Driving safety detection method based on cloud edge collaboration

The invention discloses a driving safety detection method based on cloud edge collaboration. The method comprises the steps that video data of a driver are collected and preprocessed; establishing a driving safety detection model and deploying the driving safety detection model to the edge device and the cloud server; respectively introducing an intermediate classifier between at least one group of adjacent network layers of each sub-model and training; performing multi-thread deployment by adopting a time slice round-robin scheduling algorithm to realize time slice distribution of each sub-model, and inputting the preprocessed data into each trained sub-model for concurrent reasoning; dynamically obtaining a segmentation point of each sub-model, segmenting the corresponding sub-model into an edge network and a cloud network, realizing data compression transmission, and recording an initial reasoning position of the cloud network; the cloud server starts reasoning according to the obtained ...