Systems, methods, tangible non-transitory computer-readable media, and devices associated with motion flow estimation are provided. For example, scene data including representations of an environment over a first set of time intervals can be accessed. Extracted visual cues can be generated based on the representations and machine-learned feature extraction models. At least one of the machine-learned feature extraction models can be configured to generate a portion of the extracted visual cues based on a first set of the representations of the environment from a first perspective and a second set of the representations of the environment from a second perspective. The extracted visual cues can be encoded using energy functions. Three-dimensional motion estimates of object instances at time intervals subsequent to the first set of time intervals can be determined based on the energy functions and machine-learned inference models.

A speed estimation system includes: a detection module configured to determine bounding boxes of an object moving on a surface in images, respectively, captured using a camera; a solver module configured to, based on the bounding boxes, determine a homography of the surface by solving an optimization problem, where the solver module is not trained; and a speed module configured to, using the homography, determine a speed that the object is moving on the surface.

A speed estimation system includes: a detection module configured to determine bounding boxes of an object moving on a surface in images, respectively, captured using a camera; a solver module configured to, based on the bounding boxes, determine a homography of the surface by solving an optimization problem, where the solver module is not trained; and a speed module configured to, using the homography, determine a speed that the object is moving on the surface.

A method for detecting the angular position of a cap with respect to a bottle is provided. A first image of a cap provided with a first marker and of at least a portion of the bottle with which the cap is associated and which is provided with a second marker is captured. Liquid drops and other possible impurities existing thereon are removed from and/or displaced relative to the cap and bottle portion. A second image of the cap and bottle portion is then captured. The first image and second image are compared to obtain at least one processing which is free from “noise” and interferences due to the liquid drops and on which the positions of the first and second markers can be determined without errors. The relative angular position of the first and second markers are determined. An apparatus suitable to implement the aforesaid method is also provided.

A method for detecting the angular position of a cap with respect to a bottle is provided. A first image of a cap provided with a first marker and of at least a portion of the bottle with which the cap is associated and which is provided with a second marker is captured. Liquid drops and other possible impurities existing thereon are removed from and/or displaced relative to the cap and bottle portion. A second image of the cap and bottle portion is then captured. The first image and second image are compared to obtain at least one processing which is free from “noise” and interferences due to the liquid drops and on which the positions of the first and second markers can be determined without errors. The relative angular position of the first and second markers are determined. An apparatus suitable to implement the aforesaid method is also provided.

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.

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.

Multi-color flash with image post-processing that uses a camera device with a multi-color flash and implements post-processing to generate images is described. In one aspect, the multi-color flash with image post-processing may be implemented by a controller configured to control a camera and flashes of at least two different colors. The controller may be configured to cause the camera to acquire a first image of a scene while the scene is being illuminated with the first flash but not the second flash, then cause the camera to acquire a second image of the scene while the scene is being illuminated with the second flash but not the first flash, and generate a final image of the scene in post-processing based on a combination of the first image and the second image.

Multi-color flash with image post-processing that uses a camera device with a multi-color flash and implements post-processing to generate images is described. In one aspect, the multi-color flash with image post-processing may be implemented by a controller configured to control a camera and flashes of at least two different colors. The controller may be configured to cause the camera to acquire a first image of a scene while the scene is being illuminated with the first flash but not the second flash, then cause the camera to acquire a second image of the scene while the scene is being illuminated with the second flash but not the first flash, and generate a final image of the scene in post-processing based on a combination of the first image and the second image.

A tracking device includes full-spherical cameras arranged on the right and left. The tracking device pastes a left full-spherical camera image captured with the full-spherical camera on a spherical object, and is installed with a virtual camera inside the spherical object. The virtual camera may freely rotate in a virtual image capturing space formed inside the spherical object, and acquire an external left camera image. Similarly, the tracking device is also installed with a virtual camera that acquires a right camera image, and forms a convergence stereo camera by means of the virtual cameras. The tracking device tracks a location of a subject by means of a particle filter by using the convergence stereo camera formed in this way. In a second embodiment, the full-spherical cameras are vertically arranged and the virtual cameras are vertically installed.