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.

A system and method are disclosed for training a system or a model to allow estimation of the value of livestock that is farmed for monetary gain. The various aspects of the invention include generation of data that is used to supplement or augment capture or real data, wherein the subject of the data is an animal. Labels or attributes are generated and validated.

A snapshot hyperspectral imaging method includes the steps of: S1, selecting a set of reference wavelengths for calibration, rectifying the shifted positions due to dispersion at each reference wavelength, and selecting a center wavelength; S2, estimating relative dispersion at each reconstructed wavelength with respect to the center wavelength; S3, generating a dispersion matrix describing the direction of dispersion, and generating a spectral response matrix using a spectral response curve of a sensor; S4, capturing images blurred with dispersion; S5, deblurring the dispersed images captured in S4 using the dispersion matrix and the spectral response matrix generated in S3 to obtain spectral data spatially aligned in all spectrums; and S6, projecting the aligned spectral data obtained in S5 into color space, extracting a foreground image by a threshold method, sampling the dispersed images obtained in S4 as strong prior constraints for the foreground image, and reconstructing accurate spatial hyperspectral data.

The present disclosure relates to the field of image processing and discloses an agricultural advisory system (100) comprising a user device (102) and a cloud server (104). The user device (102) captures a digital image of a scene, receives a sensed data corresponding to scene-related and environmental parameters, and transmits the image and the sensed data to the cloud server. The server (104) stores one or more pre-trained prediction models and a three-dimensional HyperIntelliStack which maps red green blue (RGB) pixel values with hyperspectral reflectance values. The server (104) receives the digital images and the sensed data, transforms the received image made of RGB pixel values into a hyperspectral image using the HyperIntelliStack data structure, computes vegetation indices for each pixel of the hyperspectral image to generate a segmented image, and generates at least one advisory for agriculture and allied areas using the segmented image and one or more prediction models.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for image segmentation and chemical analysis using machine learning. In some implementations, a system obtains a hyperspectral image that includes a representation of an object. The system segments the hyperspectral image to identify regions of a particular type on the object. The system generates a set of feature values derived from image data for different wavelength bands that is located in the hyperspectral image in the identified regions of the particular type. The system generates a prediction of a level of one or more chemicals in the object based on an output produced by a machine learning model in response to the set of feature values being provided as input to the machine learning model. The system provides data indicating the prediction of the level of the one or more chemicals in the object.

Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for fish weight estimation based on fish tracks identified in images. In some implementations, a method includes obtaining images of fish enclosed in a fish enclosure, identifying fish tracks shown in the images of the fish, determining a quality score for each of the fish tracks, selecting a subset of the fish tracks based on the quality scores, determining a representative weight of the fish in the fish enclosure based on weights of the fish shown in the subset of the fish tracks, and outputting the representative weight for display or storage at a device connected to the one or more processors.

A harvester selectively harvests edible crowns ready for harvesting. The harvester may include an imaging system for capturing image(s) of the edible crowns and a de-leafing component that removes leaves of the broccoli plant. For example, broccoli plants typically have an abundance of leaves that reside beneath, alongside of, and even above the edible crowns. The leaves may conceal the edible crowns and impact a quality of the image(s). The de-leafing component may be positioned in front of the imaging system, relative to a direction of travel of the harvester, to remove the leaves and isolate or expose the edible crown. Therein, the imaging system may image the edible crowns for use in determining whether the edible crowns are ready for harvesting.

In an embodiment, a method for estimating a composition of food includes: receiving a first three-dimensional (3D) image; identifying food in the first 3D image; determining a volume of the identified food based on the first 3D image; and estimating a composition of the identified food using a millimeter-wave radar.

A method, a computer program product, and a computer system for classifying bacteria. The method comprises extracting a morphology signature corresponding to one or more bacteria and extracting a motility signature corresponding to the one or more bacteria. The method further comprises merging the morphology signature and the motility signature into a merged vector signature and classifying the one or more bacteria based on the merged vector signature.

Described herein are systems and methods for determining dryness of produce using image data. A method can include receiving, by a computing system and from an imaging device, image data of a batch of produce, performing, by the computing system, object detection to identify each produce in a frame of the image data, extracting, by the computing system, temperature values in pixels of the identified produce in the frame, and determining, by the computing system, distribution characteristics of the extracted temperature values. The method can also include predicting, by the computing system, a dryness metric for the batch of produce based on applying a trained model to the determined distribution characteristics. The model can be trained using temperature distributions of other produce, the temperature distributions being annotated based on previous mappings of skewness of the temperature distributions to dryness.