Methods and Systems for Automated Machine Vision Monitoring of Vehicle Seats
Methods and systems for monitoring and analyzing vehicle seats, vehicle seat installation, and/or vehicle seat operation. The systems and methods may include (1) obtaining, by one or more processors, image data of a vehicle seat located within a vehicle, wherein the image data may include one or more connecting points of the vehicle seat to the vehicle; (2) inputting, by the one or more processors, the image data into a machine vision model that is trained: (a) using historical image data of vehicle seats within vehicles, (b) to learn a relationship between extracted features of the historical image data and a properness of an installation of a vehicle seat, and/or (c) to output a determination of a properness of an installation of a vehicle seat in response to detecting input image data; and/or (3) presenting, by the one or more processors, an indication of the output of the machine vision model.
1 . A computer-implemented method comprising:
obtaining, by one or more processors, image data of a vehicle seat located within a vehicle, wherein the image data includes one or more connecting points of the vehicle seat to the vehicle;
inputting, by the one or more processors, the image data into a machine vision model, wherein the machine vision model is trained:
a) using historical image data of vehicle seats within vehicles, wherein the historical image data is labeled to indicate whether a depicted vehicle seat is properly installed,
b) to learn a relationship between extracted features of the historical image data and a properness of an installation of a vehicle seat, and
c) to output a determination of a properness of an installation of a vehicle seat in response to detecting input image data; and
presenting, by the one or more processors, an indication of the output of the machine vision model.
2 . The computer-implemented method of claim 1 , wherein the image data includes two or more images depicting the one or more connecting points from different orientations.
3 . The computer-implemented method of claim 1 , wherein the output of the machine vision model includes a confidence in a labeling decision.
4 . The computer-implemented method of claim 3 , further comprising:
determining, via the one or more processors, that the confidence in the labeling decision is below a threshold value; and
presenting, via the one or more processors, the image data to a reviewer to obtain a review decision of whether the vehicle seat is properly installed within the vehicle.
5 . The computer-implemented method of claim 4 , further comprising:
comparing, by the one or more processors, the review decision to the labeling decision of the machine vision model; and
retraining, by the one or more processors, the machine vision model based at least in part upon the comparison.
6 . The computer-implemented method of claim 1 , wherein:
the machine vision model includes an object identification model trained to identify a presence of a vehicle seat in the input image data; and
the output of the machine vision model includes an indication that no vehicle seat was detected when the object identification model does not detect the presence of a vehicle seat in the input image data.
7 . The computer-implemented method of claim 6 , wherein:
the object identification model is trained to identify a model of the vehicle seat detected in the input image data; and
the output of the machine vision model includes an indication of the vehicle model.
8 . The computer-implemented method of claim 7 , further comprising:
obtaining, by the one or more processors, installation instructions associated with the model of the vehicle seat; and
presenting, by the one or more processors, at least a portion of the installation instructions.
9 . The computer-implemented method of claim 1 , wherein the image data is captured by an image sensor communicatively coupled to the vehicle.
10 . The computer-implemented method of claim 1 , wherein the image data is captured by a mobile device of an individual associated with the vehicle.
11 . A computer system comprising:
one or more processors;
a non-transitory program memory coupled to the one or more processors and storing executable instructions that, when executed by the one or more processors, cause the computer system to:
obtain image data of a vehicle seat located within a vehicle, wherein the image data includes one or more connecting points of the vehicle seat to the vehicle;
input the image data into a machine vision model, wherein the machine vision model is trained:
a) using historical image data of vehicle seats within vehicles, wherein the historical image data is labeled to indicate whether a depicted vehicle seat is properly installed,
b) to learn a relationship between extracted features of the historical image data and a properness of an installation of a vehicle seat, and
c) to output a determination of a properness of an installation of a vehicle seat in response to detecting input image data; and
present an indication of the output of the machine vision model.
12 . The computer system of claim 11 , wherein the image data includes two or more images depicting the one or more connecting points from different orientations.
13 . The computer system of claim 11 , wherein the output of the machine vision model includes a confidence in a labeling decision.
14 . The computer system of claim 13 , wherein the executable instructions, when executed by the one or more processors, further cause the computer system to:
determine that the confidence in the labeling decision is below a threshold value; and
present the image data to a reviewer to obtain a review decision of whether the vehicle seat is properly installed within the vehicle.
15 . The computer system of claim 14 , wherein the executable instructions, when executed by the one or more processors, further cause the computer system to:
compare the review decision to the labeling decision of the machine vision model; and
retrain the machine vision model based at least in part upon the comparison.
16 . The computer system of claim 11 , wherein:
the machine vision model includes an object identification model trained to identify a presence of a vehicle seat in the input image data; and
the output of the machine vision model includes an indication that no vehicle seat was detected when the object identification model does not detect the presence of a vehicle seat in the input image data.
17 . The computer system of claim 16 , wherein:
the object identification model is trained to identify a model of the vehicle seat detected in the input image data; and
the output of the machine vision model includes an indication of the vehicle model.
18 . The computer system of claim 17 , wherein the executable instructions, when executed by the one or more processors, further cause the computer system to:
obtain installation instructions associated with the model of the vehicle seat; and
present at least a portion of the installation instructions.
19 . The computer system of claim 11 , wherein the image data is captured by an image sensor communicatively coupled to the vehicle.
20 . A tangible, non-transitory computer-readable medium storing executable instructions that, when executed by one or more processors of a computer system, cause the computer system to:
obtain image data of a vehicle seat located within a vehicle, wherein the image data includes one or more connecting points of the vehicle seat to the vehicle;
input the image data into a machine vision model, wherein the machine vision model is trained:
a) using historical image data of vehicle seats within vehicles, wherein the historical image data is labeled to indicate whether a depicted vehicle seat is properly installed,
b) to learn a relationship between extracted features of the historical image data and a properness of an installation of a vehicle seat, and
c) to output a determination of a properness of an installation of a vehicle seat in response to detecting input image data; and
present an indication of the output of the machine vision model.