DETECTING, TRACKING AND COUNTING FISH IN LOW QUALITY UNCONSTRAINED UNDERWATER VIDEOS

TLDR

Real‑time underwater footage from the Ken‑Ding sub‑tropical coral reef, managed by EcoGrid in Taiwan, remains largely unanalyzed by marine biologists. The study presents a machine‑vision system that detects, tracks, and counts fish in such videos. The system integrates video texture analysis, dual‑algorithm fish detection combined for higher accuracy, and CamShift‑based tracking to handle fluctuating fish numbers. Tested on 20 videos, the method achieved up to 85 % accuracy and works reliably in murky water, algae, moving plants, and low‑contrast conditions.

Abstract

In this work a machine vision system capable of analysing underwater videos for detecting, tracking and counting fish is presented. The real-time videos, collected near the Ken-Ding sub-tropical coral reef waters are managed by EcoGrid, Taiwan and are barely analysed by marine biologists. The video processing system consists of three subsystems: the video texture analysis, fish detection and tracking modules. Fish detection is based on two algorithms computed independently, whose results are combined in order to obtain a more accurate outcome. The tracking was carried out by the application of the CamShift algorithm that enables the tracking of objects whose numbers may vary over time. Unlike existing fish-counting methods, our approach provides a reliable method in which the fish number is computed in unconstrained environments and under several scenarios (murky water, algae on camera lens, moving plants, low contrast, etc.). The proposed approach was tested with 20 underwater videos, achieving an overall accuracy as high as 85%.