Method and system for machine vision detection

1. A system for determining locations of seal plugs of a connector comprising:

an image acquisition device configured to acquire an image of a connector having a plurality of openings and at least one seal plug received within at least one opening of the connector;

a processor in communication with the image acquisition device configured to process the image of the connector for:

detecting an area of the connector within the acquired image;

performing a thresholding operation on the area within the acquired image of the connector in Hue Saturation Value (HSV) color space to obtain a mask image;

performing image post-processing on the mask image using erode and dilate operations to obtain an output image;

applying at least one of a blob detection algorithm or a tip detection algorithm to the output image;

identifying locations of seal plugs within the output image based on the at least one of the blob detection algorithm or the tip detection algorithm; and

identifying available locations within the connector available for automated wire contact insertion based on the locations of the seal plugs.

2. The system of claim 1 , wherein the processor is further configured for:

generating an output of a layout of the identified locations of the connector available for automated wire contact insertion; and

providing the layout of the identified locations of the connector available for automated wire contact insertion to a controller for automated wire contact insertion into the available locations.

3. The system of claim 1 , wherein detecting an area of the connector within the acquired image comprises:

applying a clustering algorithm to the acquired image;

segmenting the image according to output of the clustering algorithm; and

generating an output image identifying the area of the connector within the acquired image.

4. The system of claim 1 , wherein detecting an area of the connector within the acquired image comprises:

filtering the acquired image by color; and

cropping the acquired image based on median pixel coordinates to obtain a cropped image of the area of the connector.

5. The system of claim 1 , wherein performing a thresholding operation on the area within the acquired image of the connector in Hue Saturation Value (HSV) color space to obtain a mask image comprises:

converting the area within the acquired image of the connector to HSV color space;

generating two or more masks of the area within the acquired image of the connector; and

combining the two or more masks to produce the mask image.

6. The system of claim 5 , wherein performing a thresholding operation on the area within the acquired image of the connector in Hue Saturation Value (HSV) color space to obtain a mask image further comprises:

generating a high intensity mask for the area within the acquired image of the connector,

wherein combining the two or more masks to produce the mask image further comprises combining the two or more masks and subtracting the high intensity mask of the area within the acquired image of the connector to produce the mask image.

7. The system of claim 1 , wherein applying at least one of a blob detection algorithm or a tip detection algorithm to the output image comprises:

finding contours within the output image;

fitting rectangles to each contour within the output image;

finding lowest corners of the rectangles relative to a bottom of the output image;

computing a center estimate for each rectangle;

estimating a seal plug radius for each rectangle; and

computing a seal plug center, unit vector, and radius for each rectangle.

8. An apparatus comprising at least one processor and at least one memory including computer program code, the at least one memory and computer program code configured to, with the processor, cause the apparatus to at least:

acquire an image of a connector having a plurality of openings and at least one seal plug received within at least one opening of the connector;

detect an area of the connector within the acquired image;

perform a thresholding operation on the area within the acquired image of the connector in Hue Saturation Value (HSV) color space to obtain a mask image;

apply at least one of a blob detection algorithm or a tip detection algorithm to the mask image;

identify locations of seal plugs within an output image based on the at least one of the blob detection algorithm or the tip detection algorithm; and

identify available locations within the connector available for automated wire contact insertion based on the locations of the seal plugs.

9. The apparatus of claim 8 , wherein the apparatus is further caused to:

generate an output of a layout of the identified locations of the connector available for automated wire contact insertion; and

provide the layout of the identified locations of the connector available for automated wire contact insertion to a controller for automated wire contact insertion into the available locations.

10. The apparatus of claim 8 , wherein causing the apparatus to detect an area of the connector within the acquired image comprises causing the apparatus to:

apply a clustering algorithm to the acquired image;

segment the image according to output of the clustering algorithm; and

generate an output image identifying the area of the connector within the acquired image.

11. The apparatus of claim 8 , wherein causing the apparatus to detect an area of the connector within the acquired image comprises causing the apparatus to:

filter the acquired image by color; and

crop the acquired image based on median pixel coordinates to obtain a cropped image of the area of the connector.

12. The apparatus of claim 8 , wherein causing the apparatus to perform a thresholding operation on the area within the acquired image of the connector in Hue Saturation Value (HSV) color space to obtain a mask image comprises causing the apparatus to:

convert the area within the acquired image of the connector to HSV color space;

generate two or more masks of the area within the acquired image of the connector; and

combine the two or more masks to produce the mask image.

13. The apparatus of claim 12 , wherein causing the apparatus to perform a thresholding operation on the area within the acquired image of the connector in Hue Saturation Value (HSV) color space to obtain a mask image further comprises causing the apparatus to:

generate a high intensity mask for the area within the acquired image of the connector,

wherein causing the apparatus to combine the two or more masks to produce the mask image further comprises causing the apparatus to combine the two or more masks and subtract the high intensity mask for the area within the acquired image of the connector to produce the mask image.

14. The apparatus of claim 8 , wherein causing the apparatus to apply at least one of a blob detection algorithm or a tip detection algorithm to the output image comprises causing the apparatus to:

find contours within the output image;

fit rectangles to each contour within the output image;

find lowest corners of the rectangles relative to a bottom of the output image;

compute a center estimate for each rectangle;

estimate a seal plug radius for each rectangle; and

compute a seal plug center, unit vector, and radius for each rectangle.

15. The apparatus of claim 8 , wherein causing the apparatus to perform a thresholding operation on the area within the acquired image of the connector in Hue Saturation Value (HSV) color space to obtain a mask image further comprises causing the apparatus to:

perform image post-processing on the mask image using erode and dilate operations.

16. A method for determining locations of seal plugs of a connector comprising:

capturing an acquired image of a connector having a plurality of openings and at least one seal plug received within at least one opening of the connector;

detecting an area of the connector within the acquired image;

performing a thresholding operation on the area within the acquired image of the connector in Hue Saturation Value (HSV) color space to obtain a mask image;

performing image post-processing on the mask image using erode and dilate operations to obtain an output image;

applying at least one of a blob detection algorithm or a tip detection algorithm to the output image;

identifying locations of seal plugs within the output image based on the at least one of the blob detection algorithm or the tip detection algorithm; and

identifying available locations within the connector available for automated wire contact insertion based on the locations of the seal plugs.

17. The method of claim 16 , further comprising:

generating an output of a layout of the identified locations of the connector available for automated wire contact insertion; and

providing the layout of the identified locations of the connector available for automated wire contact insertion to a controller for automated wire contact insertion into the available locations.

18. The method of claim 16 , wherein detecting an area of the connector within the acquired image comprises:

applying a clustering algorithm to the acquired image;

segmenting the image according to output of the clustering algorithm; and

generating an output image identifying the area of the connector within the acquired image.

19. The method of claim 16 , wherein detecting an area of the connector within the acquired image comprises:

filtering the acquired image by color; and

cropping the acquired image based on median pixel coordinates to obtain a cropped image of the area of the connector.

20. The method of claim 16 , wherein performing a thresholding operation on the area within the acquired image of the connector in Hue Saturation Value (HSV) color space to obtain a mask image comprises:

converting the area within the acquired image of the connector to HSV color space;

generating two or more masks to the area within the acquired image of the connector; and

combining the two or more masks to produce the mask image.