Hybrid depth estimation system
A hybrid depth estimation system includes a switchable projector that controllably projects either dot light or surface light onto an object; a sensor that receives reflected dot light or reflected surface light from the object to capture a first image or a second image respectively; a dot time-of-flight (ToF) depth generator that generates a dot depth map and an associated dot confidence map according to the first image; a surface ToF depth generator that generates a surface depth map according to the second image; and a denoise processor that processes the surface depth map according to a plurality of points on the dot depth map with high confidence, thereby generating a denoised depth map.
1. A hybrid depth estimation system, comprising:
a switchable projector that controllably projects either dot light or surface light onto an object;
a sensor that receives reflected dot light or reflected surface light from the object to capture a first image or a second image respectively;
a dot time-of-flight (ToF) depth generator that generates a dot depth map and an associated dot confidence map according to the first image;
a surface ToF depth generator that generates a surface depth map according to the second image; and
a denoise processor that processes the surface depth map according to a plurality of points on the dot depth map with high confidence, thereby generating a denoised depth map.
2. The system of claim 1 , wherein the switchable projector comprises a dot-diffuser projector.
3. The system of claim 1 , further comprising:
a mode detector that generates a mode signal controlling the switchable projector.
4. The system of claim 1 , wherein the switchable projector is a single light source, and the sensor is a single capture device.
5. The system of claim 1 , further comprising:
a buffer that temporarily stores the surface depth map.
6. A hybrid depth estimation system, comprising:
a switchable projector that controllably projects either dot light or surface light onto an object;
a sensor that receives reflected dot light or reflected surface light from the object to capture a first image or a second image respectively;
a dot time-of-flight (ToF) depth generator that generates a dot depth map and an associated dot confidence map according to the first image;
a surface ToF depth generator that generates a surface depth map according to the second image;
a denoise processor that processes the surface depth map according to a plurality of points on the dot depth map with high confidence, thereby generating a denoised depth map and an associated denoised confidence map;
a structured-light (SL) depth decoder that generates an SL depth map according to the dot confidence map;
an edge detector that generates an edge map according to the denoised confidence map; and
a fusion processor that processes the SL depth map, the dot depth map and the surface depth map according to the dot confidence map and the edge map, thereby generating an enhanced depth map.
7. The system of claim 6 , wherein the fusion processor performs fusion operation on depths located on edges detected by the edge detector.
8. The system of claim 6 , wherein the fusion processor performs fusion operation according to distance of the object.
9. The system of claim 8 , wherein the SL depth map has higher weighting when the object is near the sensor, and the surface depth map has higher weighting when the object is far from the sensor.
10. The system of claim 6 , wherein the switchable projector comprises a dot-diffuser projector.
11. The system of claim 6 , further comprising:
a mode detector that generates a mode signal controlling the switchable projector.
12. The system of claim 6 , wherein the switchable projector is a single light source, and the sensor is a single capture device.
13. The system of claim 6 , further comprising:
a buffer that temporarily stores the surface depth map.