Cable wire insertion depth monitoring

Abstract

To provide cable wire insertion depth monitoring.SOLUTION: A method (200) for cable wire insertion monitoring includes receiving, from a camera system (312), an inspection image (314) of a connector housing (302) held in a housing retainer (306) of a housing inspection system (300). Insertion of a cable wire (324) into a corresponding cable cavity (304) of the connector housing (302) is detected via an insertion monitoring machine vision system (402). Based at least in part on the inspection image (314), an insertion depth of the cable wire (324) into the corresponding cable cavity (304) is estimated. An indication (416) of the insertion depth of the cable wire (324) is output.SELECTED DRAWING: Figure 3B

Description

[Technical Field]

[0001] The present invention relates generally to computer vision systems, and more particularly to the use of machine vision to monitor the insertion depth of cable wires into connector housings. [Background technology]

[0002] Various types of cable connectors are often used to conductively couple one cable to another and / or to couple a cable to an electronic device for data and / or power transmission. In some examples, such cable connectors include one or more cable wires that are inserted into corresponding cable cavities in a connector housing. The size and shape of the connector housing, as well as the number and distribution of cable cavities included therein, can vary from situation to situation depending on the purpose of the cable connector. Summary of the Invention [Means for solving the problem]

[0003] This summary is not an extensive overview of the specification, and is not intended to identify key or critical elements of the specification, nor to delineate the scope of particular embodiments of the specification or the scope of the claims. Its sole purpose is to present some concepts of the specification in a simplified form as a prelude to the more detailed description that is presented in the present disclosure.

[0004] A method for cable wire insertion monitoring includes receiving an inspection image of a connector housing held in a housing retainer of a housing inspection system from a camera system, detecting insertion of cable wires into corresponding cable cavities of the connector housing via an insertion monitoring machine vision system, estimating insertion depths of the cable wires into the corresponding cable cavities based at least in part on the inspection image, and outputting an indication of the insertion depths of the cable wires.

[0005] The discussed features, functions, and advantages may be realized independently in various embodiments or may be combined in other embodiments, and further details of such features, functions, and advantages may be understood with reference to the following description and drawings. [Brief explanation of the drawings]

[0006] [Figure 1] 1 is a schematic diagram of an exemplary cable connector including a cable housing into which multiple cable wires are inserted. [Figure 2] 1 illustrates an exemplary method for cable wire insertion monitoring. [Figure 3A] 1 is a schematic diagram of an exemplary connector housing held in a housing retainer of a housing inspection system. [Figure 3B] FIG. 1 is a schematic diagram of the use of a camera system of a housing inspection system to capture inspection images of a connector housing. [Figure 3C] 1 is a schematic diagram of an exemplary inspection image captured by a camera system. [Figure 4] 10 is a schematic diagram of an estimation of insertion depth of a cable wire into a connector housing. FIG. [Figure 5] FIG. 10 is a schematic diagram of identifying correspondences between image features in a test image and a template connector image. [Figure 6A] 10 is a schematic diagram of the insertion of cable wires into the cable cavity of the connector housing. FIG. [Figure 6B] 10 is a schematic diagram of the insertion of cable wires into the cable cavity of the connector housing. FIG. [Figure 6C] 10 is a schematic diagram of the insertion of cable wires into the cable cavity of the connector housing. FIG. [Figure 7] 10A-10C illustrate exemplary full insertion and partial retraction depth distributions of cable wires inserted into a cable cavity. [Figure 8] FIG. 1 is a schematic diagram of an exemplary computer system. DETAILED DESCRIPTION OF THE INVENTION

[0007] Construction of cable connectors typically involves one or more steps of inserting individual cable wires into cable cavities in a connector housing. Such insertion may be performed manually, such as by a human operator, and / or automatically, such as via a suitable mechanical or robotic insertion system. In either case, however, cable wire insertion can be inconsistent and error-prone. Furthermore, manual inspection of connector housings during manufacturing is tedious, time-consuming, and may not always detect cable insertion errors.

[0008] Accordingly, the present disclosure relates to techniques for cable wire insertion depth monitoring. The techniques described herein include capturing inspection images of a connector housing held in a housing retainer of a housing inspection system. This may be done to detect the insertion of a cable wire into a cable cavity of the connector housing and then estimate the insertion depth of the cable wire. For example, as the cable wire is inserted into the cable cavity, a portion of the cable wire (e.g., a cable contact attached to the cable wire) may become visible in the inspection image captured by a camera system. Based on such images, the housing inspection system may estimate the insertion depth of the cable wire into the cable cavity, for example, by stereo triangulation if a stereo camera system is used. In this way, the housing inspection system may detect when the cable wire is not inserted to the correct insertion depth, potentially mitigating, for example, scenarios in which the cable wire does not lock into place within the connector housing due to insufficient insertion. For example, the techniques described herein may output a notification when it is detected that the cable wire is not inserted far enough into the cable cavity. This can beneficially improve the speed and quality at which cable connectors are built.

[0009] The insertion of cable wires into a connector housing is illustrated generally with reference to FIG. 1, which shows an exemplary cable connector 100. The cable connector includes a connector housing 102, which contains multiple cable cavities into which cables may be inserted during assembly of the cable connector. Several of the cable cavities are labeled as cable cavities 104 in FIG. 1. Additionally, FIG. 1 shows three different cable wires 106A, 106B, and 106C. Cable wires 106B and 106C have been inserted into their respective cable cavities in the connector housing, while cable wire 106A has not yet been inserted.

[0010] It will be understood that the particular components shown in Figure 1, as well as the other Figures 2-8 described herein, are greatly simplified for purposes of explanation. The size, shape, and specific appearance of the components shown in Figures 1-8 are non-limiting and not drawn to scale. Furthermore, it will be understood that the components shown in Figures 1-8 may be constructed from any suitable material. For example, the connector housings, housing retainers, cable wires, cable contacts, and other components described herein may be constructed from any suitable combination of plastic and / or metal, by way of non-limiting example.

[0011] While the example of Figure 1 shows three different cable wires, it will be understood that any suitable number of different cable wires may be inserted into the connector housing. For example, the number of inserted cable wires may be equal to or less than the number of cable cavities in the connector housing. In other words, the specific configuration shown in Figure 1 is non-limiting, and it will be understood that the techniques described herein may be applicable to cable connectors used to connect any suitable number of cable wires to each other and / or to electronic devices such as PCBs.

[0012] This disclosure focuses primarily on electrically conductive cable wires used to transmit power and / or data, however, in some examples the cable connectors described herein may be used with cable wires that are not electrically conductive but include other suitable transmission media, such as fiber optic cable.

[0013] As used herein, "cable wire" includes any length of material (e.g., copper wire, optical fiber) used for transmitting data and / or power that is often coated with a protective material (e.g., plastic or rubber insulation, ground shield). In other words, the term "cable wire" is not used to refer solely to the conductive (e.g., copper) or non-conductive (e.g., optical fiber) core of a cable, but may also refer to any coating, insulation, and / or shielding applied to the core.

[0014] A "cable" includes one or more different cable wires. When a cable includes only one cable wire, the terms "cable wire" and "cable" may be used interchangeably. However, in some examples, a cable includes two or more cable wires bundled together. For example, in some embodiments, a cable is a multi-conductor cable including two or more cable wires, e.g., different conductive copper wires each coated with their own respective insulating cable jacket and bundled together with additional insulation and / or shielding to form a multi-conductor cable. In some embodiments, a cable is a shielded twisted pair cable, where different cable wires include pairs of conductors twisted together and protected by an insulating jacket. The twisted pairs are bundled together and surrounded by additional shielding and / or insulation to form a shielded twisted pair cable. When a cable includes two or more different cable wires, the different cable wires may each be inserted into a different cable cavity of the connector housing.

[0015] Generally, there is a correspondence between different specific cable wires and the cable cavities into which they are inserted. For example, different specific cable wires may have different purposes (e.g., transmit power, transmit data, complete a ground connection) and therefore may be inserted into different specific cable cavities so that a final cable connector can be used to couple the cable wires to the correct downstream components (e.g., ground points, input / output lines, power inlets). In some cases, different cable wires have different distinguishable appearances; for example, the cable wires may have different sizes (e.g., gauges), use different colors or types of insulating / protective jackets, use different materials for the cable wire cores (e.g., different conductive metals or non-conductive materials), and / or differ in any other suitable manner.

[0016] In the example of FIG. 1 , conductive cable contacts 108 are attached to the ends of cable wires 106A. However, in general, the ends of cable wires may be processed in any suitable manner. For example, in some examples, conductive contacts may be attached to the cable wire ends, and such contacts may have any suitable size and shape. In some cases, different types of conductive contacts may be attached to different cable wires inserted into the same connector housing. In some examples, the cable wires need not include conductive contacts. Rather, for example, the cable wires may be terminated at exposed lengths of the cable wire core or in any other suitable manner.

[0017] Each cable cavity of the connector housing is sized and shaped for insertion of a cable wire. As shown, cable wires 106B and 106C are inserted into the respective cable cavity of the connector housing. The cable cavities have any suitable size based on the size of the cable intended for insertion into the cable cavity. In some examples, the same connector housing may include different cable cavity sizes intended for insertion of cable wires having different sizes (e.g., different wire gauges).

[0018] In some cases, the cable cavity is sized to accommodate an insulating jacket surrounding a cable wire core (e.g., copper wire or fiber optic material) so that a length of insulated cable is inserted into the connector housing. In other instances, the insulating jacket may be trimmed so that only the cable core is inserted into the connector housing.

[0019] Any suitable length of cable wire may be inserted into the connector housing. Generally, the cable wire is inserted far enough into the connector housing to enable transmission of data and / or power between the cable wire and any components coupled to the connector housing, such as other cable wires and / or electronic devices. Additionally or alternatively, the cable wire may be inserted far enough so that a retention feature within the connector housing holds the cable wire in place.

[0020] However, as discussed above, such insertion can sometimes be prone to insertion errors, such as inserting the cable wire at an incorrect insertion distance. Manual inspection and verification of cable wire insertion can be tedious and time-consuming. Accordingly, FIG. 2 illustrates an exemplary method 200 for automated cable wire insertion verification. The steps of method 200 may be initiated, terminated, and / or repeated at any appropriate time and in response to any appropriate condition. Method 200 is primarily described as being performed by a housing inspection system including a controller executing software instructions to implement a machine vision system for cable wire insertion depth monitoring. However, it will be understood that the steps of method 200 may be performed by any suitable computer system of one or more computing devices, and that any computing device performing the steps of method 200 may have any suitable functionality, hardware configuration, and form factor. In some examples, method 200 is performed by computer system 800, described below with reference to FIG. 8.

[0021] At step 202, method 200 includes receiving, from a camera system, an inspection image of a connector housing held in a housing retainer of a housing inspection system. An exemplary housing inspection system is illustrated generally with reference to FIG. 3A. Specifically, FIG. 3A includes a schematic diagram of a housing inspection system 300 used to inspect a connector housing 302. The connector housing includes multiple cable cavities, some of which are labeled as cable cavities 304. During a subsequent insertion sequence, one or more cable wires may be inserted into corresponding cable cavities in the connector housing, as described in detail below.

[0022] The connector housing is retained in housing retainer 306. In this example, the housing retainer includes two clamps that utilize friction to grip the sides of the connector housing, thereby holding the connector housing in place. However, it will be understood that the housing retainer may take the form of any suitable mechanism or structure that holds the connector housing in place while automated cable insertion verification is performed. For example, the housing retainer may use friction, suction, magnetic attraction, adhesive, and / or any other suitable force to hold the connector housing. In some examples, the housing retainer may be sized and shaped to accommodate a wide variety of different types of housing retainers having different shapes and sizes without requiring significant modification or reconfiguration of the housing retainer.

[0023] The connector housing may be inserted into the housing inspection system in any suitable manner. In some examples, a human operator loads the connector housing into the housing inspection system before inserting the cable wires into the connector housing, and then removes the connector housing from the inspection system once cable insertion is complete. In some examples, the insertion and / or removal of the connector housing may be performed by a suitable automated system, such as a suitable automated machine or robot.

[0024] Similarly, while the connector housing is held in place by the housing retainer, the cable wires may be inserted into the connector housing in any suitable manner. For example, the cable wires may be inserted manually by a human operator. Additionally or alternatively, the cable wires may be inserted automatically by a suitable automated system.

[0025] In the example of FIG. 3A , housing inspection system 300 is communicatively coupled to controller 308. A “controller” takes the form of any suitable computer logic hardware configured to execute software, firmware, and / or hardware-encoded instructions to thereby control the operation of the housing inspection system. For example, as described in more detail below, the controller may be used to control the operation of a camera system and / or implement a machine vision system used for connector housing recognition and cable wire insertion depth monitoring. If an automated system is used to insert connector housings into the housing inspection system and / or insert cable wires into the connector housings, controller 308 may control such automated system.

[0026] In this example, the controller is shown as separate from the housing inspection system. For example, the controller may be at least partially integrated into a structure physically separate from the housing inspection system or may be communicatively coupled to the housing inspection system via any suitable wired or wireless connection. However, it will be understood that in some examples, the controller may be "on-board" the housing inspection system, integrated into the same physical assembly as the housing inspection system. In some examples, the controller 308 performs one or more steps of the method 200. In some examples, the controller 308 is implemented as a computer system 800, described below with respect to FIG. 8.

[0027] In some cases, prior to inserting the cable wires into the connector housing, the housing inspection system receives a set of cable insertion parameters that include information related to the cable wire insertion process. In the example of Figure 3A, the controller 308 receives a set of cable insertion parameters 310. Generally, these include any information related to the subsequent cable insertion process in which the cable wires are inserted into the cable cavity of the connector housing.

[0028] For example, in some cases, the cable insertion parameters specify the intended type of connector housing to be inserted into a housing inspection system for the current assembly process. Once the connector housing is inserted, the housing inspection system may perform connector housing recognition to verify that the connector housing is the correct type. Additionally, or alternatively, the cable insertion parameters may specify the correct insertion sequence in which one or more cable wires are to be inserted into one or more cable cavities of the connector housing. This may include the order in which the cable cavities should be filled (e.g., based on different identifiers assigned to the cable cavities), the order in which different cable wires should be inserted (e.g., based on different identifiers assigned to the cable wires), a mapping of different specific cable wires to different cable cavities, and / or any other suitable information. It will be understood that the cable insertion parameters may include any suitable information related to cable wire insertion into a connector housing.

[0029] The cable insertion parameters may be provided in any suitable manner. In some examples, the cable insertion parameters are provided by a human user, such as an operator or supervisor of the housing inspection system. For example, the human user may specify the cable insertion parameters by providing input to an appropriate input mechanism, such as a computer mouse, keyboard, and / or touch-sensitive display interface. Additionally or alternatively, the cable insertion parameters may be retrieved from computer storage. For example, the cable insertion parameters may be stored on local data storage hardware of the housing inspection system, loaded from a removable storage device, and / or accessed over a computer network.

[0030] In some examples, aspects of the cable insertion parameters may be displayed for viewing. For example, the cable insertion parameters may include a set of instructions to a human user for inserting the cable wires in the correct sequence. In some examples, the displayed instructions are updated in real time to provide feedback to the user, for example, as to whether the correct cable wires were inserted in the last insertion step.

[0031] Figure 3B schematically illustrates another view of a connector housing held by a housing retainer of a housing inspection system. In Figure 3B, portions of the housing inspection system have been removed to provide a top view (e.g., looking along the Y-axis as labeled in Figures 3A and 3B) of a connector housing 302 held by a housing retainer 306 within the housing inspection system 300. From this perspective, it can be seen that the housing inspection system includes a camera system 312. The camera system is configured to capture an inspection image 314A of the connector housing, as described in more detail below.

[0032] In the example of Figure 3B, camera system 312 is a stereo camera system including a first camera 316A and a second camera 316B. Each of these cameras can capture a respective inspection image of the connector housing itself, and either or both of these inspection images may be used for connector housing recognition and cable wire insertion verification. For example, first inspection image 314A may be captured by first camera 316A, while second inspection image 314B (shown in Figure 3C) may be captured by second camera 316B.

[0033] In general, however, the camera system may include any suitable number and type of various cameras for capturing insertion images. For example, in some instances, the camera system may include only a single camera. In some instances, the camera system may include three or more cameras. In general, increasing the number of cameras may improve the accuracy of the insertion depth monitoring process. In other words, the housing inspection system may include a camera system of one or more suitable cameras, each sensitive to any suitable wavelength of electromagnetic radiation and having any suitable image capture capabilities, including resolution, frame rate, and / or field of view.

[0034] As an example, the camera system includes one or more grayscale or RGB cameras that are sensitive to visible wavelengths of light and output grayscale or RGB images. In some examples, the camera system includes one or more depth cameras in addition to or instead of the visible light cameras and / or other suitable cameras. The depth cameras are configured to output depth images, the pixels of which encode detected distances between the image sensors of the depth cameras and physical objects in the surrounding environment. Any suitable depth-sensing technology may be used, such as stereo, structured light, or time-of-flight.

[0035] In instances where both a visible light camera and a depth camera are used, they may in some cases be used together as an integrated camera module. As one non-limiting example, an Intel® RealSense™ camera system may be used, which includes both an RGB and a depth camera module together in known alignment and outputs both RGB and depth image data.

[0036] In the example of FIG. 3B, the housing inspection system further includes an illumination system 318. The illumination system is configured to project illumination light toward the connector housing. This may help provide relatively uniform lighting conditions while inspection images of the connector housing are captured. The illumination system may take any suitable form and may use any suitable hardware components for generating the illumination light. The illumination light may have any suitable intensity and may use electromagnetic radiation of any suitable wavelength.

[0037] The illumination light may be illuminated at any suitable time. For example, in some cases, the illumination light may be provided whenever the housing inspection system is powered on. In some cases, the illumination light may be selectively switched on and off. For example, the illumination light may be illuminated only when the connector housing is held in the housing retainer, or may be illuminated only immediately prior to capturing an inspection image (e.g., the illumination light may function as a camera flash).

[0038] In the example of FIG. 3B , the camera system is attached to the housing inspection system at a fixed position relative to the housing retainer. This can advantageously improve the consistency of inspection images captured by the camera system. For example, because the position of the camera system is fixed relative to the housing retainer, various connector housings held in the housing retainer can be imaged from approximately the same distance for each inspection image. In some cases, the housing retainer and / or connector housing are designed so that the connector housing is positioned a known, fixed distance from the camera system while the connector housing is held in the housing retainer. For example, the housing retainer may be designed to fit within a notch or groove in the connector housing. In some cases, while the connector housing is loaded into the housing retainer, a feature or marker on the connector housing is inserted to align with a feature or marker on the housing retainer, indicating that the connector housing is properly positioned relative to the camera system.

[0039] As shown, in this example, the connector housing has two distinct faces on either side of the connector housing (relative to the Z-axis labeled in FIGS. 3A and 3B). This includes an insertion face, through which the cable wires are inserted, and an observation face, which faces the camera system. In FIG. 3B, connector housing 302 includes insertion face 320 and observation face 322. The cable cavity of the connector housing extends from the insertion face of the connector housing to the observation face of the connector housing. Also, the inspection image captured by the camera system shows the observation face. In this way, when the cable wires are inserted into the connector housing, the tips of the cable wires can be visible in the inspection image captured by the camera system. This can be used to estimate the insertion depth of the cable wires, as described in more detail below.

[0040] In some cases, the flexibility of the connector housing can introduce some measurement variation when estimating the insertion depth of the cable wires. This flexibility can vary depending on the material used to construct the connector housing; for example, a metal housing may be less flexible than a plastic retainer, but some flexing and variation may still be observed. Therefore, in some instances, the housing inspection system may estimate the position of the observation surface of the connector housing relative to the camera system. This is called D face 3B. The housing inspection system then tip The position of the tip of the cable wire in the connector housing can be estimated, shown as D. tip is shown relative to the estimated position 323 of the cable wire tip, shown in the connector housing. The insertion depth of the cable wire is then determined by D tip -D face and estimate the insertion depth, e.g., D insertionThis approach can beneficially improve the accuracy of insertion depth estimation. The positions of the observation plane and the tip of the cable wire may be estimated in any suitable manner, for example, through stereo triangulation.

[0041] FIG. 3C includes a schematic diagram of exemplary inspection images 314A and 314B captured from connector housing 302 by camera system 312. As described above, inspection image 314A is captured by one camera of the stereo camera system, and inspection image 314B is captured by a second camera of the stereo camera system. Each inspection image shows an observation side of the connector housing opposite the insertion side, where the cable wires are inserted. In this example, the cable cavity extends from the insertion side through the connector housing to the observation side. Thus, the cable wires inserted into the connector housing may be visible in the captured inspection image of the observation side. For example, in FIG. 3C, cable wire 324 has been inserted into the connector housing and is therefore visible in inspection images 314A and 314B.

[0042] It will be understood that the images described herein need not be visually rendered or displayed for viewing by a human user. While two exemplary inspection images are shown in FIG. 3C, this is done for illustrative purposes only. Rather, in some examples, the images are captured and stored by the housing inspection system for processing as digital data structures that are not visually displayed on a computer display or otherwise presented for viewing.

[0043] In some examples, after capturing the inspection image, the housing inspection system may compare the inspection image to a template connector image to confirm that the connector housing is the intended connector housing type. This process is illustrated generally with respect to FIG. 4, which shows an example controller 400. Similar to controller 308 of FIG. 3A, controller 400 may be implemented as any suitable computer logic device. In some examples, controller 400 is implemented as computer system 800, described below with respect to FIG. 8.

[0044] 4, a controller 400 implements an insertion monitoring machine vision system 402. Additionally, the controller is communicatively coupled to a camera system 404 of a housing inspection system. The controller 400 receives an inspection image 406 from the camera system 402, the inspection image showing the connector housing held in the housing retainer. In some cases, two or more inspection images may be received (e.g., a stereo pair of inspection images, such as images 314A and 314B in FIG. 3C ). The inspection images are input to the insertion monitoring machine vision system, which is configured to estimate the insertion depth of the cable wire into the connector housing.

[0045] The insertion monitoring machine vision system may be implemented in any suitable manner. In the example of FIG. 4 , the insertion monitoring machine vision system includes a connector housing recognition system 408, an insertion detection system 412, and an insertion depth estimation system 414. These may be implemented as separate software applications, as a single software application performing different functions, and / or in any other suitable manner. The connector housing recognition system, the insertion detection system, and / or the insertion depth estimation system of the insertion monitoring machine vision system may be implemented by the same computing device or by two or more different computing devices operating in cooperation.

[0046] In some examples, the insertion monitoring machine vision system includes one or more suitable artificial intelligence (AI) and / or machine learning (ML) models configured to evaluate the input image. As one non-limiting example, the connector housing recognition system 408 may be trained on a plurality of different template connector images corresponding to a plurality of different connector housing types. This is shown schematically in FIG. 4, where the connector recognition machine is trained on a plurality of different template connector images, including template connector image 410. The connector housing recognition system compares the inspection image 406 to the template connector image 410 to confirm that the connector housing is the intended connector housing type.

[0047] Any suitable ML and / or AI techniques may be used to implement the connector housing recognition system. In some cases, the connector housing recognition system includes a support vector machine, which may be used to generate different classification models corresponding to different recognized connector housing types. Additionally or alternatively, the connector housing recognition system may include an artificial neural network, e.g., the connector housing recognition system may include one of a support vector machine or an artificial neural network. When a stereo camera system is used to capture inspection images of the connector housing (as shown in FIG. 3B ), the connector housing recognition system may optionally include a first recognition model trained to classify inspection images output by a first camera of the stereo camera system and a second recognition model trained to classify inspection images output by a second camera of the stereo camera system.

[0048] In one non-limiting approach, training a connector-recognition machine vision system may include placing a connector housing in a housing inspection system and then capturing one or more images (referred to as template connector images) of the connector housing. This may be repeated for each connector housing type. These template connector images may then be loaded into a database, where an image classification model is generated (e.g., using a support vector machine or artificial neural network) to generate a distinct, unique image signature for each connector type. In some examples, the "template connector image" may include a three-dimensional model or scan in addition to, or instead of, a two-dimensional image of the connector housing.

[0049] Nevertheless, in the example of FIG. 4, the connector housing recognition system is configured to verify that the correct type of connector housing is inserted into the housing inspection system. For example, in some cases, the “correct” type of connector housing is already known and may be specified in the cable insertion parameters, for example, as described above with respect to FIG. 3A. Thus, classifying the connector housing may be useful for verifying that the correct type of housing is inserted. In some cases, the housing inspection system may output an error if an incorrect connector housing type is detected. This could be, for example, a scenario in which a human operator mistakenly loads the wrong type of connector housing into the housing inspection system.

[0050] Alternatively, in some instances, the connector housing is classified essentially blindly, without prior knowledge of the "correct" connector housing type for, for example, the current type of cable connector being built. In one exemplary scenario, a user can load an appropriate connector housing into a housing inspection system, which can then classify the connector housing as a recognized connector housing type. From there, the system may automatically retrieve the correct insertion sequence and set of insertion instructions for the recognized connector housing type, which the user can follow while inserting the cable wire into the connector housing. Additionally or alternatively, the system may automatically retrieve a set of insertion parameters corresponding to the recognized connector housing type.

[0051] As one non-limiting example, an inspection image may be provided to various classification models corresponding to various recognized connector housing types, each of which then outputs a prediction score indicating the model's confidence that the inspection image corresponds to that model's connector housing type. These prediction scores may then be aggregated and compared to a classification threshold. If the most likely prediction score exceeds the classification threshold, the machine vision system classifies the connector housing as belonging to the connector housing type corresponding to the most likely prediction score. If none of the prediction scores exceed the classification threshold, the machine vision system may output a classification error. The classification threshold may have any appropriate value depending on the implementation and may, for example, be set by a user or operator to balance the risk of incorrect classification with the risk of classification error.

[0052] Once the connector housing is classified, the housing inspection system may, in some cases, perform cavity detection to identify the location of cable cavities in the connector housing. In some examples, detecting the location of cable cavities may include detecting a correspondence between image features of the inspection image and image features of the template connector image. For example, once a template connector image of a particular connector housing type is captured, the location of cable cavities in the template connector image may be manually labeled by a human user and / or automatically detected via an appropriate computer vision system (e.g., an appropriate ML and / or AI model). Thus, by detecting a correspondence between the inspection image and the template connector image, the location of cable cavities in the inspection image may be detected.

[0053] This is illustrated generally with respect to Figure 5, which includes an exemplary inspection image 500 showing a connector housing held in a housing inspection system. Inspection image 500 is compared to a template connector image 502 showing the same type of connector housing as the inspection image. In Figure 5, image features 504A and 504B of inspection image 500 correspond to image features 506A and 506B of template connector image 502.

[0054] Any suitable technique may be used to detect such correspondences between image features. In some cases, suitable feature recognition algorithms such as Scale-Invariant Feature Transform (SIFT) and / or Fast Library for Approximate Nearest Neighbors (FLANN) may be used to identify correspondences between image features in two different images. In one exemplary technique, SIFT may first be applied to both images to detect keypoints and compute their descriptors. SIFT keypoints are points in an image that are invariant to scale and rotation, and each keypoint has an associated descriptor. These descriptors effectively capture local gradient information around the keypoint, making them clear and stable to changes in viewpoint and lighting.

[0055] Once SIFT descriptors are obtained from both images, FLANN may be used to match corresponding descriptors between the two images. FLANN is an algorithm for efficiently finding approximate nearest neighbors in a high-dimensional space. It speeds up the search for the closest match between each descriptor in one image and a descriptor in the other image. In this process, each descriptor in the first image is compared to all descriptors in the second image to find the best match. The FLANN algorithm efficiently searches for the nearest neighbors (i.e., the most similar descriptors) in this high-dimensional space. Typically, the nearest neighbor is identified as the best match, but second nearest neighbors may also be considered to ensure uniqueness of matches and filter false matches. The output of this process is a set of keypoint pairs, each consisting of a keypoint from the first image and its corresponding keypoint in the second image. For example, these keypoints may represent matching cable cavities between the two images.

[0056] In some examples, upon detecting a correspondence between the cable cavities in the inspection image and the template connector image, a homography matrix is ​​generated to account for the rotation of the position of one or more cable cavities caused by the rotation of the connector housing in the inspection image relative to the template connector image. This is shown schematically with respect to FIG. 5, where homography matrix 508 is generated to account for the rotation of the connector housing between the template and inspection images.

[0057] In general, the homography matrix may be generated in any suitable manner. If SIFT is used, the SIFT descriptor is rotation-invariant, so the matched keypoints will inherently account for any rotation of the connector housing between the two images. This means that if the connector housing is rotated in one image relative to the other, the SIFT algorithm can still find the corresponding keypoints. Using the matched keypoints, a homography matrix may be estimated, describing how points in one image transform to points in another image under a planar perspective transformation. This includes translation, rotation, scale, and perspective distortion. The goal is to find a homography matrix H that satisfies the equation p' = Hp, where p and p' are corresponding points in the two images. This may be done using methods such as Direct Linear Transformation (DLT) or algorithms such as Random Sample Consensus (RANSAC), which can robustly handle outliers. The result is a homography matrix, which, when applied to points in one image, maps them to corresponding points in the other image. This matrix accounts for all planar transformations, including any rotations that occur between the two views of the object.

[0058] 2, in step 204, method 200 includes detecting, via an insertion monitoring machine vision system, the insertion of a cable wire into a cable cavity of the connector housing. Using the example of FIG. 4, insertion monitoring machine vision system 402 implements an insertion detection system 412 configured to detect the insertion of a cable wire into the cable cavity. This may be done in any suitable manner.

[0059] As one exemplary approach, a camera system may be used to capture several images of the connector housing, including at least one image captured before the insertion of the cable wire (e.g., a pre-insertion image) and at least one image captured after the insertion of the cable wire (e.g., a post-insertion image). In some cases, both the pre-insertion image and the post-insertion image may be input into an image subtraction operation. If the only change between the two images was the insertion of the cable wire, many pixel values ​​in the image subtraction result will be zero or near zero. Thus, the image subtraction result has the effect of highlighting any changes in the appearance of the connector housing, e.g., the appearance of the cable wire inserted into the cable cavity, between the capture of the two images. In other words, in some examples, the housing inspection system may generate an image subtraction result based on the pre-insertion image and the post-insertion image and use it to detect movement (e.g., the insertion of the cable wire) between the two images.

[0060] It will be appreciated that this approach is non-limiting and insertion of the cable wires may be determined in additional or alternative manners, for example, through detection of sound, vibration (e.g., vibration caused by a retention mechanism within the cable cavity engaging the cable wires), a change in weight of the connector housing, and / or a human operator manually indicating that the cable wires have been inserted.

[0061] 2, at step 206, the method 200 includes estimating an insertion depth of the cable wire into the cable cavity based at least in part on the inspection image. Using the example of FIG. 4, the insertion monitoring machine vision system 402 implements an insertion depth estimation system 414 that estimates the insertion depth of the cable wire based on the inspection image. This may be done in any suitable manner.

[0062] In one non-limiting approach, the camera system is a stereo camera system, and thus the insertion monitoring machine vision receives two or more inspection images (e.g., captured by two or more cameras of the stereo camera system). The insertion depth of the cable wire may then be estimated through stereo triangulation. For example, the insertion depth estimation system may detect the position of the cable wire in two different stereo inspection images (e.g., through appropriate image morphology detection techniques as described above).

[0063] In other words, one example employs stereo triangulation to estimate the insertion depth of a cable wire within a cable cavity by analyzing two different inspection images capturing the cable wire's position from different viewpoints. By accurately identifying and matching corresponding points on the cable wire in both images and utilizing camera calibration data to account for the geometric and optical characteristics of the imaging setup, the three-dimensional coordinates of the wire's end point can be calculated. This calculation is achieved through geometric triangulation of the lines of sight from each camera's viewpoint to the matching points, enabling the estimation of the cable wire's insertion depth within the cavity. This method provides a stable and accurate means of assessing cable wire positioning, enhancing quality control and verification processes in manufacturing and assembly applications.

[0064] It will be appreciated that other techniques may be used in addition to or instead of stereo triangulation. For example, when a camera system includes a depth camera, output from the depth camera may be used to estimate the insertion depth of a cable wire within a cable cavity; for example, a depth value representing a relatively large distance from the depth camera may correspond to a relatively small insertion depth of the cable wire. As another example, monocular depth estimation may be employed. This technique relies on a single image input and utilizes an appropriate machine learning algorithm, in particular a convolutional neural network (CNN), to infer the three-dimensional structure of the scene. Unlike stereo triangulation, which calculates depth based on the geometric relationship between two viewpoints, monocular depth estimation exploits patterns and forms within an image that provide depth-related cues, such as object size, perspective, texture gradients, and shading.

[0065] In either case, based on the inspection image, the housing inspection system estimates the insertion depth of the cable wire within the cable cavity. Returning briefly to Figure 2, in step 208, the method 200 includes outputting an indication of the insertion depth of the cable wire. Using the example of Figure 4, the insertion depth estimation system outputs an insertion depth indication 416 representing the estimated insertion depth of the cable wire into the cable cavity.

[0066] It will be appreciated that such an indication may take any suitable form. As one example, the indication may take the form of a numerical representation of the insertion depth that is displayed for viewing by a human operator, output to an autonomous system, and / or reported in another suitable manner. In general, the insertion depth indication may be “output” in a variety of suitable manners depending on the implementation. In some embodiments, outputting the insertion depth indication includes passing the insertion depth indication to a downstream application, sending the insertion depth indication to another computing device, writing the insertion depth indication to a data file, storing the insertion depth indication in non-volatile storage of the computing device, and / or storing the insertion depth indication in an external storage device communicatively coupled to the computing device.

[0067] In some examples, outputting an indication of the insertion depth of the cable wire includes outputting a confirmation that the insertion depth exceeds an insertion threshold corresponding to sufficient insertion of the cable wire into the connector housing. In the example of FIG. 4, the estimated insertion depth is compared to insertion threshold 418. In some examples, if the estimated insertion depth exceeds the insertion threshold, the housing inspection system may output a successful insertion confirmation, such as, for example, displaying an on-screen confirmation, illuminating an indicator light, activating a haptic feedback system, playing a confirmation sound, etc. Additionally or alternatively, if the insertion depth does not exceed the insertion threshold, the housing inspection system may output an error indication (e.g., an on-screen error message, an indicator light, haptic feedback, an error sound, etc.).

[0068] The insertion threshold may take any suitable form and have any suitable value depending on the implementation. In some examples, the insertion threshold corresponds to a retention depth at which a retention feature within a cable cavity engages and resists removal of a cable wire from the cable cavity. Thus, in some examples, the insertion threshold may be determined by the type of retention feature used and the location of the retention feature within the cable cavity.

[0069] In some examples, the housing inspection system may be configured to perform a monitoring accuracy assessment process, which may be used to assess the accuracy with which the camera system estimates the insertion depth of the cable wires and / or estimate the amount of cable cavity "play" (e.g., the ability of the cable wires to move within the cable cavity after being held by the retention mechanism). In some examples, this information may be used to determine an insertion threshold.

[0070] An exemplary monitoring accuracy evaluation process is illustrated generally with respect to Figures 6A-6C and 7. Figure 6A illustrates a scenario in which a cable wire 600 including cable contacts 602 is in the process of being inserted into a cable cavity 604 of a connector housing. With respect to Figures 6A-6C, the cable wire is referred to as an "evaluation" cable wire because it is being used to evaluate the monitoring accuracy of the housing inspection system. It will be understood that in practice there need not be a distinction between the cable wire and the "evaluation" cable wire.

[0071] In FIG. 6A , the evaluation cable wire has not yet been inserted far enough into the cable cavity to engage the retention feature 606. In this simplified example, the retention feature includes a pair of clips that allow the cable contacts to move forward within the cable cavity but, once engaged, resist removal of the cable wire. It will be appreciated that the retention feature may take any suitable form. While FIGS. 6A-6C focus on the insertion of one particular evaluation cable wire into one cable cavity of a connector housing, the evaluation process may be performed for each cable wire of multiple cable wires and corresponding multiple cable cavities of the connector housing.

[0072] In FIG. 6B , the evaluation cable wire is inserted to a fully inserted position 608A within the cable cavity. This refers to a position where continued insertion of the cable wire is no longer possible, for example, due to the cable wire's geometry and the prevention of further insertion into the cable cavity. It will be understood that the "fully inserted position" may refer to any position inside or outside the cable cavity, depending on the implementation. For example, in another example, "fully inserted" may refer to a scenario where the cable wire is fully inserted through the connector housing such that all or part of the cable contacts appear above the viewing surface of the connector housing. While in the fully inserted position, the housing inspection system may estimate the insertion depth of the evaluation cable wire.

[0073] In FIG. 6C , the cable wire is partially retracted to a partially retracted position 608B. The “partially retracted” position refers to a position within the cable cavity where a retention mechanism resists further removal of the cable wire from the cable cavity. As shown in FIG. 6C , retention mechanism 606 resists further removal of the cable wire from the cable cavity. During the monitoring accuracy evaluation process, a human operator and / or an automated process may insert each of the multiple evaluation cable wires into a fully inserted position and then retract each of the multiple evaluation cable wires to a partially retracted position. Once in the partially retracted position, the housing inspection system may again estimate the insertion depth of the evaluation cable wire. In this manner, for each evaluation cable wire inserted into the connector housing, an insertion depth corresponding to the fully inserted position and the partially retracted position may be estimated, respectively.

[0074] Based on these estimated insertion depth values, the housing inspection system may generate a full insertion depth distribution and a partial retraction depth distribution for each of the multiple cable wires. This is illustrated with reference to FIG. 7, which shows a full insertion depth distribution 700A reflecting estimated insertion depths for multiple different evaluation cable wires relative to their fully inserted positions. A partial retraction depth distribution 700B reflects estimated insertion depths for the evaluation cable wires relative to their partially retracted positions. The monitoring accuracy of the housing inspection system may be evaluated by comparing the full insertion depth distribution with the partial retraction depth distribution. For example, if there is a relatively large separation between the full insertion depth distribution and the partial retraction depth distribution, this may indicate relatively high monitoring accuracy of the housing inspection system and / or relatively high retention mechanism play within each cable cavity. If there is a relatively large overlap between the two distributions, this may indicate low monitoring accuracy and / or low retention mechanism play.

[0075] In some examples, a comparison of the full insertion depth distribution and the partial retraction depth distribution may be used to determine the insertion threshold. In the example of Figure 7, the insertion threshold 702 is defined as the midpoint between the two distributions 700A and 700B. It will be appreciated that in other examples, the insertion threshold may have another suitable relationship with respect to the full insertion depth distribution and / or the partial retraction depth distribution.

[0076] The methods and processes described herein may be coupled to a computer system of one or more computing devices. In particular, such methods and processes may be implemented as an executable computer application program, a network-accessible computer service, an application programming interface (API), a library, or a combination of the above and / or other computing resources.

[0077] 8 illustrates a simplified representation of a computer system 800 configured to provide any of the computing functionality described herein. Computer system 800 may take the form of one or more network-accessible devices, personal computers, server computers, mobile computing devices, and / or other computing devices.

[0078] Computer system 800 includes a logic subsystem 802 and a storage subsystem 804. Computer system 800 may optionally include a display subsystem 806, an input subsystem 808, a communication subsystem 810, and / or other subsystems not shown in FIG.

[0079] The logical subsystem 802 includes one or more physical devices configured to execute instructions. For example, a logical subsystem may be configured to execute instructions that are part of one or more applications, services, or other logical constructs. A logical subsystem may include one or more hardware processors configured to execute software instructions. Additionally or alternatively, a logical subsystem may include one or more hardware or firmware devices configured to execute hardware or firmware instructions. The processors of a logical subsystem may be single-core or multi-core, and the instructions executed therein may be configured for sequential, parallel, and / or distributed processing. Individual components of a logical subsystem may optionally be distributed among two or more separate devices, which may be remotely located and / or configured for collaborative processing. Aspects of a logical subsystem may be virtualized and executed by remotely accessible networked computing devices configured in a cloud computing configuration.

[0080] The storage subsystem 804 includes one or more physical devices configured to temporarily and / or permanently hold computer information, such as data and instructions, executable by the logical subsystem. When the storage subsystem includes two or more devices, the devices may be located in the same location and / or remotely. The storage subsystem 804 may include volatile, non-volatile, dynamic, static, read / write, read-only, random access, sequential access, location-addressable, file-addressable, and / or content-addressable devices. The storage subsystem 804 may include removable and / or built-in devices. As the logical subsystem executes instructions, the state of the storage subsystem 804 may be transformed, for example, to hold different data.

[0081] Aspects of logic subsystem 802 and storage subsystem 804 may be integrated with one or more hardware logic components, which may include program specific and application specific integrated circuits (PASICs / ASICs), program specific and application specific standard products (PSSPs / ASSPs), systems on a chip (SOCs), complex programmable logic devices (CPLDs), and the like.

[0082] The logic subsystem and storage subsystem may cooperate to instantiate one or more logical machines. As used herein, the term "machine" is used collectively to refer to a combination of hardware, firmware, software, instructions, and / or any other components that cooperate to provide computer functionality. In other words, a "machine" is never an abstract idea but always has a tangible form. A machine may be instantiated by a single computing device, or a machine may include two or more subcomponents instantiated by two or more different computing devices. In some implementations, a machine includes local components (e.g., software applications executed by a computer processor) that cooperate with remote components (e.g., cloud computing services provided by a network of server computers). The software and / or other instructions that give a particular machine its functionality may optionally be stored as one or more unexecuted modules on one or more appropriate storage devices.

[0083] When included, the display subsystem 806 may be used to present a visual representation of the data maintained by the storage subsystem 804. This visual representation may take the form of a graphical user interface (GUI). The display subsystem 806 may include one or more display devices utilizing virtually any type of technology. In some implementations, the display subsystem may include one or more virtual, augmented, or mixed reality displays.

[0084] When included, the input subsystem 808 may comprise or interface with one or more input devices. The input devices may include sensor devices or user input devices. Examples of user input devices include a keyboard, a mouse, a touchscreen, or a game controller. In some embodiments, the input subsystem may comprise or interface with selected natural user input (NUI) components. Such components may be integrated or peripheral, and the translation and / or processing of input actions may be handled on-board or off-board. Exemplary NUI components may include microphones for speech and / or voice recognition; infrared, color, stereo, and / or depth cameras for machine vision and / or gesture recognition; and head trackers, eye trackers, accelerometers, and / or gyroscopes for motion detection and / or intent recognition.

[0085] When included, communications subsystem 810 may be configured to communicatively couple computer system 800 with one or more other computing devices. Communications subsystem 810 may include wired and / or wireless communications devices that support one or more different communications protocols. Communications subsystem may be configured for communication over personal, local, and / or wide area networks.

[0086] The present disclosure is presented by way of example with reference to the associated drawings. Components, process steps, and other elements that may be substantially the same in one or more of the figures are co-identified and described with minimal repetition. It should be noted, however, that co-identified elements may differ to some extent. It should further be noted that some figures are schematic and may not be drawn to scale. The scale, aspect ratio, and number of elements of the various figures shown in the figures may be intentionally distorted to better visualize certain features or relationships.

[0087] Additionally, the present disclosure includes configurations according to the following examples.

[0088] Example 1. A method for cable wire insertion monitoring, the method comprising: receiving an inspection image of a connector housing held in a housing retainer of a housing inspection system from a camera system; detecting insertion of cable wires into corresponding cable cavities of the connector housing via an insertion monitoring machine vision system; estimating insertion depths of the cable wires into corresponding cable cavities based at least in part on the inspection image; and outputting an indication of the insertion depths of the cable wires.

[0089] Example 2. The method of example 1, wherein outputting an indication of the insertion depth of the cable wire includes outputting confirmation that the insertion depth exceeds an insertion threshold.

[0090] Example 3. The method of example 2, wherein the corresponding cable cavity includes a retention feature, and the insertion threshold corresponds to a retention depth at which the retention feature engages and resists removal of the cable wire from the corresponding cable cavity.

[0091] Example 4. The method of example 1, wherein the camera system is a stereo camera system and the insertion depth of the cable wires is estimated through stereo triangulation.

[0092] Example 5. The method of Example 1, further including: performing a monitoring accuracy evaluation process for each evaluation cable wire of the plurality of evaluation cable wires and a corresponding plurality of cable cavities of the connector housing by estimating an insertion depth for each evaluation cable wire at a fully inserted position within the corresponding cable cavity and estimating an insertion depth for each evaluation cable wire at a partially retracted position within the corresponding cable cavity.

[0093] Example 6. The method of example 5, further comprising generating a full insertion depth distribution for each of the plurality of evaluation cable wires, generating a partial retraction depth distribution for each of the plurality of evaluation cable wires, and comparing the full insertion depth distribution to the partial retraction depth distribution to evaluate the monitoring accuracy of the housing inspection system.

[0094] Example 7. The method of Example 6, further comprising determining an insertion threshold based at least in part on the full insertion depth distribution and the partial retraction depth distribution.

[0095] Example 8. The method of example 1, further comprising: comparing the inspection image to a template connector image to confirm that the connector housing is the intended connector housing type.

[0096] Example 9. The method of example 8, further comprising generating a homography matrix that accounts for the rotation of the connector housing in the test image relative to the template connector image.

[0097] Example 10. The method of example 1, wherein the corresponding cable cavity of the connector housing extends from the insertion face of the connector housing to the viewing face of the connector housing, and the inspection image of the connector housing shows the viewing face.

[0098] Example 11. The method of example 10, wherein the housing inspection system further includes an illumination system that projects illumination light toward the observation surface of the connector housing.

[0099] Example 12. The method of Example 1, wherein the step of estimating the insertion depth of the cable wire includes the steps of: estimating a first position of an observation surface of the connector housing based on the inspection image; estimating a second position of a tip of the cable wire within the connector housing; and calculating the insertion depth based on the first position of the observation surface and the second position of the tip of the cable wire.

[0100] Example 13. A housing inspection system comprising a controller that receives an inspection image of a connector housing held in a housing retainer of the housing inspection system from a camera system, detects insertion of cable wires into corresponding cable cavities of the connector housing via an insertion monitoring machine vision system, estimates insertion depths of the cable wires into corresponding cable cavities based at least in part on the inspection image, and outputs an indication of the insertion depths of the cable wires.

[0101] Example 14. The housing inspection system of example 13, wherein outputting an indication of the insertion depth of the cable wire includes outputting confirmation that the insertion depth exceeds an insertion threshold.

[0102] Example 15. The housing inspection system of example 14, wherein the cable cavity includes a retention feature, and the insertion threshold corresponds to a retention depth at which the retention feature engages and resists removal of the cable wire from the cable cavity.

[0103] Example 16. The housing inspection system of example 13, wherein the camera system is a stereo camera system and the insertion depth of the cable wires is estimated through stereo triangulation.

[0104] Example 17. The housing inspection system of Example 13, wherein the controller is further configured to perform a monitoring accuracy evaluation process by, for each evaluation cable wire of the plurality of evaluation cable wires and a corresponding cable cavity of the plurality of cable cavities of the connector housing, estimating an insertion depth of the evaluation cable wire at a fully inserted position within the corresponding cable cavity and estimating an insertion depth of the evaluation cable wire at a partially retracted position.

[0105] Example 18. The housing inspection system of Example 17, wherein the controller is further configured to: generate a full insertion depth distribution for each of the plurality of evaluation cable wires; generate a partial retraction depth distribution for each of the plurality of evaluation cable wires; and compare the full insertion depth distribution to the partial retraction depth distribution to evaluate monitoring accuracy of the housing inspection system.

[0106] Example 19. The housing inspection system of example 18, wherein the controller is further configured to determine an insertion threshold based at least in part on the full insertion depth distribution and the partial retraction depth distribution.

[0107] Example 20. A method for cable wire insertion monitoring, the method including the steps of receiving an inspection image of a connector housing held in a housing retainer of a housing inspection system from a stereo camera system, detecting insertion of a cable wire into a cable cavity of the connector housing via an insertion monitoring machine vision system, estimating an insertion depth of the cable wire into the cable cavity via stereo triangulation based at least in part on the inspection image, and outputting a confirmation that the insertion depth exceeds an insertion threshold corresponding to a retention depth at which a retention mechanism of the cable cavity resists removal of the cable wire from the cable cavity.

[0108] It will be understood that the configurations and / or techniques described herein are exemplary in nature and are susceptible to many variations, and therefore, these specific embodiments or examples should not be considered in a limiting sense. The particular routines or methods described herein may represent one or more of any number of processing strategies. Thus, various operations shown and / or described may be performed in the sequence shown and / or described, in other sequences, in parallel, or omitted. Similarly, the order of the processes described above may be changed.

[0109] The subject matter of the present disclosure includes all novel and non-obvious combinations and subcombinations of the various processes, systems, and structures disclosed herein with other features, functions, operations, and / or properties, and all equivalents thereof. [Explanation of symbols]

[0110] 100 Cable Connector 102 Connector housing 104 Cable Cavity 106A 3 different cable wires 106A-C Cable Wire 108 Conductive cable contacts 200 ways 202, 204, 206, 208 Method steps 300 Housing Inspection System 302 connector housing 304 Cable Cavity 306 Housing Retainer 308 Controller 310 Cable Insertion Parameters 312 Camera System 314A Inspection image 314B Second inspection image 316A First Camera 316B Second Camera 318 Lighting System 320 Insertion surface 322 Observation surface 323 Estimated position 324 Cable Wire 400 Exemplary Controller 402 Insertion Monitoring Machine Vision System 404 Camera System 406 Inspection Images 408 Connector Housing Recognition System 410 Template Connector Image 412 Insertion Detection System 414 Insertion Depth Estimation System 416 Insertion depth display 418 Insertion Threshold 500 Example of inspection image 502 Template Connector Image 504A, 504B Image form 506A,506B Image format 508 Homography Matrix 600 Cable Wire 602 Cable contacts 604 Cable Cavity 606 Retention mechanism 608A Fully inserted position 608B Partially retracted position 700A Full Insertion Depth Distribution 700B Partial retreat depth distribution 702 Insertion Threshold 800 Computer Systems 802 Logical Subsystem 804 Memory Subsystem 806 Display Subsystem 808 Input Subsystem 810 Communication Subsystem

Claims

1. A method (200) for cable wire insertion monitoring, said method (200) comprising: receiving (202) an inspection image (314) from a camera system (312) of a connector housing (302) held in a housing retainer (306) of a housing inspection system (300); detecting (204) the insertion of cable wires (324) into corresponding cable cavities (304) of the connector housing (302) via an insertion monitoring machine vision system (402); estimating (206) an insertion depth of the cable wire (324) into the corresponding cable cavity (304) based at least in part on the inspection image (314); outputting (208) an indication of the insertion depth (416) of the cable wire (324); A method (200) comprising:

2. 2. The method (200) of claim 1, wherein outputting the indication of the insertion depth (416) of the cable wire (314) comprises outputting a confirmation that the insertion depth exceeds an insertion threshold (418).

3. 3. The method (200) of claim 2, wherein the corresponding cable cavity (304) includes a retention feature (606), and the insertion threshold (418) corresponds to a retention depth at which the retention feature (606) engages the cable wire (324) from the corresponding cable cavity (304) and resists removal of the cable wire (324).

4. 10. The method of claim 1, wherein the camera system is a stereo camera system and the insertion depth of the cable wire is estimated through stereo triangulation.

5. 10. The method of claim 1, further comprising: performing a monitoring accuracy evaluation process by estimating, for each evaluation cable wire of a plurality of evaluation cable wires and a corresponding plurality of cable cavities of the connector housing, an insertion depth for each evaluation cable wire at a fully inserted position within the corresponding cable cavity and an insertion depth for each evaluation cable wire at a partially retracted position within the corresponding cable cavity.

6. 6. The method (200) of claim 5, further comprising: generating a full insertion depth distribution (700A) for each of the plurality of evaluation cable wires (600); generating a partial retraction depth distribution (700B) for each of the plurality of evaluation cable wires (600); and comparing the full insertion depth distribution (700A) with the partial retraction depth distribution (700B) to evaluate monitoring accuracy of the housing inspection system (300).

7. 7. The method (200) of claim 6, further comprising determining an insertion threshold (702) based at least in part on the full insertion depth distribution (700A) and the partial retraction depth distribution (700B).

8. 10. The method of claim 1, further comprising comparing the inspection image to a template connector image to verify that the connector housing is the intended connector housing type.

9. 10. The method of claim 8, further comprising generating a homography matrix that accounts for a rotation of the connector housing in the inspection image relative to the template connector image.

10. 2. The method of claim 1, wherein the corresponding cable cavity of the connector housing extends from an insertion face of the connector housing to an observation face of the connector housing, and the inspection image of the connector housing shows the observation face.

11. 11. The method (200) of claim 10, wherein the housing inspection system (300) further comprises an illumination system (318) that projects illumination light toward the viewing surface (322) of the connector housing (302).

12. 2. The method (200) of claim 1, wherein estimating the insertion depth of the cable wire (324) comprises: estimating a first position of an observation surface (320) of the connector housing based on the inspection image (314); estimating a second position of a tip of the cable wire (324) within the connector housing (302); and calculating the insertion depth based on the first position of the observation surface (302) and the second position of the tip of the cable wire (324).

13. A housing inspection system (300), comprising: receiving an inspection image (314) of a connector housing (302) held in a housing retainer (306) of the housing inspection system (300) from a camera system (312); detecting insertion of cable wires (324) into corresponding cable cavities (304) of said connector housing (302) via an insertion monitoring machine vision system (402); estimating an insertion depth of the cable wire (324) into the corresponding cable cavity (304) based at least in part on the inspection image (314); outputting an indication of the insertion depth (416) of the cable wire (324); Controller (308) A housing inspection system (300) comprising:

14. 14. The housing inspection system (300) of claim 13, wherein outputting the indication of the insertion depth (416) of the cable wire (324) comprises outputting a confirmation that the insertion depth exceeds an insertion threshold (418).

15. 15. The housing inspection system (300) of claim 14, wherein the cable cavity (304) includes a retention feature (606), and the insertion threshold corresponds to a retention depth at which the retention feature (606) engages the cable wire (324) from the cable cavity (304) and resists removal of the cable wire (324).

16. 14. The housing inspection system (300) of claim 13, wherein the camera system (314) is a stereo camera system and the insertion depth of the cable wires (324) is estimated through stereo triangulation.

17. 14. The housing inspection system (300) of claim 13, wherein the controller (308) is further configured to perform a monitoring accuracy evaluation process by estimating, for each evaluation cable wire (600) of a plurality of evaluation cable wires (600) and the corresponding cable cavity (604) of the plurality of cable cavities of the connector housing (302), an insertion depth of the evaluation cable wire (600) at a fully inserted position (608A) within the corresponding cable cavity (604) and an insertion depth of the evaluation cable wire (600) at a partially retracted position (608B) within the corresponding cable cavity (604).

18. 18. The housing inspection system (300) of claim 17, wherein the controller (308) is further configured to: generate a full insertion depth distribution (700A) for each of the plurality of evaluation cable wires (600); generate a partial retraction depth distribution (700B) for each of the plurality of evaluation cable wires (600); and compare the full insertion depth distribution (700A) with the partial retraction depth distribution (700B) to evaluate monitoring accuracy of the housing inspection system (300).

19. 20. The housing inspection system (300) of claim 18, wherein the controller (308) is further configured to determine an insertion threshold (702) based at least in part on the full insertion depth distribution (700A) and the partial retraction depth distribution (700B).

20. A method (200) for cable wire insertion monitoring, said method (200) comprising: receiving (202) an inspection image (314) of a connector housing (302) held in a housing retainer (306) of a housing inspection system (300) from a stereo camera system (312); detecting (204) the insertion of cable wires (324) into corresponding cable cavities (304) of the connector housing (302) via an insertion monitoring machine vision system (402); estimating (206) the insertion depth of the cable wires (324) into the corresponding cable cavities (304) via stereo triangulation based at least in part on the inspection images (314); outputting (208) a confirmation that the insertion depth (416) exceeds an insertion threshold (418) corresponding to a retention depth at which a retention feature (606) of the corresponding cable cavity (304) resists removal of the cable wire (324) from the cable cavity (304); A method (200) comprising:

Images