US 11,688,182 B2
Lane violation detection using convolutional neural networks
Vaibhav Ghadiok, Mountain View, CA (US); Christopher Carson, Oakland, CA (US); and Bo Shen, Fremont, CA (US)
Assigned to Hayden AI Technologies, Inc., Oakland, CA (US)
Filed by Hayden Al Technologies, Inc., Oakland, CA (US)
Filed on Oct. 5, 2021, as Appl. No. 17/450,054.
Application 17/450,054 is a continuation of application No. 17/242,969, filed on Apr. 28, 2021, granted, now 11,164,014.
Claims priority of provisional application 63/111,290, filed on Nov. 9, 2020.
Prior Publication US 2022/0147745 A1, May 12, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06K 9/00 (2022.01); G06V 20/56 (2022.01); G06N 3/08 (2023.01); G06V 10/25 (2022.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06V 20/58 (2022.01)
CPC G06V 20/588 (2022.01) [G06N 3/08 (2013.01); G06V 10/25 (2022.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06V 20/58 (2022.01); G06V 2201/08 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A method for detecting a potential traffic violation, comprising:
bounding, using one or more processors of an edge device, a vehicle detected from one or more video frames of a video in a vehicle bounding box, wherein the video is captured by one or more video image sensors of the edge device, and wherein the vehicle is detected and bounded using a first convolutional neural network;
bounding, using the one or more processors of the edge device, a plurality of lanes of a roadway detected from the one or more video frames in a plurality of polygons, wherein the plurality of lanes are detected and bounded using multiple heads of a multi-headed second convolutional neural network separate from the first convolutional neural network, and wherein at least one of the polygons is a lane-of-interest (LOI) polygon bounding a LOI; and
detecting, using the one or more processors, a potential traffic violation based in part on an overlap of at least part of the vehicle bounding box and at least part of the LOI polygon.