부산대학교 도서관

Discharges of treated industrial wastewater may impair the receiving surface water quality. Biological early warning systems (biosensors) for continuous holistic water quality monitoring may better tackle the wide range of potential threats from industrial activities (e.g. oxygen depletion, metal traces, chemical toxins). Commercial biosensor solutions based on mussels and oysters behavioural assessment have enabled overall water quality monitoring of industrial effluents. Although burrowing clams present worldwide ecological and economic importance and their behavioural changes are potential indicators of concerning environmental conditions, current technologies do not allow their use as biosensors. Proposing an experimental monitoring setup and comprehend the behavioural patterns of burrowing clams in different water quality conditions are the first steps towards reliable biosensor solutions for water quality assessment. The present work proposes an vision-based tool to assess clams’ behavioural patterns in different levels of water contamination. It may be basis for building holistic biosensor technology based on clams behavioural assessment for industrial effluent monitoring and early alarm. The proposed system measures the total occupied area by animals through a data acquisition system and data processing pipeline. An off-the-shelf camera setup registers top-view images of the animals inside a container. An image segmentation algorithm properly identify the clams and enables behavioral assessment. System suitability is explored in a case study using the yellow clam Amarilladesma mactroides and DCOIT contaminant. The performance of a Watershed and a machine learning segmentation models are investigated. Obtained results indicate both models can achieve high performance in this task. Behavioural tracking stage enables the use of statistical functions to observe behavioural changes in the animals, which may be proxy to overall water quality condition.