Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Precision Aquaculture: An Integrated Computer Vision and IoT Approach for Optimized Tilapia Feeding

Rania Hossam, Ahmed Heakl, Walid Gomaa

TL;DR

This work presents a unified computer vision and IoT system for precision Tilapia feeding, leveraging YOLOv8-based keypoint detection and depth estimation to infer fish length and weight, paired with IoT-enabled water-quality sensing to optimize feed. The approach uses dual synchronous cameras, an edge-optimized inference pipeline, and a mobile app for remote monitoring, achieving 94% keypoint precision and 96% counting accuracy on Tilapia data, with real-world testing showing strong alignment to training results. A feeding-allowance model translates population size and estimated weight into daily feed, supported by a load-cell–driven dispensing mechanism and MQTT-based data flow to a backend server. The study reports the potential for up to 58× productivity gains under optimal conditions, driven by precise stock management and waste reduction, while acknowledging limitations such as dataset scope and environmental variability. Overall, the integrated CV–IoT framework offers a scalable, edge-capable solution for sustainable aquaculture, with open pathways for broader validation and cross-species extension.

Abstract

Traditional fish farming practices often lead to inefficient feeding, resulting in environmental issues and reduced productivity. We developed an innovative system combining computer vision and IoT technologies for precise Tilapia feeding. Our solution uses real-time IoT sensors to monitor water quality parameters and computer vision algorithms to analyze fish size and count, determining optimal feed amounts. A mobile app enables remote monitoring and control. We utilized YOLOv8 for keypoint detection to measure Tilapia weight from length, achieving \textbf{94\%} precision on 3,500 annotated images. Pixel-based measurements were converted to centimeters using depth estimation for accurate feeding calculations. Our method, with data collection mirroring inference conditions, significantly improved results. Preliminary estimates suggest this approach could increase production up to 58 times compared to traditional farms. Our models, code, and dataset are open-source~\footnote{The code, dataset, and models are available upon reasonable request.

Precision Aquaculture: An Integrated Computer Vision and IoT Approach for Optimized Tilapia Feeding

TL;DR

This work presents a unified computer vision and IoT system for precision Tilapia feeding, leveraging YOLOv8-based keypoint detection and depth estimation to infer fish length and weight, paired with IoT-enabled water-quality sensing to optimize feed. The approach uses dual synchronous cameras, an edge-optimized inference pipeline, and a mobile app for remote monitoring, achieving 94% keypoint precision and 96% counting accuracy on Tilapia data, with real-world testing showing strong alignment to training results. A feeding-allowance model translates population size and estimated weight into daily feed, supported by a load-cell–driven dispensing mechanism and MQTT-based data flow to a backend server. The study reports the potential for up to 58× productivity gains under optimal conditions, driven by precise stock management and waste reduction, while acknowledging limitations such as dataset scope and environmental variability. Overall, the integrated CV–IoT framework offers a scalable, edge-capable solution for sustainable aquaculture, with open pathways for broader validation and cross-species extension.

Abstract

Traditional fish farming practices often lead to inefficient feeding, resulting in environmental issues and reduced productivity. We developed an innovative system combining computer vision and IoT technologies for precise Tilapia feeding. Our solution uses real-time IoT sensors to monitor water quality parameters and computer vision algorithms to analyze fish size and count, determining optimal feed amounts. A mobile app enables remote monitoring and control. We utilized YOLOv8 for keypoint detection to measure Tilapia weight from length, achieving \textbf{94\%} precision on 3,500 annotated images. Pixel-based measurements were converted to centimeters using depth estimation for accurate feeding calculations. Our method, with data collection mirroring inference conditions, significantly improved results. Preliminary estimates suggest this approach could increase production up to 58 times compared to traditional farms. Our models, code, and dataset are open-source~\footnote{The code, dataset, and models are available upon reasonable request.
Paper Structure (19 sections, 3 equations, 6 figures, 3 tables)

This paper contains 19 sections, 3 equations, 6 figures, 3 tables.

Table of Contents

  1. INTRODUCTION
  2. RELATED WORK
  3. Fish Mass and Length Estimation Techniques
  4. Fish Feeding Techniques
  5. METHODS
  6. Tilapia Fish Weight Estimation
  7. Keypoint Annotation and Data Collection
  8. Calculating Fish Length
  9. Calculating Fish Count
  10. Feed Estimation
  11. IOT SYSTEM
  12. RESULTS & DISCUSSION
  13. YOLOv8 Performance on Tilapia Dataset
  14. Comparative Analysis with Existing Models
  15. YOLOv8 & Edge Computing
  16. ...and 4 more sections

Figures (6)

  • Figure 1: Description of fish lengths. We opt to measure the maximum standard length to calculate fish weight froese2014length.
  • Figure 2: Examples for annotation for fish counting.
  • Figure 3: Our IoT system architecture and flow for automated aquarium monitoring and feeding.
  • Figure 4: Interior view of the prototype fish feeding system, showing electrical wiring, sensors, and mechanical components housed within a wooden enclosure.
  • Figure 5: Feeding pump mechanism.
  • ...and 1 more figures