In recent years, frequent traffic accidents have brought a lot of losses to the society. Traffic accidents caused by tired driving are increasing year by year. For large car drivers, fatigue driving is affecting their personal safety. Therefore, many scholars have conducted a lot of research on the detection of tired driving. This paper proposes an optimization algorithm of face target detection based on CNN. Combined with ResNet network, CNN object detection model is improved as the driver face detection architecture. Then, the open-source Data set WIDERFACE (Face Detection Data Setand Benchmark) is used to train the face target detection model. Compared with similar existing target detection algorithms, the proposed algorithm has higher recognition accuracy, simplified network structure and less computation.
|