This is important, because in recent years, according to the recommendations of good husbandry practices, there has been an aim to reduce the stocking density per 1 \(\hbox ^2\) of building area of the main livestock species such as cattle, pigs and poultry. The solution to this problem may be industrial insect breeding with minimised human labour and high stocking rates per unit building area. The United Nations (UN) predicts that human protein consumption will reach 39 grams per day in 2030, and 57 grams in 2050 1. Preference is given to livestock systems that use less water, minimise space and reduce greenhouse gas emissions. The current problems of feeding an ever-increasing human population involve meeting the demand for animal protein without the environmental costs associated with animal husbandry. The obtained results (average \(F1>0.88\) for ISM and average \(F1>0.95\) for SSM) confirm the great potential of the proposed system. Synthetic image generation using a collection of labelled objects was used, which significantly reduced the development time of the models and reduced the problems of dense scenes and the imbalance of the considered classes. The modules were developed using machine learning models (Mask R-CNN, U-Net, LDA), and were validated on different samples of real data. The larvae phenotyping module (LPM) calculated features for both individual larvae (length, curvature, mass, division into segments, and their classification) and the whole population (length distribution). The semantic segmentation module (SSM) extracted feed, chitin, and frass from the obtained image. The instance segmentation module (ISM) detected individual growth stages (larvae, pupae, beetles) of Tenebrio molitor, and also identified anomalies: dead larvae and pests. Present research involves the development of a 3-module system for monitoring Tenebrio molitor breeding. The large scale of Tenebrio molitor breeding makes automation of the process, which is supported by a monitoring system, essential. The Tenebrio molitor has become the first insect added to the catalogue of novel foods by the European Food Safety Authority due to its rich nutritional value and the low carbon footprint produced during its breeding.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |