Delphi Technologies, Inc.

Hongzhi Kong

Qin Sun

David L Eiche

Victor M Nieto

Adil Ansari

Jeffrey H Burns

Jianhua Li

Stephen J Kiselewich

William A Bauson

John R Bailey

Kambiz Panahi

The present invention relates to systems for determining the position and the type of an occupant in a vehicle. More specifically, the present invention provides an occupant position and type classification system including an occupant detection module, a processor in communication with the occupant detection module, and memory accessible by the processor and storing program instructions executable by the processor to perform the steps of categorizing the occupant into one of a plurality of static categories, each of the static categories including at least one class indicative of the occupant's type or position in the vehicle, and classifying the occupant into one of the classes.

Confidence boost for automotive occupant classifications

A method of exposure control for an imaging system. A predetermined number of images are captured by one or more imagers, wherein the images are defined by an image resolution matrix. The images are masked to establish a region of interest within the image resolution matrix and brightness of the images is analyzed within the region of interest. An exposure time is calculated for a subsequent image capturing step based on the brightness analysis, and an exposure time setting of the imager(s) is adjusted during the subsequent image capturing step based on the calculated exposure time.

Method of exposure control for an imaging system

A vehicle restraint system has a vision-based occupant classification system for control of airbag deployment during a crash scenario. The classification system utilizes two imaging sensors which together create a stream of paired images received and stored by an occupant classification controller. A computer program product of the controller utilizes the paired images to extract disparity/range features and stereo-vision differential edge density features. Moreover, the controller extracts wavelet features from one of the two paired images. All three features or maps are classified amongst preferably seven classifications by algorithms of the computer program product producing class confidence data fed to a sensor fusion engine of the controller for processing and output of an airbag control signal input into a restraint controller of the vehicle restraint system.

Vision-based occupant classification method and system for controlling airbag deployment in a vehicle restraint system

A method of classifying vehicle occupants utilizes a neural network engine having a state machine for determining if an occupant has changed preferably between an adult and adult, an adult and child, and a child and child from a pair of images. If no change has occurred, the method utilizes the prior occupant type and then decides if the occupant has changed in position. If no, the occupant is deemed static and the prior type is valid as a classification or output to preferably a vehicle restraint system. If the occupant has changed in position, a dynamic classification process is initiated by either an adult or a child dynamic classifier as dictated by the state machine. Valid dynamic classifier outputs or classifications can be sent to the restraint system and invalid dynamic classifier outputs are sent to a static classifier for update of the occupant type.

Method of classifying vehicle occupants

A vision-based occupant classification method utilizes a static classification routine for achieving highly accurate occupant classification, a dynamic detection routine for quickly responding to changes in occupant position, and a category state change routine for detecting potential changes in occupant category. The static classification routine determines an initial classification of the occupant, after which the dynamic detection routine monitors for changes in occupant position and the category state change routine monitors for a potential change in occupant category. If category state change routine detects a potential change in occupant category, the static classification routine is re-executed to re-classify the occupant. The category state change routine identifies a composite optical flow vector associated with occupant movement, and detects a potential change in occupant category when the composite flow vector crosses one or more pre-defined entry/exit motion gates.

Method of operation for a vision-based occupant classification system

An automotive occupant position restraint apparatus senses a position of an occupant of a motor vehicle. The apparatus includes an optical energy source emitting a first beam of optical energy. A first optical arrangement is disposed in a path of the first beam of optical energy. The first optical arrangement expands the first beam of optical energy into a plurality of second beams of optical energy spanning across a first angle. A second optical arrangement is disposed in a path of the second beams of optical energy. The second optical arrangement expands the second beams of optical energy into a plurality of third beams of optical energy spanning across a second angle larger than the first angle. An optical energy receiver receives optical energy from the third beams, wherein the received optical energy has been reflected within a passenger compartment of the motor vehicle.

Apparatus for fanning out near infrared radiation in an automotive occupant position restraint system

An object surface characterization system with adaptive lighting control includes a light projector, a light source, a camera, a processor and a memory subsystem. The processor is coupled to the light projector, the light source and the camera, as well as the memory subsystem. The memory subsystem stores code that, when executed by the processor, instructs the processor to perform a number of steps to achieve adaptive lighting control for the system.

Adaptive lighting control for vision-based occupant sensing

A technique for identifying beam images of a beam matrix includes a number of steps. Initially, a plurality of light beams of a beam matrix, which are arranged in rows and columns, are received after reflection from a surface of a target. Next, a reference light beam is located in the beam matrix. Then, a row pivot beam is located in the beam matrix based on the reference beam. Next, remaining reference row beams of a reference row that includes the row pivot beam and the reference beam are located. Then, a column pivot beam in the beam matrix is located based on the reference beam. Next, remaining reference column beams of a reference column that includes the column pivot beam and the reference beam are located. Finally, remaining ones of the light beams in the beam matrix are located.

Identification and labeling of beam images of a structured beam matrix

Electromagnetic radiation is directed from an optical grating in a regular array of beams in rows and columns toward a target object surface; and the reflected beams are focused through a lens to form beam images on an image plane of a single camera. Each of the beam images has a position on the image plane that moves substantially linearly with variation of a target distance between the optical grating and a point on the object surface from which that beam image is reflected; and the direction of the substantially linear movement of each beam image forms a predetermined angle with the column of the array of beam images on the image plane to which that beam belongs at a common target distance. Positional data for each of the beam images on the image plane is derived and provided to a processor which uses stored reference data defining predetermined beam paths in the image plane for the beam images to locate and determine the associated one of the predetermined beam paths for each of the beam images on the image plane, determine the location of each of the beam images along its associated predetermined beam path, determine the target distance for that beam and store an array of the determined target distances for each of the located beam images to characterize the object surface. The predetermined angle may provide for each beam having a separate predetermined beam path. For greater resolution, some of the beam paths may have two associated beams, and processing is provided to distinguish the beams on a single beam path uniquely.

Growing community of inventors

Kokomo, IN, United States of America

Hongzhi Kong