Detection of object edges in images containing cast shadows
Detecting object boundaries in the presence of cast shadows is a difficult task for machine vision systems. A new edge detector is presented which responds to shadow penumbras and abrupt object edges with distinguishable signals. The detector requires the use of spatially extended light sources and sufficient video resolution to resolve the shadow penumbras of interest. Detection of high frequency noise is suppressed without requiring image-dependent adjustment of signal thresholds. The ability of the edge operator to distinguish shadow penumbras from abrupt object boundaries while suppressing responses to high frequency noise and texture is illustrated with idealized shadow and object edge intensity profiles. Selective detection of object boundaries in a video scene with a cast shadow is also demonstrated. 18 refs.
- Research Organization:
- Sandia National Labs., Albuquerque, NM (United States)
- Sponsoring Organization:
- DOE; USDOE, Washington, DC (United States)
- DOE Contract Number:
- AC04-76DP00789
- OSTI ID:
- 5125322
- Report Number(s):
- SAND-92-0830C; CONF-920795--2; ON: DE92016092
- Country of Publication:
- United States
- Language:
- English
Similar Records
LDRD final report on enhanced edge detection techniques for manufacturing quality control and materials characterization
Distinguishing cast shadow boundaries from abrupt object boundaries via edge detection