Methods, systems, and apparatuses, including computer programs encoded on a computer-readable storage medium for estimating the shape, size, and mass of fish are described. A pair of stereo cameras may be utilized to obtain right and left images of fish in a defined area. The right and left images may be processed, enhanced, and combined. Object detection may be used to detect and track a fish in images. A pose estimator may be used to determine key points and features of the detected fish. Based on the key points, a three-dimensional (3-D) model of the fish is generated that provides an estimate of the size and shape of the fish. A regression model or neural network model can be applied to the 3-D model to determine a likely weight of the fish.

The present disclosure provides a method for artificial rearing of porcupine pufferfish fries in indoor cement ponds. The method includes the following steps: nursery pond preparation, ponding of newly hatched prelarvae, feeding strategies at fry rearing stages, water quality management during fry rearing, separate ponding of fries, and emergence of fries. Compared with the prior art, the method realizes large-scale production of artificial rearing of porcupine pufferfish fries through a strict control of the water quality and environmental conditions of a nursery pond, along with scientific and reasonable feeding and operation management based on biological characteristics and nutrient requirements of the porcupine pufferfish at different fry breeding stages.

The present disclosure provides a method for artificial rearing of porcupine pufferfish fries in indoor cement ponds. The method includes the following steps: nursery pond preparation, ponding of newly hatched prelarvae, feeding strategies at fry rearing stages, water quality management during fry rearing, separate ponding of fries, and emergence of fries. Compared with the prior art, the method realizes large-scale production of artificial rearing of porcupine pufferfish fries through a strict control of the water quality and environmental conditions of a nursery pond, along with scientific and reasonable feeding and operation management based on biological characteristics and nutrient requirements of the porcupine pufferfish at different fry breeding stages.

A method of monocular depth estimation includes receiving a plurality of monocular images corresponding to images of fish within a marine enclosure and further receiving acoustic data synchronized in time relative to the plurality of images. The plurality of images and the acoustic data are provided to a convolutional neural network (CNN) for training a monocular depth model. The monocular depth model is trained to generate, based on the received plurality of monocular images and the acoustic data, a distance-from-feeder estimate of a vertical biomass center of fish within the marine enclosure.

A method of surface splash scoring includes receiving, at an electronic device, a set of camera frames corresponding to images of a water surface. The electronic device processes the set of camera frames with a trained machine learning model to generate one or more quantifications associated with fish activity proximate the water surface. In some embodiments, a surface splash score is computed that represents an appetite level anticipated to be exhibited for a first time period. Subsequently, the electronic device generates an output indicative of the surface splash score.

An underwater camera system for monitoring fish in a fish pen is described. A stereoscopic camera may be used to determine dimensions of fish, and the underwater camera system may use the fish dimensions to estimate a biomass value of fish within the fish pen. The biomass value and rates of change of the biomass value may be used to adjust feeding of the fish in the fish pen. Images captured by the stereoscopic camera may be used to focus a variable focal lens camera on a fish to obtain high-resolution images that can be used for diagnosing fish conditions. Images captured by the stereoscopic camera may be used to predict motion of the fish, and the predicted motion may be used to generate various fish monitoring analytic values. The fish monitoring analytic values may be used to automatically control operation of the fish pen.

Bottom grading apparatuses for aquaculture systems are disclosed herein. An example system includes a vessel filled with water that receives fish, the vessel having a bottom surface with drain; a plenum in fluid communication with the vessel; a multiway valve in fluid communication with the plenum, a mortality pipe, and a grading pipe; and a mortality container in fluid communication with the mortality pipe and the vessel, wherein the fish can re-enter the vessel through the mortality container and deceased fish remain in the mortality container, wherein when the multiway valve is closed to the mortality pipe, the fish will divert through the grading pipe.

Bottom grading apparatuses for aquaculture systems are disclosed herein. An example system includes a vessel filled with water that receives fish, the vessel having a bottom surface with drain; a plenum in fluid communication with the vessel; a multiway valve in fluid communication with the plenum, a mortality pipe, and a grading pipe; and a mortality container in fluid communication with the mortality pipe and the vessel, wherein the fish can re-enter the vessel through the mortality container and deceased fish remain in the mortality container, wherein when the multiway valve is closed to the mortality pipe, the fish will divert through the grading pipe.

Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for escape detection and mitigation for aquaculture. In some implementations, a method includes obtaining one or more images that depict one or more fish within a population of fish that are located within an enclosure; providing, to one or more detection models configured to classify fish that are depicted within the images as likely being member or as likely not being member of a type of fish, the one or images; generating, as a result of providing the one or more images to the one or more detection models, a value that reflects a quantity of fish that are depicted in the images that are likely a member of the type of fish; and detecting a condition based at least on the value.

Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for escape detection and mitigation for aquaculture. In some implementations, a method includes obtaining one or more images that depict one or more fish within a population of fish that are located within an enclosure; providing, to one or more detection models configured to classify fish that are depicted within the images as likely being member or as likely not being member of a type of fish, the one or images; generating, as a result of providing the one or more images to the one or more detection models, a value that reflects a quantity of fish that are depicted in the images that are likely a member of the type of fish; and detecting a condition based at least on the value.