Post-processing a multi-spectral image for enhanced object identification
View Patent ↗A system and method for post-processing a multi-spectral image which has already been processed for pixel classification. A binary image is received which contains pixels that have been classified using a pixel classification method. Each pixel in the image has an associated intensity value and has a pixel value of 1 or 0 depending on whether the pixel has been classified as a material of interest or not. The image is divided into a plurality of blocks of pixels. On a block by block basis, pixel values in a block are changed according to a threshold-based filtering criteria such that pixels in the same block all have the same binary value. Once all the blocks have been processed, contiguous pixels having the same binary value are grouped to form separate objects. In such a manner, pixel classification errors in the post-processed binary image can be reduced.
1. A method for post-processing a pixel-classified binary image for determination of a number of objects in the image comprising a material of interest, the method comprising:
receiving a binary image containing pixels which have been classified using a pixel classification method, each of said pixels has a binary value depending on whether said pixel was classified as a material of interest or not based on each pixel's original intensity value prior to classification;
dividing said image into a plurality of blocks of pixels;
manipulating pixel values in each of said blocks according to a threshold-based filtering criteria such that all pixels in a given block have a binary value which is uniform throughout the entire block;
grouping together connected pixels having a same binary value to form objects; and
counting the number of formed objects in said image.
2. The method of claim 1 , wherein said pixel classification method comprises any of: a correlation method, a ratio method, and a best fitting reflectance method.
3. The method of claim 1 , wherein manipulating pixel values according to said threshold-based filtering criteria comprises:
for each of said blocks of pixels:
calculating a density value for the current block using intensity values collected for pixels in this block;
comparing said density to a pre-determined threshold value; and
in response to said density being less than said threshold, setting all pixels in this block to 0, otherwise setting all pixels in this block to a non-zero value.
4. The method of claim 3 , wherein calculating said density comprises determining a mean of pixel intensity values.
5. The method of claim 1 , further comprising combining pixel intensity values to generate a new intensity value for at least one pixel in a given block.
6. The method of claim 1 , wherein pixels of said image have been classified as to a material of interest being human tissue, and said formed objects are human occupants in a motor vehicle.
7. The method of claim 1 , wherein all of said blocks have a substantially uniform size.
8. The method of claim 1 , wherein a size of any given block is selected based upon an estimated size of objects likely to be identified as a material of interest within a field of view of an imaging system used to capture said image.
9. A system for post-processing a pixel-classified binary image for determination of a number of objects in the image comprising a material of interest, the system comprising:
a memory and a storage device; and
a processor in communication with said memory and storage device, said processor executing machine readable instructions for performing:
receiving a binary image containing pixels which have been classified using a pixel classification method, each of said pixels has a binary value depending on whether said pixel was classified as a material of interest or not based on each pixel's original intensity value prior to classification;
dividing said image into a plurality of blocks of pixels;
manipulating pixel values in each of said blocks according to a threshold-based filtering criteria such that all pixels in a given block have a binary value which is uniform throughout the entire block; and
grouping together connected pixels having a same binary value to form objects; and
counting the number of formed objects in said image.
10. The system of claim 8 , wherein said pixel classification method comprises any of: a correlation method, a ratio method, and a best fitting reflectance method.
11. The system of claim 8 , wherein manipulating pixel values according to said threshold-based filtering criteria comprises:
for each of said blocks of pixels:
calculating a density value for the current block using intensity values collected for pixels in this block;
comparing said density to a pre-determined threshold value; and
in response to said density being less than said threshold, setting all pixels in this block to zero, otherwise setting all pixels in this block to a non-zero value.
12. The system of claim 11 , wherein calculating said density comprises determining a mean of pixel intensity values.
13. The system of claim 11 , further comprising combining pixel intensity values to generate a new intensity value for at least one pixel in a given block.
14. The system of claim 11 , wherein pixels of said image have been classified as to a material of interest being human tissue, and said formed objects are human occupants in a motor vehicle.
15. The system of claim 11 , wherein all of said blocks have a substantially uniform size.
16. The system of claim 11 , wherein a size of any given block is selected based upon an estimated size of objects likely to be identified as a material of interest within a field of view of an imaging system used to capture said image.
17. A computer implemented method for post-processing a pixel-classified binary image for determination of a number of objects in the image comprising a material of interest, the method comprising:
receiving a binary image containing pixels which have been classified using a pixel classification method, each of said pixels has a binary value depending on whether said pixel was classified as a material of interest or not based on each pixel's original intensity value prior to classification;
dividing said image into a plurality of blocks of pixels;
for each of said blocks:
calculating a mean density value using intensity values of pixels in this block;
comparing said mean density value to a pre-determined threshold; and
in response to said density being less than said threshold, setting all pixels in this block to zero, otherwise setting all pixels in this block to a non-zero value; and
grouping together connected pixels having a same binary value to form objects; and
counting the number of formed objects in said image.
18. The computer implemented method of claim 17 , further comprising combining pixel intensity values to generate a new intensity value for at least one pixel in a given block.
19. The computer implemented method of claim 17 , wherein all of said blocks have a substantially uniform size.
20. The computer implemented method of claim 17 , wherein pixels of said image have been classified as to a material of interest being human tissue, and said formed objects are human occupants in a motor vehicle.
21. The computer implemented method of claim 17 , wherein a size of any given block is selected based upon an estimated size of objects likely to be identified as a material of interest within a field of view of an imaging system used to capture said image.