Classifying Sonar Images: Can a Computer‐Driven Process Identify Eels?

Abstract

Abstract.-The purpose of this study was to explore the extent to which a computer-driven process can be used to classify sonar images. The data we present come from a feasibility study for a hydroacoustic monitoring system aimed at the automatic detection of downstream-migrating adult American eels Anguilla rostrata in the intake canal of a small hydroelectric station. The images were collected by a dual-frequency identification sonar with sufficient resolution to show the distinct shape and swimming motion of eels, and thus to allow confident visual identification. The goal was to find a set of image processing, tracking, and pattern recognition techniques that would reproduce the results of the visual classification. Of the three classification methods that we tested with our example data set, neural network analysis had the lowest misclassification rate for eels (7% of the eels being misclassified as debris) and the second-lowest misclassification rate for debris (5% of the debris being misclassified as eels). Discriminant function analysis misclassified 12% of the eels as debris and 4% of the debris as eels. A K-nearest-neighbor analysis initially provided the poorest results (17% misclassified eels and 12% misclassified debris). However, after applying an algebraic correction, K-nearest-neighbor analysis yielded an accurate estimate of the number of eels in the data set. We discuss the value of flagging cases of uncertain classification, how image processing and feature selection can affect the results, and how the numeric ratio of the targets present determines what error rates are acceptable. We conclude that, depending on the application, different degrees of automation may be achieved, ranging from a relatively high degree of human supervision in the classification of all potential targets to a fully automated process that requires only periodic quality control and adjustments of the classification model.

A Novel Approach to Surveying Sturgeon Using Side‐Scan Sonar and Occupancy Modeling

“…Unlike other hydroacoustic systems, with side-scan sonar it is difficult to create a fully objective method for identifying fish. With DIDSON, swimming motion as well as target shape can be evaluated to identify species; using split-beam sonar, it is possible to quantify target strength with prior calibration (Nealson and Brundage 2007;Mueller et al 2008). While DIDSON may be more useful for identifying species, it is more limited in scanning range, is more expensive than side-scan sonar units, is more cumbersome to deploy in the field, and lacks mapping capability.…”

Realtime Classification of Fish in Underwater Sonar Videos

“…Overall, most (if not all) investigations of DIDSON data are based on visual analyses of the image sequences whereas computer‐driven image analysis is only rudimentary developed; see Mueller et al . (, ) and references given there.…”

Can acoustic shadows identify fish species? A novel application of imaging sonar data

“…Eel exhibits special body architecture in combination with special swimming behaviour (Gray 1933; Webb 1982), leading to recognisable patterns in the videos as well as in echograms. Mueller et al. (2008) presented a computer‐driven process that classified DIDSON images of eel and debris with high accuracy.…”