-
公开(公告)号:US20240013430A1
公开(公告)日:2024-01-11
申请号:US18308057
申请日:2023-04-27
Applicant: PEGATRON CORPORATION
Inventor: Wen-Ting WANG , Yu-Hung TSENG
CPC classification number: G06T7/70 , G06T7/11 , G06T7/13 , G06T7/60 , G06V10/764 , G06V10/82 , G06V2201/07
Abstract: An object detection assistant system includes a memory and a processor. The processor is coupled to the memory. The memory stores one or more commands. The processor accesses and executes one or more commands of the memory. One or more commands include inputting a detection result parameter output by an object detection neural network for object detection of an image to an assistant neural network to output a first correction coefficient after processing by the assistant neural network, where the detection result parameter includes object information and a first confidence; inputting the first correction coefficient and detection result parameters to a Bayesian classifier to output a second correction coefficient; and adjusting the first confidence according to the second correction coefficient to obtain second confidence, and the second confidence being taken as the first confidence of the adjusted detection result parameter.