The invention relates to the technical field of
phenotype measurement in aquatic genetic breeding, in particular to a
macrobrachium rosenbergii small-size
shrimp high-
throughput phenotype measurement method and measurement
system. According to the method, a
camera obscura environment is constructed through a white shooting bottom plate, a dark
extinction inner wall and an LED area array
light source in a measuring box body, and illumination is adaptively adjusted by combining rough segmentation of a preview and analysis of a local gray
histogram, so that stable bimodal gray distribution is formed between a
shrimp body and a background. On the basis, a segmentation-key point combined
deep learning model is adopted, a
shrimp body
mask and a standard key point are output at the same time,
topological consistency loss constraints of a framework side length proportion and an included angle are introduced in training, and key point mismarking and drifting caused by the transparent body color are remarkably reduced. According to the method, rapid, non-contact, high-precision and high-
throughput measurement of
macrobrachium rosenbergii small-specification individual
phenotype parameters and weight is realized, and a high-quality structured phenotype
database is provided for genetic evaluation and multi-character combined selection.