Data processing: vehicles – navigation – and relative location – Vehicle control – guidance – operation – or indication
Reexamination Certificate
2002-09-13
2004-02-03
Marc-Coleman, Marthe Y. (Department: 3661)
Data processing: vehicles, navigation, and relative location
Vehicle control, guidance, operation, or indication
C701S301000, C348S116000, C342S070000
Reexamination Certificate
active
06687577
ABSTRACT:
BACKGROUND OF INVENTION
The present invention relates generally to external object recognition for vehicles, pedestrians, and other items and more particularly to an obstacle classification system for use in moving vehicles.
Due to the current density of traffic on the roads, motor vehicle operators are flooded with information. Consequently, operating a motor vehicle is a complex procedure in which various situations arise where the operator has limited, little, or no time to react or to manually engage safety measures.
Many crash detection systems incorporate crash detection algorithms based on sensed data. The application of remote sensing systems using radar, lidar, and vision based technologies for obstacle detection, tracking, alarm processing, and potential safety countermeasure deployment is well known in the art.
To perform pre-crash sensing, vehicle sensors should not only detect possible threats but classify them as well. Such classifications are often broken down into different target categories, such as: vehicle, wall, pole, and pedestrian.
For situations involving the target vehicle category, it is also useful to determine the direction and angle of the target vehicle and its type, e.g., frontal view of a car, side view of an SUV, and rear view of a large truck, for proper collision avoidance and safety measure engagement.
Current classification techniques match the image of the target obstacle to a database template. This is useful only if the obstacle (or something very close to the obstacle) appears in the template.
The limitations associated with current obstacle classification techniques have made it apparent that a new technique for obstacle and classification is needed. This new method should include a set of classifying parameters for a number of objects and should operate for various discrepancies within the individual classifications.
SUMMARY OF INVENTION
In accordance with one aspect of the present invention, an obstacle classifying system for a host vehicle having at least one sensor, adapted to detect at least boundary data of an obstacle, coupled to the host vehicle, is disclosed. The sensor is further adapted to generate an obstacle signal.
A controller, also coupled to the host vehicle, is adapted to receive the obstacle signal and generate a bounding box for the obstacle in response to the obstacle signal. The controller also includes classifying logic.
The bounding box includes at least one vertical pixel, corresponding to a maximum height of the obstacle, and at least one horizontal pixel, corresponding to a maximum width of the obstacle.
The host vehicle classifying logic is adapted to activate in response to the height and width of the obstacle within obstacle parameters and to classify a type of obstacle based on obstacle height and the obstacle width.
In accordance with another aspect of the present invention, an obstacle classifying method for a host vehicle comprising: detecting an obstacle through at least one sensor coupled to the host vehicle; generating an obstacle signal; receiving said obstacle signal in a controller coupled to the host vehicle; generating a bounding box around an image of said obstacle in response to said obstacle signal, said bounding box including a number of vertical pixels corresponding to a height of said obstacle and a number of horizontal pixels corresponding to a width of said obstacle; activating vehicle classifying logic in response to said height and said width of said obstacle within vehicle parameters; classifying a type of a target vehicle based on said obstacle height; estimating a rotation angle of said target vehicle in relation to the host vehicle; activating said other object classifying logic in response to said height and said width of said obstacle within other object parameters; and classifying said obstacle based on at least one of said obstacle height and said obstacle width.
Additional objects and features of the present invention will become apparent upon review of the drawings and accompanying detailed description of the preferred embodiments.
REFERENCES:
patent: 5253050 (1993-10-01), Karasudani
patent: 5410346 (1995-04-01), Saneyoshi et al.
patent: 6018308 (2000-01-01), Shirai
Artz & Artz P.C.
Ford Global Technologies LLC
MacKenzie Frank A.
Marc-Coleman Marthe Y.
LandOfFree
Simple classification scheme for vehicle/pole/pedestrian... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Simple classification scheme for vehicle/pole/pedestrian..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Simple classification scheme for vehicle/pole/pedestrian... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3343854