Automatic cable wire insertion verification

1 . A method for cable wire insertion verification, the method comprising:

receiving, from a camera system, an inspection image of a connector housing held in a housing retainer of a housing inspection system;

via a connector recognition machine vision system, classifying the connector housing as a recognized connector housing type based, at least in part, on a comparison between the inspection image of the connector housing and a template image corresponding to the recognized connector housing type;

capturing a pre-insertion image of the connector housing prior to a cable insertion step in which a cable wire is inserted into a cable cavity of one or more cable cavities of the connector housing;

capturing a post-insertion image of the connector housing after the cable insertion step; and

automatically verifying whether a correct cable wire is inserted into the cable cavity according to the recognized connector housing type and an image subtraction result generated based on the pre-insertion image and the post-insertion image.

2 . The method of claim 1 , wherein the connector recognition machine vision system is trained on a plurality of different template images corresponding to a plurality of different connector housing types.

3 . The method of claim 2 , wherein the connector recognition machine vision system includes one of a support vector machine or an artificial neural network.

4 . The method of claim 1 , wherein the camera system is a stereo camera system including a first camera and a second camera, and wherein the connector recognition machine vision system includes a first recognition model trained to classify inspection images output by the first camera and a second recognition model trained to classify inspection images output by the second camera.

5 . The method of claim 1 , wherein the camera system is attached to the housing inspection system at a fixed position relative to the housing retainer.

6 . The method of claim 1 , wherein the one or more cable cavities of the connector housing extend from an insertion face of the connector housing to an observation face of the connector housing, and wherein the inspection image of the connector housing depicts the observation face.

7 . The method of claim 1 , further comprising detecting positions of the one or more cable cavities in the inspection image by detecting correspondences between image features in the inspection image and image features in the template image.

8 . The method of claim 7 , further comprising generating a homography matrix to account for a rotation of the positions of the one or more cable cavities caused by rotation of the connector housing relative to the template image.

9 . The method of claim 1 , wherein the one or more cable cavities include two or more cable cavities, wherein the cable wire is one of a set of two or more cable wires that are inserted into the two or more cable cavities over a series of two or more cable insertion steps of an insertion sequence, and wherein, after each cable insertion step, the method further comprises automatically verifying whether a last-inserted cable wire is inserted into a correct cable cavity of the two or more cable cavities.

10 . The method of claim 9 , wherein, for each cable insertion step of the insertion sequence, a corresponding pre-insertion image is captured prior to the cable insertion step, a corresponding post-insertion image is captured after the cable insertion step, and a corresponding image subtraction result is generated for the cable insertion step based on the corresponding pre-insertion image and the corresponding post-insertion image.

11 . The method of claim 10 , wherein the corresponding image subtraction result for each cable insertion step of the insertion sequence is provided to an insertion verification machine vision system trained to output a correct insertion probability for the cable insertion step.

12 . The method of claim 10 , wherein for at least one cable wire of the set of two or more cable wires, the corresponding pre-insertion image is the inspection image of the connector housing, and wherein for one or more additional cable wires of the set of two or more cable wires, the corresponding pre-insertion image is captured after a preceding cable insertion step.

13 . The method of claim 1 , further comprising, prior to cable wire insertion, receiving cable insertion parameters specifying a correct insertion sequence in which one or more cable wires are inserted into the one or more cable cavities of the connector housing.

14 . A housing inspection system, comprising:

a controller configured to:

receive, from a camera system, an inspection image of a connector housing held in a housing retainer of the housing inspection system;

via a connector recognition machine vision system, classify the connector housing as a recognized connector housing type based, at least in part, on a comparison between the inspection image of the connector housing and a template image corresponding to the recognized connector housing type;

capture a pre-insertion image of the connector housing prior to a cable insertion step in which a cable wire is inserted into a cable cavity of one or more cable cavities of the connector housing;

capture a post-insertion image of the connector housing after the cable insertion step; and

automatically verify whether a correct cable wire is inserted into the cable cavity according to the recognized connector housing type and an image subtraction result generated based on the pre-insertion image and the post-insertion image.

15 . The housing inspection system of claim 14 , wherein the connector recognition machine vision system is trained on a plurality of different template images corresponding to a plurality of different connector housing types.

16 . The housing inspection system of claim 14 , wherein the camera system is a stereo camera system including a first camera and a second camera, and wherein the connector recognition machine vision system includes a first recognition model trained to classify inspection images output by the first camera and a second recognition model trained to classify inspection images output by the second camera.

17 . The housing inspection system of claim 14 , wherein the controller is further configured to detect positions of the one or more cable cavities in the inspection image by detecting correspondences between image features in the inspection image and image features in the template image.

18 . The housing inspection system of claim 17 , wherein the controller is further configured to generate a homography matrix to account for a rotation of the positions of the one or more cable cavities caused by rotation of the connector housing relative to the template image.

19 . The housing inspection system of claim 14 , wherein the one or more cable cavities include two or more cable cavities, wherein the cable wire is one of a set of two or more cable wires that are inserted into the two or more cable cavities over a series of two or more cable insertion steps of an insertion sequence, and wherein, after each cable insertion step, the controller is further configured to automatically verify whether a last-inserted cable wire is inserted into a correct cable cavity of the two or more cable cavities.

20 . A method for cable wire insertion verification, the method comprising:

receiving, from a camera system, an inspection image of a connector housing held in a housing retainer of a housing inspection system, wherein the camera system is attached to the housing inspection system at a fixed position relative to the housing retainer;

via a connector recognition machine vision system, classifying the connector housing as a recognized connector housing type based, at least in part, on a comparison between the inspection image of the connector housing and a template image corresponding to the recognized connector housing type by identifying correspondences between detected cable cavities in the inspection image and cable cavities in the template image; and

after each insertion step of a series of insertion steps of an insertion sequence, automatically verifying whether a correct cable wire is inserted into a cable cavity of the connector housing according to the recognized connector housing type and an image subtraction result, wherein the image subtraction result is generated by, prior to each insertion step, capturing a pre-insertion image of the connector housing, after each insertion step, capturing a post-insertion image of the connector housing, and generating the image subtraction result based on the pre-insertion image and the post-insertion image.