A list of images is received. The images were captured by a sensor of an ADV chronologically while driving through a driving environment. A first image of the images is identified that includes a first object in a first dimension (e.g., larger size) detected by an object detector using an object detection algorithm. In response to the detection of the first object, the images in the list are traversed backwardly in time from the first image to identify a second image that includes a second object in a second dimension (e.g., smaller size) based on a moving trail of the ADV represented by the list of images. The second object is then labeled or annotated in the second image equivalent to the first object in the first image. The list of images having the labeled second image can be utilized for subsequent object detection during autonomous driving.

A list of images is received. The images were captured by a sensor of an ADV chronologically while driving through a driving environment. A first image of the images is identified that includes a first object in a first dimension (e.g., larger size) detected by an object detector using an object detection algorithm. In response to the detection of the first object, the images in the list are traversed backwardly in time from the first image to identify a second image that includes a second object in a second dimension (e.g., smaller size) based on a moving trail of the ADV represented by the list of images. The second object is then labeled or annotated in the second image equivalent to the first object in the first image. The list of images having the labeled second image can be utilized for subsequent object detection during autonomous driving.

This invention relates to a method for training a neural network, comprising detecting a hole in each training image of a plurality of training images; transforming each training image into a transformed image, to suppress non-crack information in the training image; and training a neural network using the transformed images, to detect cracks in images (i.e. in objects in images).

Unlike state of art eye blink detection techniques that are generalized for usage across individuals affecting accuracy of eye blink prediction from subject to subject, embodiments of the present disclosure provide a method and system for personalized eye blink detection using passive camera-based approach. The method first generates a subject specific annotation data, which is then further processed to derive subject specific personalized blink threshold values. The method disclosed provides three unique approaches to compute the personalized blink threshold values which is one time calibration process. The personalized blink threshold values are then used to generate a binary decision vector (D) while analyzing input test images (video sequences) of the subject of interest. Further, values taken by elements of the decision vector (D) are analyzed for a predefined time period to predict possible eye blinks of the subject.

Techniques are disclosed for generating a sequence of symbols based on input data for a neuro-linguistic model. The model may be used by a behavior recognition system to analyze the input data. A mapper component of a neuro-linguistic module in the behavior recognition system receives one or more normalized vectors generated from the input data. The mapper component generates one or more clusters based on a statistical distribution of the normalized vectors. The mapper component evaluates statistics and identifies statistically relevant clusters. The mapper component assigns a distinct symbol to each of the identified clusters.

Techniques are disclosed for generating a sequence of symbols based on input data for a neuro-linguistic model. The model may be used by a behavior recognition system to analyze the input data. A mapper component of a neuro-linguistic module in the behavior recognition system receives one or more normalized vectors generated from the input data. The mapper component generates one or more clusters based on a statistical distribution of the normalized vectors. The mapper component evaluates statistics and identifies statistically relevant clusters. The mapper component assigns a distinct symbol to each of the identified clusters.

A method for finding at least one trigger for human intervention in a control of a vehicle, the method may include receiving, from a plurality of vehicles, and by an I/O module of a computerized system, visual information acquired during situations that are suspected as situations that require human intervention in the control of at least one of the plurality of vehicles; determining, based at least on the visual information, the at least one trigger for human intervention; and transmitting to one or more of the plurality of vehicles, the at least one trigger.

A method for finding at least one trigger for human intervention in a control of a vehicle, the method may include receiving, from a plurality of vehicles, and by an I/O module of a computerized system, visual information acquired during situations that are suspected as situations that require human intervention in the control of at least one of the plurality of vehicles; determining, based at least on the visual information, the at least one trigger for human intervention; and transmitting to one or more of the plurality of vehicles, the at least one trigger.

An artificial intelligence based method and apparatus for processing information. A specific embodiment of the method includes: acquiring search click information recorded within a predetermined time period; generating a candidate entry set by selecting, from the search click information, entries having click volumes exceeding a click volume threshold within a preset unit time period; forming, for each candidate entry in the candidate entry set, a click volume sequence according to a chronological order of each of the click volumes corresponding to the candidate entry in the predetermined time period; determining, based on click volume sequences, categories of the candidate entries respectively corresponding to click volume sequences; and determining candidate entries having the categories being a preset category as points of interest to generate a set of points of interest.

Systems, methods and techniques for training and applying machine learning models to predict whether or not one or more individuals will suffer a fall event. In certain embodiments, a machine learning model can include both a static component and a dynamic component, where each component is associated with different types of medical data. In certain embodiments, an adjustment factor based on fall history of individuals is applied to the output of the machine learning model to generate a final score predictive of a fall event. In certain embodiments, the machine learning model is both trained and applied to medical data associated with predetermined forms, and where the predetermined forms include a value range associated with a medical condition.