Shape from focus
Shape from focus or shape from defocus is a method of 3D reconstruction which consists of the use of information about the focus of an optical system to provide a means of measurement for 3D information.[1] One of the simplest forms of this method can be found in most autofocus cameras today. In its most simple form, the methods analyze an image based upon overall contrast from a histogram, the width of edges, or more commonly, the frequency spectrum derived from a fast Fourier transform of the image. That information might be used to drive a servo mechanism in the lens, focusing it until the quantity measured on one of the earlier parameters is optimized.
References
- ^ Favaro, Paolo, and Stefano Soatto. "A geometric approach to shape from defocus." IEEE Transactions on Pattern Analysis and Machine Intelligence 27.3 (2005): 406-417.
- v
- t
- e
Computer vision
- Datasets
- Digital geometry
- Commercial systems
- Feature detection
- Geometry
- Image sensor technology
- Learning
- Morphology
- Motion analysis
- Noise reduction techniques
- Recognition and categorization
- Research infrastructure
- Researchers
- Segmentation
- Software
- Computer stereo vision
- Motion capture
- Object recognition
- 3D object recognition
3D reconstruction |
|
---|
- 3D pose estimation
- Activity recognition
- Audio-visual speech recognition
- Automatic image annotation
- Automatic number-plate recognition
- Automated species identification
- Augmented reality
- Bioimage informatics
- Blob detection
- Computer-aided diagnosis
- Content-based image retrieval
- Eye tracking
- Face recognition
- Foreground detection
- Gesture recognition
- Image denoising
- Image restoration
- Landmark detection
- Medical image computing
- Object detection
- Optical character recognition
- Pose tracking
- Remote sensing
- Robotic mapping
- Autonomous vehicles
- Video content analysis
- Video motion analysis
- Video surveillance
- Video tracking
Main category