公开(公告)号：US20240144489A1

公开(公告)日：2024-05-02

申请号：US18480127

申请日：2023-10-03

申请人： VIETTEL GROUP

发明人： Hong Dang Nguyen ,  Thi Hanh Vu ,  Manh Quy Nguyen

IPC分类号： G06T7/246 ,  G06V10/82 ,  G06V20/40

CPC分类号： G06T7/248 ,  G06V10/82 ,  G06V20/46 ,  G06T2207/10016

摘要： A method for multi-object tracking from video. The method includes the following steps: (1) Capturing frames from the streaming source and preprocess the data; (2) Extract video features with three choices: a 3D-CNN backbone followed by a Transformer Encoder, a Video Transformer Encoder, a 2D-CNN Encoder with a stack of frames as input followed by a Transformer Encoder; (3) Multi-object tracking using a new end-to-end multi-task deep learning model named JDAT (Joint Detection Association Transformer), then post-processing and updating tracking state with Temporal Aggregation Module (TAM). The deep learning models in step 2 and step 3 are trained simultaneously end-to-end with a loss function that is accumulated over multiple timesteps (Collective Average Loss—CAL). Also, the model can be pretrained with weakly labeled image dataset in a self-supervised learning manner first, then finetuned on supervised video datasets with full tracking labels.

公开(公告)号：US20240144724A1

公开(公告)日：2024-05-02

申请号：US18476745

申请日：2023-09-28

申请人： VIETTEL GROUP

发明人： Hong Phuc Vu ,  Thi Hanh Vu ,  Hong Dang Nguyen ,  Manh Quy Nguyen

IPC分类号： G06V40/20 ,  G06T3/40 ,  G06T5/00 ,  G06T5/50 ,  G06V10/44 ,  G06V20/52

CPC分类号： G06V40/20 ,  G06T3/40 ,  G06T5/002 ,  G06T5/50 ,  G06V10/44 ,  G06V20/52 ,  G06T2207/20216

摘要： This invention proposes a method of crowd abnormal behavior detection from video using artificial intelligence, includes three steps: step 1: Data-preprocessing; step 2: Feature extraction and abnormal prediction using a three-dimensional convolution neural network (3D CNN), step 3: Post-processing and synthesizing information to issue warning.