Identifying overfilled containers

Patent metadata

Field	Value
Publication number	US-2024395006-A1
Application number	US-202418795833-A
Country	US
Kind code	A1
Filing date	Aug 6, 2024
Priority date	Apr 20, 2020
Publication date	Nov 28, 2024
Grant date	—

Abstract

Among other things, the techniques described herein include a method for receiving a plurality of images of one or more containers while the one or more containers are being emptied, the plurality of images comprising a training set of images and a validation set of images; labeling each image of the plurality of images as including either an overfilled container or a not-overfilled container; processing each image of the plurality of images to reduce bias of a machine learning model; training, and based on the labeling, the machine learning model using the plurality of images; and optimizing the machine learning model by performing learning against the validation set, the optimized machine learning model being used to generate a prediction for a new image of a container, the prediction indicating whether the container in the new image was overfilled prior to the new container being emptied.

First claim

1 - 14 . (canceled)

15 . A method comprising:
processing, by one or more processors, a plurality of images of one or more containers to extract a hue saturation value (HSV) for each of the plurality of images; dividing, by the one or more processors and based on the HSV for each of the plurality of images, the plurality of images into different sets of images within the plurality of images; after dividing the plurality of images into different sets of images, labeling, by the one or more processors, each image of the plurality of images as including either a container having a first visual characteristic or a container having a second visual characteristic; training, by the one or more processors and based on the labeling, a machine learning model using the plurality of labeled images; and generating, by the one or more processors using the trained machine learning model, a prediction for a new image of a container, the prediction indicating whether the container in the new image has the first visual characteristic or the second visual characteristic.

16 . The method of claim 15 , wherein the first visual characteristic and the second visual characteristic are each related to an appearance of a container lid.

17 . The method of claim 15 , wherein the first visual characteristic and the second visual characteristic are each related to a container shape.

18 . The method of claim 15 , wherein the first visual characteristic and the second visual characteristic are each related to a container fill level.

19 . The method of claim 15 , wherein the first visual characteristic and the second visual characteristic are each related to a container size.

20 . The method of claim 15 , wherein the first visual characteristic indicates a container being associated with a particular condition and the second visual characteristic indicates a container not being associated with the particular condition.

21 . The method of claim 20 , wherein the particular condition comprises at least one of an overfilled container condition, a required repair to the container, a container positioning condition, unusual activity related to servicing the container, or an obstruction blocking the container.

22 . The method of claim 15 , wherein the different sets of images comprise a first set with images obtained during day and a second set with images obtained during night.

23 . The method of claim 15 , wherein each of the different sets of images include images with different corresponding time-stamps, each time-stamp indicating a time when a respective image was obtained by a corresponding vehicle.

24 . The method of claim 15 , further comprising:
pre-processing, by the one or more processors, the plurality of images to determine geographic locations where the plurality of images were obtained; and wherein the labeling further comprises labeling the plurality of images according to the geographic locations.

25 . A method comprising:
processing, by one or more processors, a plurality of images to extract a hue saturation value (HSV) for each of the plurality of images, wherein the plurality of images correspond to detection of a triggering condition; dividing, by the one or more processors and based on the HSV for each of the plurality of images, the plurality of images into different sets of images within the plurality of images; after dividing the plurality of images into different sets of images, labeling, by the one or more processors, each image of the plurality of images as being associated with a particular condition or not associated with the particular condition, wherein the particular condition corresponds to one or more refuse-container characteristics; training, by the one or more processors and based on the labeling, a machine learning model using the plurality of labeled images; and generating, by the one or more processors using the trained machine learning model, a prediction for a new image, the prediction indicating that the new image includes a depiction of a refuse container.

26 . The method of claim 25 , wherein the images are captured by a camera of a vehicle.

27 . The method of claim 26 , wherein the triggering condition comprises a change in speed of the vehicle.

28 . The method of claim 26 , wherein the triggering condition comprises a change in position of a lift arm of the vehicle.

29 . The method of claim 26 , wherein the triggering condition comprises a location of the vehicle.

30 . The method of claim 25 , wherein the one or more refuse-container characteristics are related to an appearance of a refuse-container lid.

31 . The method of claim 25 , wherein the one or more refuse-container characteristics are related to a refuse-container shape.

32 . The method of claim 25 , wherein the one or more refuse-container characteristics are related to a refuse-container size.

33 . The method of claim 25 , wherein the different sets of images comprise a first set with images obtained during day and a second set with images obtained during night.

34 . The method of claim 25 , wherein each of the different sets of images include images with different corresponding time-stamps, each time-stamp indicating a time when a respective image was obtained by a corresponding vehicle.

Assignees

• Heil Co

Inventors

• Swaroop Prem
• Kamble Atish P
• Dev Bodhayan

Classifications

• G06V10/776

  Validation; Performance evaluation · CPC title

• G06V10/7747

  Organisation of the process, e.g. bagging or boosting · CPC title

• G06V10/764

  using classification, e.g. of video objects · CPC title

• G06F18/2148

  characterised by the process organisation or structure, e.g. boosting cascade · CPC title

• G06F18/217

  Validation; Performance evaluation; Active pattern learning techniques · CPC title