method: TencentOCR2023-03-28
Authors: Haoxi Li, Weida Chen, Huiwenshi, Sicong Liu, Fan Yang, Huiwen Shi, Lifu Wang, Qingxiang Lin,Huiwen Shi,Yuxin Wang,Mei Jiang, Jing Lv, Chunchao Guo, Hongfa Wang, Dapeng Tao, Wei Liu
Affiliation: TencentOCR
Description: We integrated the detection results of DBNet and Cascade MaskRCNN built with multiple Backbone architectures, combined with the Parseq English recognition model for recognition, and further improved the end-to-end tracking with OCSort. As a result, we obtained end-to-end tracking and trajectory recognition results.
roadtext_text2_3_v6.json