US 12,450,769 B2
Object detection system and object detection assistant system
Wen-Ting Wang, Taipei (TW); and Yu-Hung Tseng, Taipei (TW)
Assigned to PEGATRON CORPORATION, Taipei (TW)
Filed by PEGATRON CORPORATION, Taipei (TW)
Filed on Apr. 27, 2023, as Appl. No. 18/308,057.
Claims priority of application No. 111125826 (TW), filed on Jul. 8, 2022.
Prior Publication US 2024/0013430 A1, Jan. 11, 2024
Int. Cl. G06K 9/00 (2022.01); G06T 7/11 (2017.01); G06T 7/13 (2017.01); G06T 7/60 (2017.01); G06T 7/70 (2017.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01)
CPC G06T 7/70 (2017.01) [G06T 7/11 (2017.01); G06T 7/13 (2017.01); G06T 7/60 (2013.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06V 2201/07 (2022.01)] 10 Claims
OG exemplary drawing
 
6. An object detection system, comprising:
a memory, storing commands; and
a processor, coupling to the memory, and accessing and executing the commands of the memory, the commands comprising:
performing, via an object detection neural network, object detection on an image to output a detection result parameter to an assistant neural network, the detection result parameter comprising object information and first confidence;
processing, via the assistant neural network, the detection result parameter to output a first correction coefficient;
inputting the first correction coefficient and the detection result parameter to a Bayesian classifier to output a second correction coefficient; and
obtaining second confidence according to the first confidence and the second correction coefficient and updating the first confidence of the detection result parameter to the second confidence.