Depth measurement

1. A method comprising the steps of:

obtaining at least a first frame and a second frame of image data, wherein the first frame of image data is captured at a first image sensor having a first focus configuration with a first focal length characteristic, and the second frame of image data is captured at a second image sensor having a second focus configuration with a second, different, focal length characteristic, the first frame of image data and second frame of image data being captured at a given time;

determining a first distance of a first object in the first frame of image data captured at the given time, based on the first focus configuration and a sharpness characteristic of the first object wherein the sharpness characteristic of the first object exceeds a predetermined threshold;

determining a second distance of a second, different, object in the second frame of image data captured at the given time, based on the second focus configuration and a sharpness characteristic of the second, different, object, wherein the sharpness characteristic of the second different, object exceeds the predetermined threshold;

estimating a distance of one or more further objects in the first frame of image data and the second frame of image data captured at the given time, based on a difference between the sharpness characteristic of the first object in the first frame of image data captured at the given time, the sharpness characteristic of the second, different, object in the second frame of image data captured at the given time, and a sharpness characteristic of each of the further objects in the first frame of image data captured at the given time, and the second frame of image data captured at the given time;

generating normalized depth information associated with the first distance of the first object, the second distance of the second, different, object, and the estimated distance of the one or more further objects; and

generating a depth map based on the normalized depth information associated with the first distance of the first object, the second distance of the second, different, object, and the estimated distance of the one or more further objects,

wherein at least one of the first image sensor, or second image sensor comprises an autofocusing focus configuration, and the autofocussing focus configuration is used to determine an area of focus within a given frame of image data, and for identifying the first object or the second, different, object within the scene, based on the area of focus.

2. The method of claim 1 , wherein the depth information is obtained from at least one of a mono-depth convolutional neural network, a time-of-flight sensor, stereo-imaging triangulation, and structured light.

3. The method of claim 1 , further comprising determining the sharpness characteristic of at least one of the first object in the first frame of image data, or the second, different, object in the second frame of image data, the determining comprising applying at least one of a Fast Fourier Transform, and a Laplace operator to the image data, or determining a point of highest contrast in the first frame of image data or the second frame of image data.

4. The method of claim 1 , wherein determining the determined distance comprises combining at least the sharpness characteristic with a depth estimator.

5. A processor comprising:

an input module for obtaining at least a first frame and a second frame of image data, wherein the first frame of image data is captured at a first image sensor having a first focus configuration with a first focal length characteristic, and the second frame of image data is captured at a second image sensor having a second focus configuration with a second, different, focal length characteristic, the first frame of image data and second frame of image data being captured at a given time;

a determination module for determining:

a first distance of first object in the first frame of image data captured at the given time, based on the first focus configuration and a sharpness characteristic of the first object in the first frame; and

a second distance of a second, different, object in the second frame of image data captured at the given time, based on the second focus configuration and a sharpness characteristic of the second, different, object in the second frame;

an analysis module for analysing the first frame of image data captured at the given time and the second frame of image data captured at the given time to determine whether the sharpness characteristic of the first object in the first frame and the sharpness characteristic of the second, different, object in the second frame exceed a predetermined threshold;

an estimation module for estimating a distance of one or more further objects in the first frame of image data and second frame of image data captured at the given time, based on a difference between the sharpness characteristic of the first object in the first frame of image data captured at the given time, the sharpness characteristic of the second, different, object in the second frame of image data captured at the given time, and a sharpness characteristic of each of the further objects in the first frame of image data captured at the given time, and the second frame of image data captured at the given time;

a normalization module for normalizing depth information associated with the first distance of the at least one object, the second distance of the second, different, object, and the estimated distance of the one or more further objects; and

a generation module for generating a depth map based on the normalized depth information associated with the first distance of the first object, the second distance of the second, different, object, and the estimated distance of the one or more further objects,

wherein at least one of the first image sensor, or second image sensor comprises an autofocusing focus configuration, and the autofocussing focus configuration is used to determine an area of focus within a given frame of image data, and for identifying the first or the second, different, object within the scene, based on the area of focus.

6. A system comprising:

at least a first image sensor having a first focus configuration with a first focal length characteristic, for directing light to the first image sensor, the first image sensor being configured for obtaining a first frame of image data captured at a given time, and a second image sensor having a second focus configuration with a second, different, focal length characteristic for directing light to the second image sensor, the second image sensor being configured for obtaining a second frame of image data captured at the given time; and

a processor arranged to receive the first frame of image data captured at the given time obtained by the first image sensor and the second frame of image data captured at the given time obtained by the second image sensor, the processor comprising:

an input module for obtaining the first frame of image data and second frame of image data, the first frame of image data and second frame of image data being captured, at the given time;

a determination module for determining:

a first distance of a first object in the first frame of image data captured at the given time, based on the first focus configuration and a sharpness characteristic of the first object in the first frame; and

a second distance of the second, different, object in the second frame of image data captured at the given time, based on the second focus configuration and a sharpness characteristic of the second, different, object in the second frame;

an analysis module for analysing the first frame of image data captured at the given time and the second frame of image data captured at the given time to determine whether the sharpness characteristic of the first object in the first frame and the sharpness characteristic of the second, different, object in the second frame object exceed a predetermined threshold;

an estimation module for estimating a distance of one or more further objects in the first frame of image data and second frame of image data captured at the given time, based on a difference between the sharpness characteristic of the first object in the first frame of image data captured at the given time, the sharpness characteristic of the second, different, object in the second frame of image data captured at the give time, and a sharpness characteristic of each of the further objects in the first frame of image data captured at the given time, and the second frame of image data captured at the give time;

a normalization module for normalizing depth information associated with the first distance of the at least one object, the second distance of the second, different, object, and the estimated distance of the one or more further objects; and

a generation module for generating a depth map based on the normalized depth information associated with the first distance of the first object, the second distance of the second, different, object and the estimated distance of the one or more further objects,

wherein at least one of the first image sensor, or second image sensor comprises an autofocusing focus configuration, and the autofocussing focus configuration is used to determine an area of focus within a given frame of image data, and for identifying the first or the second, different, object within the scene, based on the area of focus.

7. The system of claim 6 , wherein the at least one focus configuration further comprises any of:

an aperture characteristic; and

a lens property.

8. The system of claim 6 , wherein the processor is at least one of a central processing unit; an image signal processor, a graphics processing unit, or a neural processing unit.