Abstract: A system configured to receive video and/or images from an image capture device over a livestock path, generate feature maps from an image of the video by applying at least a first convolutional neural network, slide a window across the feature maps to obtain a plurality of anchor shapes, determine if each anchor shape contains an object to generate a plurality of regions of interest, each of the plurality of regions of interest being a non-rectangular, polygonal shape, extract feature maps from each region of interest, classify objects in each region of interest, in parallel with classification, predict segmentation masks on at least a subset of the regions of interest in a pixel-to-pixel manner, identify individual animals within the objects based on classifications and the segmentation masks, and count individual animals based on identification, and provide the count to a digital device for display, processing, and/or reporting.

Abstract: A method comprising receiving, from a first infrared image capture device, three images including gas equipment including a first image captured at a first time period, a second image captured at a second time period, and a third image captured at a third time period, the three images capturing an infrared spectrum, interpreting one of the three images in a red color channel of an RGB image where pixels are red-tonal in coloring, interpreting an other of the three images in a green color channel of the RGB image where pixels are green-tonal in coloring, interpreting a remaining of the three images in a blue color channel of the RGB image where pixels are blue-tonal in coloring, and providing the RGB image for display, the RGB image indicating movement as at least one color that is different from color of at least some of the gas equipment.

Abstract: A method comprising receiving, from a infrared image capture device, an image including a fluid storage tank storing a fluid, the image including an image intensity associated with a temperature of the fluid storage tank with an internal surface that is in contact with the fluid and an image intensity associated with a temperature of the first fluid storage tank with an internal surface that is not in contact with the fluid, generating feature maps, sliding a window to obtain a plurality of anchor shapes using a region proposal network, determining if each anchor shape contains an object to generate a plurality of regions of interest, extracting feature maps from each region of interest, classifying objects in each region of interest, identifying stored fluid using the objects, determining volume of stored fluid based on the stored fluid, and providing the volume to a digital device for display.

Abstract: An example method includes receiving a set of first images. For each first image in a subset of the set of first images, multiple inputs to multiple artificial intelligence model systems are generated, the multiple inputs and the first image are provided to the multiple artificial intelligence model systems, multiple responses from the multiple artificial intelligence model systems are received, based on the multiple responses, a label for the first image is determined, and the first image and the label are added to a model training data set. A computer vision model is trained based on the model training data set. A second image is received, the computer vision model is applied to the second image, and an output from the computer vision model is received.

Abstract: A method comprising receiving, from a first infrared image capture device, three images including gas equipment including a first image captured at a first time period, a second image captured at a second time period, and a third image captured at a third time period, the three images capturing an infrared spectrum, interpreting one of the three images in a red color channel of an RGB image where pixels are red-tonal in coloring, interpreting an other of the three images in a green color channel of the RGB image where pixels are green-tonal in coloring, interpreting a remaining of the three images in a blue color channel of the RGB image where pixels are blue-tonal in coloring, and providing the RGB image for display, the RGB image indicating movement as at least one color that is different from color of at least some of the gas equipment.

Abstract: A system configured to receive video and/or images from an image capture device over a livestock path, generate feature maps from an image of the video by applying at least a first convolutional neural network, slide a window across the feature maps to obtain a plurality of anchor shapes, determine if each anchor shape contains an object to generate a plurality of regions of interest, each of the plurality of regions of interest being a non-rectangular, polygonal shape, extract feature maps from each region of interest, classify objects in each region of interest, in parallel with classification, predict segmentation masks on at least a subset of the regions of interest in a pixel-to-pixel manner, identify individual animals within the objects based on classifications and the segmentation masks, and count individual animals based on identification, and provide the count to a digital device for display, processing, and/or reporting.