摘要
Automated image systems to characterize aquatic organisms improve research and enable fast response to environmental risk situations. In November 2015, a dam in Mariana City-MG (Brazil) collapsed and led to the disposal of mud tailings from the mining process to the Doce River. The accident resulted in several casualties and incalculable damage to surrounding communities and the environment. The mud increased water turbidity, an essential condition to the functioning of the image analysis systems, and directly affected the characterization of the organisms, making it impossible to distinguish copepods in the mud, due to the blurred outline. To get a quick response evaluating environmental situations, this work aimed to develop and test different algorithms characterizing and classifying copepods by their size (length and area) using in situ images acquired by the Lightframe On-Sight Keyspecies Investigation device. Field tests were carried out under different turbidity levels throughout the gradient observed in the coastal zone adjacent to the Doce River. The best algorithm reduced nearly 50% of the noise in some images when compared with manual treatment and led to 96% accuracy in measurement and counting. Semi-automated devices that perform post-processing corrections are suitable for fast environmental evaluation under high turbidity scenarios.
Automated image systems to characterize aquatic organisms improve research and enable fast response to environmental risk situations. In November 2015, a dam in Mariana City-MG (Brazil) collapsed and led to the disposal of mud tailings from the mining process to the Doce River. The accident resulted in several casualties and incalculable damage to surrounding communities and the environment. The mud increased water turbidity, an essential condition to the functioning of the image analysis systems, and directly affected the characterization of the organisms, making it impossible to distinguish copepods in the mud, due to the blurred outline. To get a quick response evaluating environmental situations, this work aimed to develop and test different algorithms characterizing and classifying copepods by their size (length and area) using in situ images acquired by the Lightframe On-Sight Keyspecies Investigation device. Field tests were carried out under different turbidity levels throughout the gradient observed in the coastal zone adjacent to the Doce River. The best algorithm reduced nearly 50% of the noise in some images when compared with manual treatment and led to 96% accuracy in measurement and counting. Semi-automated devices that perform post-processing corrections are suitable for fast environmental evaluation under high turbidity scenarios.
