| CPC G06V 10/7747 (2022.01) [G06V 10/26 (2022.01); G06V 10/764 (2022.01); G06V 10/776 (2022.01); G06V 10/82 (2022.01); G06V 20/64 (2022.01); G08B 21/02 (2013.01)] | 20 Claims |
|
1. A system for detecting an item of interest in a container, comprising:
at least one processor circuit; and
at least one memory that stores program code configured to be executed by the at least one processor circuit, the program code comprising:
a cropper configured to:
receive a first three-dimensional image depicting a container for storing items; and
segment the first three-dimensional image into a plurality of segmented windows;
a point sampler configured to:
sample a predetermined number of voxels from each of the plurality of segmented windows; and
provide the voxels sampled from each segmented window of the plurality of segmented windows as an input to a machine learning model that is configured to generate classifications for the provided voxels, each classification comprising a probability as to whether a respective voxel comprises at least a portion of the item of interest, the machine learning model being configured to output a final classification as to whether the first three-dimensional image comprises the item of interest based on the generated classifications; and
an alert generator configured to:
determine that the final classification meets a threshold condition; and
responsive to a determination that the final classification meets the threshold condition, generate an alert that indicates that the item of interest has been detected in the container.
|