公开(公告)号：US10733890B2

公开(公告)日：2020-08-04

申请号：US16005898

申请日：2018-06-12

Applicant: NATIONAL CHUNG CHENG UNIVERSITY

Inventor： Ching-Chun Huang ,  Vu-Hoang Tran ,  Hung-Sheng Cheng

IPC: G08G1/14 ,  G06T7/00 ,  G06K9/00

Abstract: A method to be implemented by a computer system includes: transforming each of training images into a respective transformed training image; calculating a classification loss value based on detection results that are acquired from parking status prediction results obtained by performing feature extraction on the transformed training images; and adjusting candidate spatial transforming parameters, candidate feature extraction parameters and candidate logistic regression parameters when it is determined that a combination of the aforementioned parameters is not optimal based on the classification loss value, followed by repeating above-mentioned steps using the adjusted parameters.