Optimal data sampling for image analysis

1. A method comprising:

receiving, from an image capture device, image data comprising at least one image with a first image resolution; and

reducing an amount of storage space utilized for storing the image data by:

estimating accuracy of an analysis on the image data;

determining an optimal image resolution for sampling the image data based on the estimated accuracy and a learned model, wherein the optimal image resolution is lower than the first image resolution;

sampling the image data based on the optimal image resolution; and

sending sampled data resulting from the sampling as output data to a storage device for storage, wherein the sampled data requires less storage space than the image data.

2. The method of claim 1 , wherein the image capture device is one of a camera or a medical imaging device.

3. The method of claim 1 , further comprising:

retrieving the sampled data from the storage device; and

performing image analysis on the sampled data.

4. The method of claim 3 , wherein utilizing the sampled data instead of the image data for the image analysis reduces computational time and memory consumption.

5. The method of claim 3 , wherein reducing an amount of storage space utilized for storing the image data further comprises:

estimating accuracy of the image analysis on the image data with the first image resolution;

wherein determining the optimal image resolution is further based on the estimated accuracy of image analysis.

6. The method of claim 5 , wherein the optimal image resolution represents an optimal trade-off between the estimated accuracy of image analysis and one or more costs associated with the image analysis.

7. The method of claim 6 , wherein the one or more costs associated with the image analysis comprise at least one of execution time, memory consumption, central processing unit (CPU) consumption, input/output (I/O) bandwidth consumption, or network bandwidth consumption.

8. A system comprising:

at least one processor; and

a non-transitory processor-readable memory device storing instructions that when executed by the at least one processor causes the at least one processor to perform operations including:

receiving, from an image capture device, image data comprising at least one image with a first image resolution; and

reducing an amount of storage space utilized for storing the image data by:

estimating accuracy of an analysis on the image data;

determining an optimal image resolution for sampling the image data based on the estimated accuracy and a learned model, wherein the optimal image resolution is lower than the first image resolution;

sampling the image data based on the optimal image resolution; and

sending sampled data resulting from the sampling as output data to a storage device for storage, wherein the sampled data requires less storage space than the image data.

9. The system of claim 8 , wherein the image capture device is one of a camera or a medical imaging device.

10. The system of claim 8 , wherein the operations further comprise:

retrieving the sampled data from the storage device; and

performing image analysis on the sampled data.

11. The system of claim 10 , wherein utilizing the sampled data instead of the image data for the image analysis reduces computational time and memory consumption.

12. The system of claim 10 , wherein the operations further comprise:

estimating accuracy of the image analysis on the image data with the first image resolution;

wherein determining the optimal image resolution is further based on the estimated accuracy of image analysis.

13. The system of claim 12 , wherein the optimal image resolution represents an optimal trade-off between the estimated accuracy of image analysis and one or more costs associated with the image analysis.

14. The system of claim 13 , wherein the one or more costs associated with the image analysis comprise at least one of execution time, memory consumption, central processing unit (CPU) consumption, input/output (I/O) bandwidth consumption, or network bandwidth consumption.

15. A computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to:

receive, from an image capture device, image data comprising at least one image with a first image resolution; and

reduce an amount of storage space utilized for storing the image data by:

estimating accuracy of an analysis on the image data;

determining an optimal image resolution for sampling the image data based on the estimated accuracy and a learned model, wherein the optimal image resolution is lower than the first image resolution;

sampling the image data based on the optimal image resolution; and

sending sampled data resulting from the sampling as output data to a storage device for storage, wherein the sampled data requires less storage space than the image data.

16. The computer program product of claim 15 , wherein the image capture device is one of a camera or a medical imaging device.

17. The computer program product of claim 15 , wherein the program instructions are further executable by the processor to cause the processor to:

retrieve the sampled data from the storage device; and

perform image analysis on the sampled data.

18. The computer program product of claim 17 , wherein utilizing the sampled data instead of the image data for the image analysis reduces computational time and memory consumption.

19. The computer program product of claim 17 , wherein the program instructions are further executable by the processor to cause the processor to:

estimate accuracy of the image analysis on the image data with the first image resolution;

wherein the processor determines the optimal image resolution further based on the estimated accuracy of image analysis.

20. The computer program product of claim 19 , wherein the optimal image resolution represents an optimal trade-off between the estimated accuracy of image analysis and one or more costs associated with the image analysis, and the one or more costs associated with the image analysis comprise at least one of execution time, memory consumption, central processing unit (CPU) consumption, input/output (I/O) bandwidth consumption, or network bandwidth consumption.