Windshield localization for occupancy detection

摘要

A system and method to capture an image of an oncoming target vehicle and localize the windshield of the target vehicle. Upon capturing an image, it is then analyzed to detect certain features of the target vehicle. Based on geometrical relationships of the detected features, the area of the image containing the windshield of the vehicle can then be identified and localized for downstream processing.

主权项

1. A system configured to perform feature-based image analysis for localization of a windshield within an image comprising:
an image capture device operably connected to a data processing device and a target trigger device, wherein said image capture device captures an image upon receiving notification from said target trigger device; and a processor-usable medium embodying computer code, said processor-usable medium being coupled to said data processing device, said computer program code comprising instructions executable by said processor and configured for: identifying at least one object of interest on a target vehicle within said image that is not a windshield; locating said at least one object of interest within said image; and identifying a windshield of said target vehicle within said image based on a location of said at least one object of interest and a relative geometric relationship between said identified at least one object of interest and said windshield by conversion of physical dimensions to pixel dimensions within said image utilizing one of:l′≈(a⁢⁢cos⁢⁢θ+b⁢⁢sin⁢⁢θ)⁢⁢c′c,⁢andl′≈fH(⁢a⁢⁢cos2⁢θ+b⁢⁢sin⁢⁢θ⁢⁢cos⁢⁢θ)sd,  where l′ represents a vertical distance in image pixels between the headlights and the windshield in said captured image c′ represents the distance in image pixels between two headlights in said captured image, a represents a real-world distance from a headlight to the forward most edge of a hood of said vehicle, b represents a real-world distance from the forward most edge of the hood to the bottom of the windshield, c represents a real-world distance between the two headlights, f represents the focal length of the image capture device, H represents a horizontal number of pixels of the image capture device, s represents the horizontal physical dimension of the image capture sensor, θ represents the elevation look down angle from the camera to the hood of the vehicle, and d represents the real-world horizontal distance from the location of the image capture device to the front of the target vehicle.