Automated Detection, Classification and Counting of Fish in Fish Passages With Deep Learning

The Ocean Aware project, led by Innovasea and funded through Canada's Ocean Supercluster, is developing a fish passage observation platform to monitor fish without the use of traditional tags. This will provide an alternative to standard tracking technology, such as acoustic telemetry fish tracking, which are often not appropriate for tracking at-risk fish species protected by legislation. Rather, the observation platform uses a combination of sensors including acoustic devices, visual and active sonar, and optical cameras. This will enable more in-depth scientific research and better support regulatory monitoring of at-risk fish species in fish passages or marine energy sites. Analysis of this data will require a robust and accurate method to automatically detect fish, count fish, and classify them by species in real-time using both sonar and optical cameras. To meet this need, we developed and tested an automated real-time deep learning framework combining state of the art convolutional neural networks and Kalman filters. First, we showed that an adaptation of the widely used YOLO machine learning model can accurately detect and classify eight species of fish from a public high resolution DIDSON imaging sonar dataset captured from the Ocqueoc River in Michigan, USA. Although there has been extensive research in the literature identifying particular fish such as eel vs. non-eel and seal vs. fish, to our knowledge this is the first successful application of deep learning for classifying multiple fish species with high resolution imaging sonar. Second, we integrated the Norfair object tracking framework to track and count fish using a public video dataset captured by optical cameras from the Wells Dam fish ladder on the Columbia River in Washington State, USA. Our results demonstrate that deep learning models can indeed be used to detect, classify species, and track fish using both high resolution imaging sonar and underwater video from a fish ladder. This work is a first step toward developing a fully implemented system which can accurately detect, classify and generate insights about fish in a wide variety of fish passage environments and conditions with data collected from multiple types of sensors.

Fish Segmentation in Sonar Images by Mask R-CNN on Feature Maps of Conditional Random Fields

Imaging sonar systems are widely used for monitoring fish behavior in turbid or low ambient light waters. For analyzing fish behavior in sonar images, fish segmentation is often required. In this paper, Mask R-CNN is adopted for segmenting fish in sonar images. Sonar images acquired from different shallow waters can be quite different in the contrast between fish and the background. That difference can make Mask R-CNN trained on examples collected from one fish farm ineffective to fish segmentation for the other fish farms. In this paper, a preprocessing convolutional neural network (PreCNN) is proposed to provide “standardized” feature maps for Mask R-CNN and to ease applying Mask R-CNN trained for one fish farm to the others. PreCNN aims at decoupling learning of fish instances from learning of fish-cultured environments. PreCNN is a semantic segmentation network and integrated with conditional random fields. PreCNN can utilize successive sonar images and can be trained by semi-supervised learning to make use of unlabeled information. Experimental results have shown that Mask R-CNN on the output of PreCNN is more accurate than Mask R-CNN directly on sonar images. Applying Mask R-CNN plus PreCNN trained for one fish farm to new fish farms is also more effective.

A SIFT-Like Feature Detector and Descriptor for Multibeam Sonar Imaging

Multibeam imaging sonar has become an increasingly important tool in the field of underwater object detection and description. In recent years, the scale-invariant feature transform (SIFT) algorithm has been widely adopted to obtain stable features of objects in sonar images but does not perform well on multibeam sonar images due to its sensitivity to speckle noise. In this paper, we introduce MBS-SIFT, a SIFT-like feature detector and descriptor for multibeam sonar images. This algorithm contains a feature detector followed by a local feature descriptor. A new gradient definition robust to speckle noise is presented to detect extrema in scale space, and then, interest points are filtered and located. It is also used to assign orientation and generate descriptors of interest points. Simulations and experiments demonstrate that the proposed method can capture features of underwater objects more accurately than existing approaches.

Deep Learning for Automated Detection and Identification of Migrating American Eel Anguilla rostrata from Imaging Sonar Data

Adult American eels (Anguilla rostrata) are vulnerable to hydropower turbine mortality during outmigration from growth habitat in inland waters to the ocean where they spawn. Imaging sonar is a reliable and proven technology for monitoring of fish passage and migration; however, there is no efficient automated method for eel detection. We designed a deep learning model for automated detection of adult American eels from sonar data. The method employs convolution neural network (CNN) to distinguish between 14 images of eels and non-eel objects. Prior to image classification with CNN, background subtraction and wavelet denoising were applied to enhance sonar images. The CNN model was first trained and tested on data obtained from a laboratory experiment, which yielded overall accuracies of >98% for image-based classification. Then, the model was trained and tested on field data that were obtained near the Iroquois Dam located on the St. Lawrence River; the accuracy achieved was commensurate with that of human experts.