A method and system for high-throughput phenotyping of small-sized macrobrachium rosenbergii shrimps

By combining dark-box imaging and deep learning models, the problems of feature point labeling errors and posture fixation in the phenotypic measurement of small-sized giant freshwater prawns were solved, and multiple body size parameters and actual weight were acquired simultaneously, improving the accuracy and efficiency of early-stage phenotypic measurement in breeding.

CN121582324BActive Publication Date: 2026-05-08ZHEJIANG DANSHUI FISHERY RESEARCH INSTITUTE (ZHEJIANG DANSHUI FISHERY ENVIRONMENTAL MONITORING STATION)
7 Cites 0 Cited by

Patent Information

Application Number
CN202610100305.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2026-01-26
Publication Date
2026-05-08
Estimated Expiration
2046-01-26

AI Technical Summary

Technical Problem

Existing technologies struggle to perform high-throughput, accurate phenotypic measurements on small-sized giant freshwater prawns (3-5 cm in length), especially when they are transparent, have strong out-of-water stress, and are small in size. This results in problems such as high error rates in feature point labeling, difficulty in image acquisition, and difficulty in obtaining multiple body size parameters and true body weight.

Method used

By employing dark-box imaging technology combined with a deep learning model, and through adaptive adjustment of LED array light source and local grayscale histogram analysis, the contrast of shrimp body contours is enhanced. A joint deep learning model with shared feature encoders is used for shrimp body segmentation and key point detection, and a skeleton topology consistency loss is introduced to ensure the accuracy of key point coordinates. Weight data is collected synchronously with a high-precision electronic scale to form a structured phenotypic database.

Benefits of technology

This technology enables rapid, accurate, and non-contact measurement of multiple phenotypic parameters and weight in small-sized giant freshwater prawns, reducing characteristic point errors, improving the robustness and efficiency of measurements, and providing high-quality breeding data support.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The present application relates to the technical field of phenotype measurement in aquatic genetic breeding, and particularly relates to a high-throughput phenotype measurement method and system for small-sized Macrobrachium rosenbergii. In the measurement box, a dark box environment is constructed by a white shooting bottom plate, dark light-absorbing inner walls and an LED surface array light source, combined with preview graph rough segmentation and local gray histogram analysis, to adaptively adjust the light to make the shrimp body and the background form a stable bimodal gray distribution. On this basis, a segmentation-key point joint deep learning model is used to simultaneously output the shrimp body mask and standard key points, and the topological consistency loss constraint of the skeleton side length ratio and the included angle is introduced in the training to significantly reduce the key point mislabeling and drift caused by transparent body color. The present application realizes the rapid, non-contact, high-precision and high-throughput determination of the phenotype parameters and weight of small-sized Macrobrachium rosenbergii individuals, and provides a high-quality structured phenotype database for genetic evaluation and multi-trait joint selection.
Need to check novelty before this filing date? Find Prior Art