US 12,006,141 B2
Systems and methods for detecting waste receptacles using convolutional neural networks
Justin Szoke-Sieswerda, London (CA); Kenneth Alexander McIsaac, St. Mary's (CA); and Leo Van Kampen, Conestogo (CA)
Assigned to McNeilus Truck and Manufacturing, Inc., Dodge Center, MN (US)
Filed by McNeilus Truck and Manufacturing, Inc., Dodge Center, MN (US)
Filed on Oct. 25, 2022, as Appl. No. 17/973,411.
Application 17/973,411 is a continuation of application No. 16/758,834, granted, now 11,527,072, previously published as PCT/CA2018/051312, filed on Oct. 18, 2018.
Claims priority of provisional application 62/576,393, filed on Oct. 24, 2017.
Prior Publication US 2023/0046145 A1, Feb. 16, 2023
Int. Cl. G06V 20/56 (2022.01); B25J 9/16 (2006.01); B25J 19/02 (2006.01); B65F 3/04 (2006.01); G06F 18/241 (2023.01); G06N 3/04 (2023.01); G06N 3/08 (2023.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); B65F 3/02 (2006.01)
CPC B65F 3/04 (2013.01) [B25J 9/1697 (2013.01); B25J 19/023 (2013.01); B65F 3/041 (2013.01); G06F 18/241 (2023.01); G06N 3/04 (2013.01); G06N 3/08 (2013.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06V 20/56 (2022.01); B65F 2003/023 (2013.01); B65F 2210/138 (2013.01)] 23 Claims
OG exemplary drawing
 
1. A system for detecting a waste receptacle, comprising:
a camera configured to capture an image;
a convolutional neural network trained for identifying waste receptacles, the convolutional neural network comprising a plurality of depthwise separable convolution filters and a MobileNet architecture; and
one or more processors in communication with a waste-collection vehicle, the camera, and the convolutional neural network, the one or more processors configured to:
determine, based on use of the convolutional neural network, whether the image includes the waste receptacle; and
determine, based on whether the image includes the waste receptacle, an action.