Occupant labeling for airbag-related applications
First Claim
1. An occupant labeling system for identifying the upper torso of the occupant, comprising:
- a k-metric module, including an upper torso metric and a lower torso metric, wherein said k-metric module provides for generating said upper torso metric and said lower torso metric; and
a parameter estimator, including an upper torso parameter and a lower torso parameter, wherein said parameter estimator provides for generating said upper torso parameter and said lower torso parameter from said upper torso metric and said lower torso metric.
1 Assignment
0 Petitions
Accused Products
Abstract
An invention is disclosed to divide a segmented image of an occupant into an upper torso image and a lower torso image. An occupant labeling heuristic can identify each pixel within the segmented image as an upper torso pixel or a lower torso pixel. A k-means module can provide an initial pixel classification by comparing the distance between the particular pixel and an estimated midpoint on the upper torso with the distance between the particular pixel and an estimated midpoint on the lower torso. The iterative parameters estimator can update the mean values for the upper torso and lower torso by performing a conditional likelihood heuristic. Pixels can then be classified as either upper or lower torso pixels by comparing a Mahalonobis distance for each torso. Airbag-related applications can then use the upper torso image to generate occupant characteristics relevant to airbag-related applications.
-
Citations
25 Claims
-
1. An occupant labeling system for identifying the upper torso of the occupant, comprising:
-
a k-metric module, including an upper torso metric and a lower torso metric, wherein said k-metric module provides for generating said upper torso metric and said lower torso metric; and
a parameter estimator, including an upper torso parameter and a lower torso parameter, wherein said parameter estimator provides for generating said upper torso parameter and said lower torso parameter from said upper torso metric and said lower torso metric. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13)
-
-
14. An occupant labeling system for identifying the upper torso of the occupant, comprising:
-
a k-means module, including a segmented image, an initial guess, an upper torso mean, and a lower torso mean, wherein said k-means module provides for generating said upper torso mean and said lower torso mean with said segmented image and said initial guess;
an iterative parameter estimator, including an upper torso parameter, a lower torso parameter, and a Mahalanobis distance, wherein said iterative parameter estimator provides for generating said upper torso parameter and said lower torso parameter with said Mahalanobis distance, said upper torso mean, and said lower torso mean; and
a pixel classifier, including an upper torso image, wherein said pixel classifer generates said upper torso image from said upper torso parameter and said lower torso parameter. - View Dependent Claims (15, 16, 17)
-
-
18. An occupant tracking and airbag deployment system comprising:
-
an image segmenter, including an ambient image and a segmented image, wherein said image segmenter generates said segmented image from said ambient image;
an image classifier, including an occupant type classification, wherein said image classifier generates said occupant type classification from said segmented image; and
an occupant labeler, including an upper torso image and a occupant labeling heuristic, wherein said occupant labeler generates said upper torso image from said segmented image, said occupant labeling heuristic, and said occupant type classification. - View Dependent Claims (19, 20)
-
-
21. A method for identifying the upper torso of an occupant from a segmented image of occupant pixels, comprising:
-
determining the distance of a pixel to an estimated midpoint on the upper torso;
updating the estimated midpoint of the upper torso; and
selectively identifying an upper torso pixel with the updated estimated midpoint. - View Dependent Claims (22, 23, 24, 25)
-
Specification