| 摘要 |
<p>Robust landmarks having one or more detectable properties in an image that are invariant with respect to scale or tilt, and methods for detecting such marks. In one example, a robust mark has one or more unique detectable properties in an image, such as a cardinal property, an ordinal property, and/or an inclusive property, that does not change as a function of the size of the mark as it appears in the image, and/or an orientation (rotation) and position (translation) of the mark with respect to a camera obtaining the image. In another example, a robust mark has one or more invariant characteristics that are relatively simple to detect in an image, that are unlikely to occur by chance in a given scene, and that are relatively unaffected by arbitrary image content. These properties facilitate automatic identification of the mark under a wide variety of imaging conditions. Exemplary detection methods include cumulative phase rotation analysis, regions analysis, and intersecting edges analysis of signals generated by scanning an image containing one or more robust marks in a succession of scanning paths. In one example, such scanning paths are essentially closed paths.</p> |
