A 3d feature is extracted from the accumulation and main motion orientation, and a Bayesian classifier is used for smoke detection.

根据累积量和主运动方向提取出3维特征矢量，采用贝叶斯分类器进行烟雾的检测。

youdao

In order to accelerate detection speed, video images are divided into blocks. Each block motion orientation is estimated by block matching methods.

为了加快检测速度，将视频图像分割成大小相等的块，并估计每个块的运动方向。

youdao

And a time sequence of motion orientation for each block is generated over a sliding time window. Then accumulation and main motion orientation are computed according to the sequence.

采用滑动时间窗口生成块运动方向时间序列，在此时间序列的基础上计算块的累积量和主运动方向。

youdao

And a time sequence of motion orientation for each block is generated over a sliding time window. Then accumulation and main motion orientation are computed according to the sequence.

采用滑动时间窗口生成块运动方向时间序列，在此时间序列的基础上计算块的累积量和主运动方向。

youdao