A deep learning model for estimating body weight of live pacific white shrimp in a clay pond shrimp aquaculture

Abstract

This paper presents a novel approach to address the essential challenge of accurately determining the total weight of shrimp within aquaculture ponds. Precise weight estimation is crucial in mitigating issues of overfeeding and underfeeding, thus enhancing efficiency and productivity in shrimp farming. The proposed system leverages image processing techniques to detect individual live shrimp and extract pertinent features for weight estimation within a clay pond environment. Specifically, an automated feed tray captures images of live shrimp, which are then processed using a combination of Detectron2, PyTorch, and CUDA (Compute Unified Device Architecture) for individual shrimp detection. Essential features such as area, perimeter, width, length, and posture are extracted through image analysis, enabling accurate estimation of shrimp weight. An Artificial Neural Network (ANN) model, utilizing these features, accurately predicts shrimp weight with a coefficient of determination (R²) of 94.50% when incorporating all extracted features. Furthermore, our system integrates a user-friendly web application that empowers farmers to monitor shrimp weight trends, facilitating precision feeding strategies and effective farm management. This study contributes a low-cost solution using a deep learning model to estimate the weight of live Pacific white shrimp in clay ponds, enabling daily weight calculations, helping farmers optimize feed quantities, providing shrimp size distribution insights, and reducing the Feed Conversion Ratio (FCR) for greater profitability. The procedure for shrimp feature extraction is also provided, including the calculation of shrimp length and width, as well as shrimp posture classification.