This study is supported by the National Nature Science Foundation of China (No.62071213), Special Project in key Areas of Artificial Intelligence in Guangdong Universities (No.2019KZDZX1017), Guangdong Basic and Applied Basic Research Foundation (No. 2019A1515010716), and open fund of Guangdong Key Laboratory of digital signal and image processing technology (2019GDDSIPL-03, 2020GDDSIPL-03).