Seat belt detection using gated Bi-LSTM with part-to-whole attention on diagonally sampled patches

Xinyu Gu, Zheng Lu, Jianfeng Ren, Qian Zhang

Abstract: Highlights•Novel seat belt detection framework exploiting inherent properties of seat belts.•Patch Diagonal Sampling obtains patches to capture fine-grained seat belt details.•Part-to-whole Attention exploits attentive patch information under global context.•Gated Bi-LSTM captures interactions among patches to aggregate all information.•The framework greatly outperforms SoTA methods on the large, constructed dataset.