| 摘要 |
A method for processing video images having the steps of generating video images (103) with a multi-spectral video source (102) and converting analog color data contained in the generated video images (103) to digital color data for subsequent signal processing. The method further includes the steps of extracting the digital color data from designated areas of the generated video images and utilizing the extracted digital color data for identifying a color distinguishable from a background color. Thus, the invention provides a method for processing generated video images which has an intrinsic immunity to the effects of shadows by exploiting multi-spectral color information to distinguish, for example, a passing vehicle from the roadway 116. In a preferred embodiment, a video image processor (100) is employed having a multi-spectral video source (102) for generating the video images. A color digitizer (104) is employed for converting the analog color data contained in the generated video images to the digital color data for the subsequent signal processing. Then, a digital signal processor (106) is employed to extract the digital color data from the designated areas of the generated video images. Finally, a central processing unit (108) utilizes the extracted digital color data to identify a color distinguishable from the background color. <IMAGE> |
