A method of generating a time-lapse video includes: identifying an image storage mode; obtaining a first image; based on identifying that the image storage mode is an emphasis mode for emphasizing one or more images, obtaining a first time difference between the first image and a stored image, and a first feature value indicating a first amount of change between the first image and the stored image; for each respective image of a first plurality of images of a first image group stored in a memory, identifying a second image from among the first plurality of images, based on a second time difference and a second feature value; generating a second image group by removing the second image from the first image group and adding the first image to the first image group; and generating the time-lapse video by using a second plurality of images of the second image group.

A method of generating a time-lapse video includes: identifying an image storage mode; obtaining a first image; based on identifying that the image storage mode is an emphasis mode for emphasizing one or more images, obtaining a first time difference between the first image and a stored image, and a first feature value indicating a first amount of change between the first image and the stored image; for each respective image of a first plurality of images of a first image group stored in a memory, identifying a second image from among the first plurality of images, based on a second time difference and a second feature value; generating a second image group by removing the second image from the first image group and adding the first image to the first image group; and generating the time-lapse video by using a second plurality of images of the second image group.

A method and a system for generating a dynamic addictive neural circuit based on weakly supervised contrastive learning are disclosed. The method includes: based on a convolutional neural network, reducing a dimensionality of voxels of multiple groups of fMRI to attributes of brain region nodes, and generating multiple groups of dynamic brain connection maps containing time series based on the attributes of the brain region nodes; extracting spatio-temporal features of brain connections in the dynamic brain connection maps; inputting the spatio-temporal features into an abnormal connection detection network, calculating an abnormal probability of brain connections based on contrastive learning, and obtaining the brain connection with a highest abnormal probability at each time point; and generating the dynamic addictive neural circuit based on neuroscientific prior knowledge and the brain connection with the greatest probability of abnormality.

A method and a system for generating a dynamic addictive neural circuit based on weakly supervised contrastive learning are disclosed. The method includes: based on a convolutional neural network, reducing a dimensionality of voxels of multiple groups of fMRI to attributes of brain region nodes, and generating multiple groups of dynamic brain connection maps containing time series based on the attributes of the brain region nodes; extracting spatio-temporal features of brain connections in the dynamic brain connection maps; inputting the spatio-temporal features into an abnormal connection detection network, calculating an abnormal probability of brain connections based on contrastive learning, and obtaining the brain connection with a highest abnormal probability at each time point; and generating the dynamic addictive neural circuit based on neuroscientific prior knowledge and the brain connection with the greatest probability of abnormality.

Systems and methods described herein utilize synthetic pixel generation using a custom neural network to generate synthetic versions of objects hidden by occlusions for effective detection and tracking. A computing device stores an object detector model and a synthetic image generator model; receives a video feed; detects objects of interest in a current frame of the video feed; identifies an occluded object in the current frame; retrieves a previous frame from the video feed; generates synthetic data based on the previous frame for the occluded object; and forwards a modified version of the current frame to an object tracking system, wherein the modified version of the current frame includes the synthetic data.

A system and method that automatically resolves conflicts among sensor information in a sensor fusion robot system. Such methods can accommodate converging ambiguous and divergent sensor information in a manner that can allow continued, and relatively accurate, robotic operations. The processes can include handling sensor conflict via sensor prioritization, including, but not limited, prioritization based on the particular stage or segment of the assembly operation when the conflict occurs, overriding sensor data that exceeds a threshold value, and/or prioritization based on evaluations of recent sensor performance, predictions, system configuration, and/or historical information. The processes can include responding to sensor conflicts through comparisons of the accuracy of workpiece location predictions from different sensors during different assembly stages in connection with arriving at a determination of which sensor(s) is providing accurate and reliable predictions.

An editing device acquires a first image in which an occupant of a vehicle has been imaged in association with a time point in a time series and a second image in which scenery around the vehicle has been imaged in association with a time point in a time series, acquires first index information indicating feelings of the occupant when the first image has been captured on the basis of the first image, and extracts the first image and the second image from first images of the time series and second images of the time series on the basis of the first index information and the time point associated with the first image based on the first index information to generate a library including the extracted images.

A device can comprise a memory and a processor operatively coupled to the memory and comprising computer executable components, comprising a trajectory determination component that determines a trajectory of an adjacent-lane traveling vehicle traveling in a lane adjacent to a vehicle comprising the device, wherein visibility of the adjacent-lane traveling vehicle, from the vehicle, is impaired by a succeeding vehicle traveling between the adjacent-lane traveling vehicle and the vehicle, a collision avoidance component that, in response to the trajectory of the adjacent-lane traveling vehicle being determined, by the trajectory determination component, to prevent a safe lane change by the vehicle to the lane, initiates a collision avoidance action for the vehicle.

The methods and systems herein enable relative movement-based seatbelt use detection. Image data of an occupant of a vehicle is received over time. The image data is then input into a machine-learned model or other module that determines whether relative movement between one or more portions of the occupant and corresponding portions of a seatbelt are less than a threshold amount. If the relative movement is less than the threshold amount, an indication of seatbelt misuse (e.g., a fake seatbelt) is output to a vehicle component. By basing the indication of seatbelt misuse on relative movement between the occupant and the seatbelt, seatbelt use detection may be improved.

Systems, methods, apparatuses, and computer program products for contactless image-based blood oxygen estimation. A method may include receiving an image or video of a part of a subject captured by a camera of a computing device. The method may also include extracting a region of interest of the part of the subject from the image or video. The method may further include performing feature extraction of the region of interest. In addition, the method may include estimating a blood oxygen saturation level of the subject based on a spatial and temporal data analysis of more than two color channels. Feature extraction and estimation of the blood oxygen saturation level may include implementing a combination of spatial averaging, color channel mixing, and temporal trend analysis.