A system tracks human head and facial features over time by analyzing a sequence of images. The system provides descriptions of motion of both head and facial features between two image frames. These descriptions of motion are further analyzed by the system to recognize facial movement and expression. The system analyzes motion between two images using parameterized models of image motion. Initially, a first image in a sequence of images is segmented into a face region and a plurality of facial feature regions. A planar model is used to recover motion parameters that estimate motion between the segmented face region in the first image and a second image in the sequence of images. The second image is warped or shifted back towards the first image using the estimated motion parameters of the planar model, in order to model the facial features relative to the first image. An affine model and an affine model with curvature are used to recover motion parameters that estimate the image motion between the segmented facial feature regions and the warped second image. The recovered motion parameters of the facial feature regions represent the relative motions of the facial features between the first image and the warped image. The face region in the second image is tracked using the recovered motion parameters of the face region. The facial feature regions in the second image are tracked using both the recovered motion parameters for the face region and the motion parameters for the facial feature regions. The parameters describing the motion of the face and facial features are filtered to derive mid-level predicates that define facial gestures occurring between the two images. These mid-level predicates are evaluated over time to determine facial expression and gestures occurring in the image sequence.

Apparatus and method for recognizing facial expressions and facial gestures in a sequence of images

A gesture-enabled electronic communication system informs users of gestures made by other users participating in a communication session. The system captures a three-dimensional movement of a first user from among the multiple users participating in an electronic communication session, wherein the three-dimensional movement is determined using at least one image capture device aimed at the first user. The system identifies a three-dimensional object properties stream using the captured movement and then identifies a particular electronic communication gesture representing the three-dimensional object properties stream by comparing the identified three-dimensional object properties stream with multiple electronic communication gesture definitions. In response to identifying the particular electronic communication gesture from among the multiple electronic communication gesture definitions, the system transmits, to the users participating in the electronic communication session, an electronic object corresponding to the identified electronic communication gesture.

Informing a user of gestures made by others out of the user's line of sight

System and method for controlling operation of a vehicle or a component thereof based on recognition of a individual including a processor embodying a pattern recognition algorithm trained to identify whether a person is the individual by analyzing data derived from optical images and an optical receiving unit for receiving images including the person and deriving data from the images. The optical receiving unit provides the data to the algorithm to obtain an indication from the algorithm whether the person is the individual. A security system enables operation of the vehicle when the algorithm provides an indication that the person is an individual authorized to operate the vehicle and prevents operation of the vehicle when the algorithm does not provide an indication that the person is an individual authorized to operate the vehicle. A component adjustment system adjusts the component based on the recognition of the individual.

Vehicular component control systems and methods

Vehicular monitoring arrangement for monitoring an environment of the vehicle including at least one active pixel camera for obtaining images of the environment of the vehicle and a processor coupled to the active pixel camera(s) for determining at least one characteristic of an object in the environment based on the images obtained by the active pixel camera(s). The active pixel camera can be arranged in a headliner, roof or ceiling of the vehicle to obtain images of an interior environment of the vehicle, in an A-pillar or B-pillar of the vehicle to obtain images of an interior environment of the vehicle, or in a roof, ceiling, B-pillar or C-pillar of the vehicle to obtain images of an interior environment of the vehicle behind a front seat of the vehicle. The determined characteristic can be used to enable optimal control of a reactive component, system or subsystem coupled to the processor. When the reactive component is an airbag assembly including at least one airbag, the processor can be designed to control at least one deployment parameter of the airbag(s).

Vehicular monitoring systems using image processing

A computer-implemented method, system, and program product comprises a gesture processing system for capturing a three-dimensional movement of a user, wherein the three-dimensional movement is determined using at least one stereoscopic image device aimed at the user to identify and track at least one particular three-dimensional movement of the user. The gesture processing system predicts at least one defined movement within the captured three-dimensional movement matching at least one gesture definition of at least one gesture type from among a plurality of gesture definitions. A resource control system receives a request to access a resource based on the predicted at least one gesture type. The resource control system only allows user access to the resource by matching the predicted at least one gesture type with at least one required gesture type.

Controlling resource access based on user gesturing in a 3d captured image stream of the user

A moving object detecting system includes an image acquiring section, a feature extracting section, a background detecting section, a prediction parameter calculating section, a region estimating section, and a moving object determining section. The image acquiring section has a mobile imaging system and acquires image frames sequentially obtained upon movement of the imaging system. The feature extracting section extracts features of the acquired image frames. The background feature detecting section detects a background feature from the features. The prediction parameter calculating section obtains prediction parameters for predicting a motion of the background region upon movement of the imaging system in accordance with a positional relationship between the correlated background features. The region estimating section estimates a region where features detected from image frames obtained by the mobile imaging system may have been present in an image frame of the immediately preceding frame by using the prediction parameters. The moving object determining section determines whether a feature corresponding to the given feature is present in the estimation region, thereby checking the presence/absence of the moving object.

Moving object detecting system

PURPOSE:To simply precisely and quickly judge a moving object by judging whether the characteristics in an image hourly obtained in a moving photographing system exist in a moving range estimated in the image obtained in the movement of the photographing system. CONSTITUTION:A photographing position is being moved, for instance, a region of a large space differential value is extracted 2 as characteristic points, and the characteristic points of a background part detected from the information of the respective characteristic points are mutually controlled among a plurality of images. Next parameters for predicting the movement of a background part region which moves in input image in the movement of the image input part 1 are estimated 4, the presence region of the respective characteristic points in the image obtained before one timing from the position in the image of this parameter and characteristic points is predicted and estimated 5, and further searching 6 is performed whether the characteristic points corresponding to the predicted presence region before one timing exist or not. And, when the characteristic points corresponding to it cannot be found, its number and an approach point are checked to detect 7 at moving object information newly appeared in the input image.

Watanabe Mutsumi

Papers

Moving object detecting system

Moving object detector

System zur Auffindung eines beweglichen Objekts