AI-Based Shrimp Detection and Size Estimation Using Smartphone Sensors

DOI

10.2991/978-94-6239-828-3_28How to use a DOI?

Keywords

Shrimp aquaculture; Object detection; YOLOv8; Length estimation; Weight prediction; Smartphone imaging

Abstract

Shrimp aquaculture is a major contributor to global seafood production, where accurate monitoring of shrimp size and weight is essential for feeding management, growth evaluation, and harvest planning. In modern farming conditions, shrimp size is commonly assessed through manual sampling, which requires physical handling of individual shrimps. This process is labor-intensive and time-consuming, and repeated handling may also induce stress that negatively affects shrimp growth and survival.

This paper presents a smartphone-based system for whiteleg shrimp (Litopenaeus vannamei) detection, length estimation, and average weight prediction using computer vision methods. The proposed system employs a YOLOv8 object detection model to identify shrimps in images captured by standard smartphone cameras under actual aquaculture conditions. Shrimp length is estimated by converting pixel measurements obtained from detected bounding boxes into real-world dimensions through reference calibration using an object of a known size. Image-level features extracted from the detected shrimp regions are then used by a Support Vector Regression model to predict average shrimp weight.

The detection model was trained using 6,350 images and tested using a separate set of 280 images. Length estimation was evaluated using 29 separate images, while weight prediction was evaluated using another 26 images. The detection model achieved a precision of 0.988, a recall of 0.927, an mAP@0.5 of 0.982, and an mAP@0.5:0.95 of 0.877. Length estimation achieved an MAE of 1.54 cm, an RMSE of 1.63 cm, and a MAPE of 14.6%. Average weight prediction achieved an MAE of 1.05 g, an RMSE of 1.78 g, and a MAPE of 7.5%.

The results demonstrate the feasibility of combining shrimp detection, reference calibration, length estimation, and average weight prediction in one smartphone workflow under the tested outdoor farm conditions.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Yu-Yu Chen
AU  - Eka Sari Oktarina
AU  - Valentinus Roby Hananto
AU  - Victor Kryssanov
PY  - 2026
DA  - 2026/11/04
TI  - AI-Based Shrimp Detection and Size Estimation Using Smartphone Sensors
BT  - Proceedings of the 2026 11th International Conference on Sustainable Information Engineering and Technology (SIET 2026)
PB  - Atlantis Press
SP  - 316
EP  - 326
SN  - 2589-4900
UR  - https://doi.org/10.2991/978-94-6239-828-3_28
DO  - 10.2991/978-94-6239-828-3_28
ID  - Chen2026
ER  -