Optimising the Workflow for Fish Detection in DIDSON (Dual-Frequency IDentification SONar) Data with the Use of Optical Flow and a Genetic Algorithm

Abstract

DIDSON acoustic cameras provide a way to collect temporally dense, high-resolution imaging data, similar to videos. Detection of fish targets on those videos takes place in a manual or semi-automated manner, typically assisted by specialised software. Exploiting the visual nature of the recordings, tools and techniques from the field of computer vision can be applied in order to facilitate the relatively involved workflows. Furthermore, machine learning techniques can be used to minimise user intervention and optimise for specific detection and tracking scenarios. This study explored the feasibility of combining optical flow with a genetic algorithm, with the aim of automating motion detection and optimising target-to-background segmentation (masking) under custom criteria, expressed in terms of the result. A 1000-frame video sequence sample with sparse, smoothly moving targets, reconstructed from a 125 s DIDSON recording, was analysed under two distinct scenarios, and an elementary detection method was used to assess and compare the resulting foreground (target) masks. The results indicate a high sensitivity to motion, as well as to the visual characteristics of targets, with the resulting foreground masks generally capturing fish targets on the majority of frames, potentially with small gaps of undetected targets, lasting for no more than a few frames. Despite the high computational overhead, implementation refinements could increase computational feasibility, while an extension of the algorithms, in order to include the steps of target detection and tracking, could further improve automation and potentially provide an efficient tool for the automated preliminary assessment of voluminous DIDSON data recordings.

Activity Segmentation and Fish Tracking From Sonar Videos by Combining Artifacts Filtering and a Kalman Approach

“…Moreover, researchers have explored automated fish segmentation in videos captured by DIDSON (Dual-Frequency IDentification SONar) in [12]. This approach involves two main parts: a fixed process that includes data extraction, preprocessing for geometric reconstruction, frame smoothing, merging into a continuous video stream, and background removal to enhance the quality and clarity of the raw DIDSON images.…”

Monitoring fish using imaging sonar: Capacity, challenges and future perspective

“…The sonar images contain a large number of speckle noises, which influences the accuracy of detection. To remove the small speckles and smooth sonar images, the noise removal filters, including wavelets transform (Zang et al, 2021), Gaussian temporal smoothing (Perivolioti et al, 2021), Kovesi method (Shen et al, 2020), median filter (Huang et al, 2014; Jing et al, 2016) and Gaussian filter (French et al, 2018), are used. The custom algorithm for sonar image pre‐processing is also studied.…”

“…As the edge extracted are commonly broken and fine, morphological operations such as filling and erosion are needed in the subsequent steps (Jing et al, 2017; Shahrestani et al, 2017). To improve the robustness to noise, the Gaussian mixture model and optical flow were also utilized for fish segmentation successfully (Kupilik & Petersen, 2014a; Perivolioti et al, 2021). In some complex scenarios, the foreground objects also contain non‐fish objects.…”