Identifying overfilled containers

1. A method comprising:

receiving, by one or more processors, 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;

pre-processing, by the one or more processors, the plurality of images to extract hue saturation value (HSV) scale for the plurality of images;

dividing, by the one or more processors and based on the HSV scale, the plurality of images into different sets of images within the plurality of images;

labeling, by the one or more processors, [i] each image of the plurality of images according to the different sets, and [ii] each image of the plurality of images as including either an overfilled container or a not-overfilled container;

processing, by the one or more processors, each image of the plurality of images to reduce bias of a machine learning model;

training, by the one or more processors and based on the labeling, the machine learning model using the plurality of labeled images; and

optimizing, by the one or more processors, 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.

2. The method of claim 1 , further comprising:

performing, by the one or more processors and subsequent to the processing, object detection on each image of the plurality of images to identify a respective container within the plurality of images; and

cropping, by the one or more processors, each image of the plurality of images to extract a portion of the image with the respective identified container,

wherein the training of the machine learning model is performed using the images after the cropping has been performed.

3. The method of claim 1 , further comprising:

performing, by the one or more processors and subsequent to the processing, object detection on each image of the plurality of images to identify top 40-60% of a respective container within the plurality of images; and

cropping, by the one or more processors, each image of the plurality of images to extract a portion of the image with the top 40-60% of the respective identified container,

wherein the training of the machine learning model is performed using the images after the cropping has been performed.

4. The method of claim 1 , wherein the different sets of images comprise a first set with images obtained during day and a second set with images obtained during night.

5. The method of claim 1 , 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.

6. The method of claim 1 , 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; and

the training of the machine learning model is based on the labeled images.

7. The method of claim 1 , wherein:

while a particular container of the one or more containers is being emptied, a sequence of images among the plurality of images are obtained from one or more vehicles; and

the training is performed using the sequence of images.

8. The method of claim 7 , wherein the sequence of images is a video stream.

9. The method of claim 1 , further comprising:

performing, by the one or more processors, object detection on each image of the plurality of images to identify a respective container within the plurality of images; and

masking, by the one or more processors, other objects in the plurality of images,

wherein the training of the machine learning model is performed using the images after the masking has been performed.

10. The method of claim 1 , wherein the processing further comprises:

reducing, by the one or more processors, at least one of glare from headlights or brightness due to sunlight in each image of the plurality of images.

11. A non-transitory computer program product storing instructions that, when executed by at least one programmable processor, cause the at least one programmable processor to perform operations comprising:

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;

pre-processing the plurality of images to extract hue saturation value (HSV) scale for the plurality of images;

dividing, based on the HSV scale, the plurality of images into different sets of images within the plurality of images;

labeling [i] each image of the plurality of images according to the different sets, and [ii] 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, based on the labeling, the machine learning model using the plurality of labeled 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 container being emptied.

12. A system comprising:

at least one programmable processor; and

a machine-readable medium storing instructions that, when executed by the at least one processor, cause the at least one programmable processor to perform operations comprising:

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;

pre-processing the plurality of images to extract hue saturation value (HSV) scale for the plurality of images;

dividing, based on the HSV scale, the plurality of images into different sets of images within the plurality of images;

labeling [i] each image of the plurality of images according to the different sets, and [ii] 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, based on the labeling, the machine learning model using the plurality of labeled 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 image was overfilled prior to the container being emptied.

13. An article of manufacture comprising computer executable instructions stored on non-transitory computer readable media, which, when executed by a computer, causes the computer to perform operations comprising:

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;

pre-processing the plurality of images to extract hue saturation value (HSV) scale for the plurality of images;

dividing, based on the HSV scale, the plurality of images into different sets of images within the plurality of images;

labeling [i] each image of the plurality of images according to the different sets, and [ii] 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, based on the labeling, the machine learning model using the plurality of labeled 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.

14. The method of claim 1 , further comprising:

assigning each of the plurality of images to one of a plurality of classes, wherein each class of the plurality of classes is associated with a respective set of the different sets, wherein:

the labeling further comprises labeling the plurality of images according to the plurality of classes, and

the training of the machine learning model is based on the labeled images.

15. The non-transitory computer program product of claim 11 , wherein the operations further comprise:

assigning each of the plurality of images to one of a plurality of classes, wherein each class of the plurality of classes is associated with a respective set of the different sets, wherein:

the labeling further comprises labeling the plurality of images according to the plurality of classes, and

the training of the machine learning model is based on the labeled images.

16. The system of claim 12 , wherein the operations further comprise:

assigning each of the plurality of images to one of a plurality of classes, wherein each class of the plurality of classes is associated with a respective set of the different sets, wherein:

the labeling further comprises labeling the plurality of images according to the plurality of classes, and

the training of the machine learning model is based on the labeled images.

17. The article of manufacture of claim 13 , wherein the operations further comprise:

assigning each of the plurality of images to one of a plurality of classes, wherein each class of the plurality of classes is associated with a respective set of the different sets, wherein:

the labeling further comprises labeling the plurality of images according to the plurality of classes, and

the training of the machine learning model is based on the labeled images.