Automotive Technologies International, Inc.

Tie-Qi Chen

David S Breed

Wendell C Johnson

Wilbur E DuVall

Ray Piirainen

Jeffrey L Morin

Kunhong Xu

Michael E Kussul

Andrew J Varga

Henk Helleman

Method for controlling output of a classification algorithm which classifies an occupant of a seat in a vehicle in which a bladder or other type of weight sensor is arranged in a bottom cushion of the seat, data relating to the pressure exerted by the occupant on the bottom cushion is obtained from the weight sensor, the occupant is initially classified, a current classification is output using data from the weight sensor, the occupant is periodically re-classified using data from the weight sensor, and a classification change is allowed only upon obtaining evidence of a new classification which is greater than evidence of the current classification. The classification change may be enabled by determining a substantially consecutive period of time when the re-classification is unchanged and different from the current classification, and enabling the classification change upon when the consecutive period of time is greater than a threshold.

Method for controlling output of a classification algorithm

Arrangement and method for obtaining information about objects in an environment in or around a vehicle includes one or more optical imagers for obtaining images of the environment and a processor coupled to the imager(s) for obtaining information about an object in one or more images obtained by the imager(s). The processor is arranged to process the obtained images to determine edges of objects in the images and input data about the edges into a trained pattern recognition algorithm which has been trained to provide information about the object as output. The pattern recognition algorithm may include a neural network or variation thereof. The information about the object may be used to control a vehicular component such as an airbag or light filter.

Image processing for vehicular applications applying edge detection technique

Vehicle including a compartment receivable of an object and a system for tracking the object includes at least one imaging device each arranged to receive an image of a portion of the compartment containing the object and a control unit coupled to each imaging device and which controls the imaging device to obtain a first set of images without the object and at least one second image including the object. The control unit analyzes the second image(s) in consideration of the first set of images to derive information about the object. This information may be the type, size and/or position of the object or a part thereof. The information may be used to control vehicular components which have a variable use based on the type, size or position of the object or part thereof.

Image processing for vehicular applications applying image comparisons

Optical classification method for classifying an occupant in a vehicle by acquiring images of the occupant from a single camera and analyzing the images acquired from the single camera to determine a classification of the occupant. The single camera may be a digital CMOS camera, a high-power near-infrared LED, and the LED control circuit. It is possible to detect brightness of the images and control illumination of an LED in conjunction with the acquisition of images by the single camera. The illumination of the LED may be periodic to enable a comparison of resulting images with the LED on and the LED off so as to determine whether a daytime condition or a nighttime condition is present. The position of the occupant can be monitored when the occupant is classified as a child, an adult or a forward-facing child restraint.

Occupant sensing system

Method for controlling output of a classification algorithm which classifies an occupant of a seat including initially classifying the occupant and outputting the classification, subsequently periodically classifying the occupant and enabling a change in the classification of the occupant only upon obtaining evidence of a new classification which is greater than evidence of the current classification. The initial classification of the occupant may be conducted based on satisfaction of a condition such as the detection of closure of a door by, e.g., a sensor such as a door closure sensor, the detection of an empty seat by, e.g., an occupant presence sensor, weight sensor, electric field sensor, wave sensor, camera and the like, the detection of the switching on of the vehicle ignition by an appropriate sensor, motion or the absence of motion of the vehicle.

Method for controlling an occupant protection device in a vehicle in which data is acquired from at least one sensor relating to an occupant in a seat to be protected by the occupant protection device, the type of occupant is classified based on the acquired data and when the occupant is classified as an empty seat or a rear-facing child seat, deployment of the occupant protection device is disabled or adjusted. Otherwise, the size of the occupant is classified based on the acquired data, the position of the occupant is determined by one of a plurality of algorithms selected based on the classified size of the occupant using the acquired data, each algorithm being applicable for a specific size of occupant. Deployment of the occupant protection device is disabled or adjusted when the determined position of the occupant is more likely to result in injury to the occupant if the occupant protection device were to deploy. The algorithms may be pattern recognition algorithms such as neural networks.

System for determining the occupancy state of a seat in a vehicle and controlling a component based thereon

Method for developing and adapting a system for determining the location of an object in a passenger compartment of a vehicle using a variety of transducers and pattern recognition technologies and techniques that applies to any combination of transducers that provide information about vehicle occupancy. These include weight sensors, capacitive sensors, inductive sensors, ultrasonic, optic, infrared, radar among others. The adaptation process begins with a selection of candidate transducers for a particular vehicle model based on, e.g., cost, vehicle interior passenger compartment geometry, desired accuracy and reliability, vehicle aesthetics, vehicle manufacturer preferences. Once a candidate set of transducers is selected, these transducers are mounted in the test vehicle and the vehicle is subjected to an extensive data collection process wherein various objects are placed in the vehicle at various locations and various databases are collected. A pattern recognition system is developed using the acquired data and an accuracy assessment is made. Further studies are made to determine which if any of the transducers can be eliminated from the design. The design process usually begins with a surplus of sensors plus an objective as to how many sensors are to be in the final vehicle installation. The adaptation process can determine the degree of importance of the transducers and the least important could be eliminated to reduce system cost and complexity. Various data collection techniques are utilized such as collecting data under the influence of thermal gradients and the use of neural networks to insure data quality. Other techniques used include the use of pre-processors, post-processors, modular networks, large databases and multiple databases.

Growing community of inventors

Windsor, CA, United States of America

Tie-Qi Chen