning tools such as convolutional neural networks (CNNs), the automated identification of plankton images can be vastly improved. Here, we describe an image processing procedure that includes preprocessing, segmentation, classification, and postprocessing for the accurate identification of 108 classes of plankton using spatially sparse CNNs. Following a filtering process to remove images with low classification scores, a fully random evaluation of the classification showed that average precision was 84% and recall was 40% for all groups. Reliably classifying rare biological classes was difficult, so after excluding the 12 rarest taxa, classification accuracy for the remaining biological groups became > 90%. This method provides proof of concept for the effectiveness of an automated classification scheme using deep-learning methods, which can be applied to a range of plankton or biological imaging systems, with the eventual application in a variety of ecological monitoring and fisheries management contexts.

In scattering media, as in underwater or haze and fog in atmosphere, image contrast deteriorates significantly due to backscatter. This adversely affects the performance of many computer vision techniques developed for clear open-air conditions, including stereo matching, when applied to images acquired in these environments. Since the strength of the scattering depends on the distance to the scene points, the scattering field embodies range information that can be exploited for 3-D reconstruction. In this paper, we present an integrated solution for 3-D structure from stereovision that incorporates the visual cues from both disparity and scattering. The method applies to images of scenes illuminated by artificial sources and natural lighting, and performance improves with discrepancy between the backscatter fields in the two views. Neither source calibration nor knowledge of medium optical properties is required. Instead, backscatter fields at infinity, i.e., stereo images taken with no target in the field of view, are directly employed in the estimation process. Results from experiments with synthetic and real data demonstrate the key advantages of our method.

Consider photography in scattering media. One

A new structured-light method for 3D imaging has been developed which can simultaneously estimate both the geometric shape of the water surface and the geometric shape of underwater objects. The method requires only a single image and thus can be applied to dynamic as well as static scenes. Experimental results show the utility of this method in non-invasive underwater 3D reconstruction applications. The performance of the new method is studied through a sensitivity analysis for different parameters of the suggested method.

Abstract-Binocular stereo vision is a common technique for the recovery of three-dimensional shape. Underwater, backscatter degrades the image quality and consequently the performance of stereo vision-based 3-D reconstruction techniques. Recently, we proposed a method that exploits the depth cue in the backscatter components of stereo pairs, as an additional constraint for recovering the 3-D scene structure. In this paper, we compare the performance of this method with the application of classic normalized SSD-based minimization to raw underwater data, as well as to de-scattered images. Results of experiments with synthetic and real data are presented to assess the performance of our method with these other techniques.