This study investigates the implementation of computer vision for automated prawn cultivation, focusing on density and growth estimation to contribute to aquaculture sustainability. Traditional methods of monitoring prawn density and growth involve manual measurements, which can be time-consuming, labor-intensive, and prone to human error. Addressing these challenges, the proposed system employs MobileNetV2 for prawn density estimation and achieves an accuracy of over 92. It successfully reduces the average cost and time required for farm monitoring at scale, making it a viable alternative to manual methodologies. © 2024 IEEE.