Lightweight night infrared image pedestrian detection method and system based on model optimization

The invention discloses a lightweight night infrared image pedestrian detection method and system based on model optimization, and the method comprises the steps: obtaining a first infrared image data set; performing data rejection on the first infrared image data set according to a first data rejection method to obtain a second infrared image data set; performing attitude feature extraction on the second infrared image data set, and performing attitude expansion to obtain a third infrared image data set; constructing a first night infrared pedestrian detection model with a first backbone network and a first multi-scale fusion feature, taking the third infrared image data set as training data, inputting the first image information into the first night infrared pedestrian detection model, and obtaining a first pedestrian detection result; and carrying out pedestrian early warning on the vehicle driving process according to the first pedestrian detection result. The technical problems that in the prior art, a p