Data processing: vehicles – navigation – and relative location – Relative location – Collision avoidance
Reexamination Certificate
2003-07-30
2004-12-21
Beaulieu, Yonel (Department: 3661)
Data processing: vehicles, navigation, and relative location
Relative location
Collision avoidance
C342S070000, C340S903000
Reexamination Certificate
active
06834232
ABSTRACT:
BACKGROUND OF INVENTION
The present invention relates to collision warning and countermeasure systems for an automotive vehicle, and more particularly to a system and method of performing object detection and association using multiple similar and dissimilar sensors.
Collision warning and countermeasure systems are becoming more widely used. Collision warning systems preferably are able to detect an object approximately 50 m-100 m from a host vehicle and assess whether the object detected is an obstacle and poses a threat to the host vehicle. These systems also preferably provide a vehicle operator knowledge and awareness of obstacles or vehicles within a close proximity in time such that the operator may perform actions to prevent colliding with the detected obstacles. Countermeasure systems exist in various passive and active forms. Some countermeasure systems are used to aid in prevention of a collision others are used to aid in the prevention of injury to a vehicle operator.
Certain collision warning systems and countermeasure systems are able to sense a vehicle or object in a close proximity to a host vehicle and warn a host vehicle operator, such that the operator can take precautionary steps to prevent a collision or injury. The collision warning systems maybe forward or rearward sensing. These systems indicate to a vehicle operator that an object, that may not be visible to the vehicle operator, is within a stated distance and location relative to the host vehicle. The vehicle operator may than respond accordingly. Other collision warning systems and countermeasure systems activate passive countermeasures such as air bags, load limiting seat belts, or active vehicle control including steering control, accelerator control, or brake control whereby the system itself aids in preventing a collision or injury.
Separate from collision warning systems and countermeasure systems other systems exist for autonomously controlling a vehicle. These systems may include sensors, such as cameras, radar sensors, or ultrasonic sensors to gather information and utilize this information when activating steering control, brake control, and accelerator control. Autonomous type systems have primarily been used for military applications but have not been used for either providing collision warning or injury prevention in automotive vehicles.
In threat estimation, detection, and identification of an object in a host vehicle's path, multiple sensors of various types have been used. The sensors have been used to detect an object followed by use of parametric association/estimation techniques to confirm when an object is a potential threat to the host vehicle and to host vehicle occupants. The object of concern may be a real object or a false object. False objects may be detected for example, when there is a stationary roadside object that is foreseen as a true potentially collision causing object or when a small object, that is not a potential threat, is in the path of the host vehicle and is identified and misclassified as a potentially collision-causing object. Another example of false object generation is when a ghost object is falsely generated by the collision warning and countermeasure system that in actuality does not exist, as known in the art.
The collision warning and countermeasure systems collect data from multiple sensors and associate, fuse, or combine the data to determine whether detected objects are real objects rather than false objects. Advantages of utilizing data from multiple sensors includes extended spatial and temporal coverage, increased accuracy in determining whether an object is a potential threat, and increased reliability in detection of objects in a close proximity of the host vehicle, thereby, providing a better assessment of the vehicle's surroundings.
Choice of architecture for processing object information, being cost effective, and being able to provide relevant information quick enough so that appropriate action can be performed is critical in determining whether a particular technology is feasible for use. There is a current desire to use cameras in detecting and classifying objects. Unfortunately, current camera technology is not cost effective and requires a large amount of processing power and time to compute relevant information required for in-vehicle use. For example, image processing from a charge coupled device (CCD) camera is time consuming due to a large amount of data collected for each image, approximately 640×480 pixels per frame at 30 frames per second. Time is critical in prevention of a collision. To accurately classify and track an object can require acquisition of tens to hundreds of frames of data each of which having a minimum desired resolution, thus, rendering current camera technology for in-vehicle use infeasible.
A desire exists to provide a safer automotive vehicle with increased collision warning and safety countermeasure intelligence as to decrease the probability of a collision or of an injury. It is therefore desirable to provide an improved collision warning and safety countermeasure system for an automotive vehicle that incorporates use of multiple sensor technologies and provides a more efficient collision and injury prevention system for an automotive vehicle.
SUMMARY OF INVENTION
The present invention provides a system and method of detecting objects within close proximity of an automotive vehicle using both object detection and image generation technologies such as electro-magnetics and electro-optical technologies, respectively. A method of performing object detection within a collision warning and countermeasure system is provided. The method includes capturing & generating an object detection signal and generating an image detection signal. Centers-of-reflection and centers-of-intensity are determined in response to the object detection signal and the image detection signal. The centers-of-intensity are associated with the centers-of-reflection for a plurality of frames. Differences between the centers-of-reflection and the centers-of-intensity are determined for each frame and a sensor difference signal is generated. An object is classified in response to the sensor difference signal.
One of several advantages of the present invention is that it provides a collision warning and countermeasure system that minimizes image processing time, processor requirements, memory requirements, & complexity, thus providing a cost effective and feasible solution for in-vehicle use of existing camera technology.
Another advantage of the present invention is that it provides a method of associating data collected from both electro-magnetic and electro-optical sensors, such as radar sensors and cameras, as to better and more efficiently classify and track objects.
Furthermore the present invention continuously adjusts a region-of-interest and corresponding center-of-intensity for each image frame to provide better certainty of an object and improved tracking capability.
The present invention itself, together with attendant advantages, will be best understood by reference to the following detailed description, taken in conjunction with the accompanying figures.
REFERENCES:
patent: 5386285 (1995-01-01), Asayama
patent: 5479173 (1995-12-01), Yoshioka et al.
patent: 5587929 (1996-12-01), League et al.
patent: 5617085 (1997-04-01), Tsutsumi et al.
patent: 5805103 (1998-09-01), Doi et al.
patent: 6134497 (2000-10-01), Hayashi et al.
patent: 6191704 (2001-02-01), Takenaga et al.
patent: 6292752 (2001-09-01), Franke et al.
patent: 2002/0005778 (2002-01-01), Breed et al.
patent: 2002/0044048 (2002-04-01), Watanabe et al.
patent: 2002/0057195 (2002-05-01), Yamamura
Beaulieu Yonel
Ford Global Technologies LLC
MacKenzie Frank A.
LandOfFree
Dual disimilar sensing object detection and targeting system does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Dual disimilar sensing object detection and targeting system, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Dual disimilar sensing object detection and targeting system will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3285463