Abstract: An apparatus is provided for automated object tracking in a video feed. The apparatus receives and sequentially processes a plurality of frames of the video feed to track objects. In particular, a plurality of objects in a frame are detected and assigned to a respective track fragment. A kinematic, visual, temporal or machine learning-based feature of an object is then identified and stored in metadata associated with the track fragment. A track fragment for the object is identified in earlier frames based on a comparison of the feature and a corresponding feature in metadata associated with the earlier frames. The track fragments for the object in the frame and the object in the earlier frames are linked to form a track of the object. The apparatus then outputs the video feed with the track of the object as an overlay thereon.

Abstract: A set of 3D user-designed images is used to create a high volume of realistic scenes or images which can be used for training and testing deep learning machines. The system creates a high volume of scenes having a wide variety of environmental, weather-related factors as well as scenes that take into account camera noise, distortion, angle of view, and the like. A generative modeling process is used to vary objects contained in an image so that more images, each one distinct, can be used to train the deep learning model without the inefficiencies of creating videos of actual, real life scenes. Object label data is known by virtue of a designer selecting an object from an image database and placing it in the scene. This and other methods care used to artificially create new scenes that do not have to be recorded in real-life conditions and that do not require costly and time-consuming, manual labelling or tagging of objects.

Abstract: A system for process control of a composite fabrication process comprises an automated composite placement head, a vision system, and a computer system. The automated composite placement head is configured to lay down composite material. The vision system is connected to the automated composite placement head and configured to produce image data during an inspection of the composite material, wherein the inspection takes place at least one of during or after laying down the composite material. The computer system is configured to identify inconsistencies in the composite material visible within the image data, and make a number of metrology decisions based on the inconsistencies.

Abstract: A set of 3D user-designed images is used to create a high volume of realistic scenes or images which can be used for training and testing deep learning machines. The system creates a high volume of scenes having a wide variety of environmental, weather-related factors as well as scenes that take into account camera noise, distortion, angle of view, and the like. A generative modeling process is used to vary objects contained in an image so that more images, each one distinct, can be used to train the deep learning model without the inefficiencies of creating videos of actual, real life scenes. Object label data is known by virtue of a designer selecting an object from an image database and placing it in the scene. This and other methods care used to artificially create new scenes that do not have to be recorded in real-life conditions and that do not require costly and time-consuming, manual labelling or tagging of objects.

Abstract: An apparatus is provided for automated object and activity tracking in a live video feed. The apparatus receives and processes a live video feed to identify a plurality of objects and activities therein. The apparatus also generates natural language text that describes a storyline of the live video feed using the plurality of objects and activities so identified. The live video feed is processed using computer vision, natural language processing and machine learning, and a catalog of identifiable objects and activities. The apparatus then outputs the natural language text audibly or visually with a display of the live video feed.

Abstract: A method of testing a battery includes causing a battery in a test environment to produce a fire having a flame that extends out from the battery, and capturing a digital image of a scene that includes at least a portion of a test environment and the flame, the digital image being formed using visible light. The method includes uploading the digital image to a computer configured to produce a quiver plot and identify points on the quiver plot that define a polygon that is an approximate outline of the flame. The computer is configured to determine dimensions of the polygon, and translate the dimensions from the quiver plot to the digital image, and from the digital image to dimensions of the flame in the scene. And the computer is configured to generate a displayable report that includes at least the dimensions of the flame.

Abstract: A method of testing a battery includes causing a battery in a test environment to produce a fire having a flame that extends out from the battery, and capturing a digital image of a scene that includes at least a portion of a test environment and the flame, the digital image being formed using visible light. The method includes uploading the digital image to a computer configured to produce a quiver plot and identify points on the quiver plot that define a polygon that is an approximate outline of the flame. The computer is configured to determine dimensions of the polygon, and translate the dimensions from the quiver plot to the digital image, and from the digital image to dimensions of the flame in the scene. And the computer is configured to generate a displayable report that includes at least the dimensions of the flame.

Abstract: A set of 3D user-designed images is used to create a high volume of realistic scenes or images which can be used for training and testing deep learning machines. The system creates a high volume of scenes having a wide variety of environmental, weather-related factors as well as scenes that take into account camera noise, distortion, angle of view, and the like. A generative modeling process is used to vary objects contained in an image so that more images, each one distinct, can be used to train the deep learning model without the inefficiencies of creating videos of actual, real life scenes. Object label data is known by virtue of a designer selecting an object from an image database and placing it in the scene. This and other methods care used to artificially create new scenes that do not have to be recorded in real-life conditions and that do not require costly and time-consuming, manual labelling or tagging of objects.

Abstract: A system for process control of a composite fabrication process comprises an automated composite placement head, a vision system, and a computer system. The automated composite placement head is configured to lay down composite material. The vision system is connected to the automated composite placement head and configured to produce image data during an inspection of the composite material, wherein the inspection takes place at least one of during or after laying down the composite material. The computer system is configured to identify inconsistencies in the composite material visible within the image data, and make a number of metrology decisions based on the inconsistencies.

Abstract: An apparatus is provided for automated object tracking in a video feed. The apparatus receives and sequentially processes a plurality of frames of the video feed to track objects. In particular, a plurality of objects in a frame are detected and assigned to a respective track fragment. A kinematic, visual, temporal or machine learning-based feature of an object is then identified and stored in metadata associated with the track fragment. A track fragment for the object is identified in earlier frames based on a comparison of the feature and a corresponding feature in metadata associated with the earlier frames. The track fragments for the object in the frame and the object in the earlier frames are linked to form a track of the object. The apparatus then outputs the video feed with the track of the object as an overlay thereon.

Abstract: An apparatus is provided for automated object and activity tracking in a live video feed. The apparatus receives and processes a live video feed to identify a plurality of objects and activities therein. The apparatus also generates natural language text that describes a storyline of the live video feed using the plurality of objects and activities so identified. The live video feed is processed using computer vision, natural language processing and machine learning, and a catalog of identifiable objects and activities. The apparatus then outputs the natural language text audibly or visually with a display of the live video feed.