CPC G06T 7/74 (2017.01) [A01B 43/00 (2013.01); A01B 59/042 (2013.01); A01B 69/001 (2013.01); B64C 39/024 (2013.01); B64D 47/08 (2013.01); G05D 1/0038 (2013.01); G05D 1/101 (2013.01); G06F 18/211 (2023.01); G06F 18/214 (2023.01); G06F 18/217 (2023.01); G06F 18/2163 (2023.01); G06F 18/285 (2023.01); G06N 3/045 (2023.01); G06N 3/08 (2013.01); G06T 3/00 (2013.01); G06T 7/0002 (2013.01); G06T 7/13 (2017.01); G06T 7/60 (2013.01); G06T 7/62 (2017.01); G06T 7/70 (2017.01); G06T 7/73 (2017.01); G06V 10/255 (2022.01); G06V 20/10 (2022.01); G06V 20/188 (2022.01); G06V 20/38 (2022.01); G08G 5/0034 (2013.01); G08G 5/0069 (2013.01); B64U 2101/00 (2023.01); B64U 2101/30 (2023.01); B64U 2101/60 (2023.01); B64U 2201/20 (2023.01); G06T 2207/10032 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/20104 (2013.01); G06T 2207/30188 (2013.01); G06T 2207/30244 (2013.01)] | 20 Claims |
1. A method of executing, by a processor, computer instructions stored on a memory, the method comprising:
receiving a plurality of target images associated with a target set of conditions in which to detect objects;
generating object identification information based on an analysis of the plurality of target images using a first neural network trained on a first set of conditions and a second neural network trained on a second set of conditions;
selecting the first neural network as the preferred neural network in response to a first number of positive object identifications using the first neural network being higher than a second number of positive object identifications using the second neural network; and
selecting the second neural network as the preferred neural network in response to the second number of positive object identifications using the second neural network being higher than the first number of positive object identifications using the first neural network.
|