초록 ▼

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 th

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.

대표청구항 ▼

The invention claimed is: 1. An arrangement for obtaining information about objects in an exterior environment around a vehicle, comprising: at least one optical imager that obtains images of the environment; and a processor coupled to said at least one imager and that obtains information about an

The invention claimed is: 1. An arrangement for obtaining information about objects in an exterior environment around a vehicle, comprising: at least one optical imager that obtains images of the environment; and a processor coupled to said at least one imager and that obtains information about an object in one or more images obtained by said at least one imager, said processor being 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 that has been trained to provide information about the object as output, wherein the pattern recognition algorithm is trained by: arranging a known object in a field of view of said at least one optical imager, obtaining images of the object, applying an edge detection algorithm to the obtained images to obtain data about the edges of the object in the images and associating the data with information about the object; then changing the position of the object, obtaining additional images, applying an edge detection algorithm to the additional images to obtain data about the edges of the object in the additional images and associating the data with the information about the object; then changing the object to another known object, obtaining images of the new object, applying an edge detection algorithm to the new images to obtain data about the edges of the new object in the images and associating the data with information about the new object; then changing the position of the new object, obtaining additional images, applying an edge detection algorithm to the images to obtain data about the edges of the new object in the additional images and associating the data with the information about the new object; then repeating the process of changing the object or its position until sets of data about objects in images is obtained; and inputting the data to a pattern recognition algorithm training program to obtain the trained pattern recognition algorithm which will receive data about edges of unknown objects in images and provide as output, information about the objects. 2. The arrangement of claim 1, wherein said pattern recognition algorithm is a neural network. 3. The arrangement of claim 1, wherein said processor includes an edge detection algorithm that receives the obtained images and outputs a vector containing the location of edges of the object. 4. The arrangement of claim 1, wherein said processor includes an edge detection algorithm that receives the obtained images and outputs a vector containing the location of edges of the object and their orientation. 5. The arrangement of claim 1, wherein each of said at least one imager is a CCD array or a CMOS array. 6. The arrangement of claim 1, wherein said pattern recognition algorithm is trained to provide as output, a classification, identification and/or location of an object. 7. A vehicle, comprising: the arrangement of claim 1; and at least one component having a variable condition, state or position depending on the presence of objects in the exterior environment around the vehicle, said processor being arranged to control said at least one component based on the information about the object obtained as output from said pattern recognition algorithm. 8. The vehicle of claim 7, wherein said at least one component comprises an airbag arranged to deploy prior to or during a crash involving the vehicle. 9. The arrangement of claim 1, further comprising an illumination source that illuminates the environment with infrared illumination, said at least one optical imager being arranged to obtain images of the environment upon illumination by said illumination source. 10. The arrangement of claim 1, further comprising an illumination source that illuminates the environment with eye-safe infrared illumination, said at least one optical imager being arranged to obtain images of the environment upon illumination by said illumination source. 11. The arrangement of claim 1, wherein said pattern recognition algorithm is trained in a training stage prior to installation in a particular vehicle, to provide as output, a classification, identification and/or location of an object. 12. A method for obtaining information about objects in an exterior environment around a vehicle, comprising: in a training stage, training a pattern recognition algorithm to provide information about objects in the environment upon receiving as input information about edges of unknown objects; installing the pattern recognition algorithm in a processor on the vehicle; arranging at least one imager on the vehicle to obtain images of the environment around the vehicle; operatively obtaining images of the environment by means of the at least one optical imager; deriving, using a processor, data about edges of objects in the obtained images; and providing the data to the pattern recognition algorithm in the processor to receive as output, information about the object; wherein the step of training the pattern recognition algorithm comprises: arranging a known object in a field of view of the at least one optical imager, obtaining images of the object, applying an edge detection algorithm to the obtained images to obtain data about the edges of the object in the images and associating the data with information about the object; then changing the position of the object, obtaining additional images, applying an edge detection algorithm to the additional images to obtain data about the edges of the object in the additional images and associating the data with the information about the object; then changing the object to another known object, obtaining images of the new object, applying an edge detection algorithm to the new images to obtain data about the edges of the new object in the images and associating the data with information about the new object; then changing the position of the new object, obtaining additional images, applying an edge detection algorithm to the images to obtain data about the edges of the new object in the additional images and associating the data with the information about the new object; then repeating the process of changing the object or its position until sets of data about objects in images is obtained; and inputting the data to a pattern recognition algorithm training program to obtain the trained pattern recognition algorithm which will receive data about edges of unknown objects in images and provide as output, information about the objects. 13. The method of claim 12, wherein the pattern recognition algorithm is a neural network. 14. The method of claim 12, wherein the step of deriving data about edges of objects in the obtained images comprising inputting the obtained images into an edge detection algorithm which outputs a vector containing the location of edges of the object, the vector being the data provided to the pattern recognition algorithm. 15. The method of claim 12, wherein the at least one optical imager comprises a CCD array or a CMOS array. 16. The method of claim 12, wherein the pattern recognition algorithm is trained to provide as output, a classification, identification and/or location of an object. 17. A method for controlling at least one component having a variable condition, state or position depending on the presence of objects in the exterior environment around the vehicle, the method comprising: obtaining information in accordance with the method of claim 12; and controlling the at least one component based on the information about the object obtained as output from the pattern recognition algorithm. 18. The method of claim 17, wherein the at least one component comprises an airbag arranged to deploy prior to or during a crash involving the vehicle. 19. The method of claim 12, further comprising arranging an illumination source on the vehicle to illuminate the environment with infrared illumination, the at least one imager being arranged to obtain images of the environment around the vehicle when illuminated by infrared illumination from the illumination source. 20. The method of claim 12, further comprising arranging an illumination source on the vehicle to illuminate the environment with eye-safe infrared illumination, the at least one imager being arranged to obtain images of the environment around the vehicle when illuminated by eye-safe infrared illumination from the illumination source. 21. A vehicle including an arrangement for obtaining information about objects in an exterior environment around a vehicle and controlling vehicular components based thereon, comprising: at least one optical imager positioned to obtain images of the environment; a processor coupled to said at least one imager and derives information about an object in one or more images obtained by said at least one imager, said processor being 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 that has been trained to provide information about the object as output via association of known information about previously obtained images and correlation of currently obtained images to the previously obtained images; and at least one component having a variable condition, state or position depending on the presence of objects in the exterior environment around the vehicle, said processor being arranged to control said at least one component based on the information about the object obtained as output from said pattern recognition algorithm, said at least one component comprising an airbag arranged to deploy prior to or during a crash involving the vehicle, wherein the pattern recognition algorithm is trained by: arranging a known object in a field of view of said at least one optical imager, obtaining images of the object, applying an edge detection algorithm to the obtained images to obtain data about the edges of the object in the images and associating the data with information about the object; then changing the position of the object, obtaining additional images, applying an edge detection algorithm to the additional images to obtain data about the edges of the object in the additional images and associating the data with the information about the object; then changing the object to another known object, obtaining images of the new object, applying an edge detection algorithm to the new images to obtain data about the edges of the new object in the images and associating the data with information about the new object; then changing the position of the new object, obtaining additional images, applying an edge detection algorithm to the images to obtain data about the edges of the new object in the additional images and associating the data with the information about the new object; then repeating the process of changing the object or its position until sets of data about objects in images is obtained; and inputting the data to a pattern recognition algorithm training program to obtain the trained pattern recognition algorithm which will receive data about edges of unknown objects in images and provide as output, information about the objects. 22. A method for obtaining information about objects in an exterior environment around a vehicle and controlling vehicular components based thereon, each component having a variable condition, state or position depending on the presence of objects in the exterior environment around the vehicle, comprising: in a training stage, training a pattern recognition algorithm to provide information about objects in the environment upon receiving as input information about edges of unknown objects; installing the pattern recognition algorithm in a processor on the vehicle; arranging at least one imager on the vehicle to obtain images of the environment around the vehicle; operatively obtaining images of the environment by means of the at least one optical imager; deriving, using a processor, data about edges of objects in the obtained images; providing the data to the pattern recognition algorithm in the processor to receive as output via association of known information about previously obtained images and correlation of currently obtained images to the previously obtained images, information about the object; and controlling each component based on the information about the object obtained as output from the pattern recognition algorithm, one of the components being an airbag arranged to deploy prior to or during a crash involving the vehicle, wherein the step of training the pattern recognition algorithm comprises: arranging a known object in a field of view of the at least one optical imager, obtaining images of the object, applying an edge detection algorithm to the obtained images to obtain data about the edges of the object in the images and associating the data with information about the object; then changing the position of the object, obtaining additional images, applying an edge detection algorithm to the additional images to obtain data about the edges of the object in the additional images and associating the data with the information about the object; then changing the object to another known object, obtaining images of the new object, applying an edge detection algorithm to the new images to obtain data about the edges of the new object in the images and associating the data with information about the new object; then changing the position of the new object, obtaining additional images, applying an edge detection algorithm to the images to obtain data about the edges of the new object in the additional images and associating the data with the information about the new object; then repeating the process of changing the object or its position until sets of data about objects in images is obtained; and inputting the data to a pattern recognition algorithm training program to obtain the trained pattern recognition algorithm which will receive data about edges of unknown objects in images and provide as output, information about the objects.