Measurement of live shrimp carapace length and its swimming speed in the cage culture using Multiple Object Tracking

Abstract

The carapace length of live shrimp is one of the important parameters to monitor the growth of the shrimp from time to time in cage culture, while its swimming speed is one of the key indicators to understanding the behavior and health of the shrimp. To estimate live shrimp carapace length and its swimming speed, we recorded a live shrimp in the cage culture using an underwater video camera. The collected datasets then being preprocessed and labeled. Before measuring the carapace length of the shrimp, we used the You Only Look Once (YOLO) v5 algorithm with K-fold cross-validation to detect shrimp heads. The accuracy value obtained is 85.6%, recall 85.4%, precision 77.3%, and F1-score 81.1%. Then the multiple object tracking (MOT) DeepSORT method was used to measure the shrimp’s carapace length and its swimming speed. The measurement results showed that the average length of the shrimp was 13.5-14.8 pixels, and the average speed of the shrimp was 62-78 pixels/second. We obtained that there is a strong linear relationship between carapace length and swimming speed of shrimp, namely SS = 11.864 CL + 43.419, where CL and SS are carapace length and swimming speed, respectively, with R-square = 0.9095. In conclusion, the live shrimp carapace length and its swimming speed can be measured using YOLO v5 and MOT DeepSORT directly and accurately.