The invention discloses a driving distraction detection method based on Yov7-Retina, and the method comprises the steps: constructing a driving distraction discrimination model, training the model, verifying the model, and monitoring the driving distraction in real time: detecting and processing a real-time video, inputting the real-time video data into the trained and verified driving distraction real-time discrimination model, and carrying out the real-time monitoring of the driving distraction. Counting the number of distracted frames and the total duration when the number of distracted frames continuously appears; and finally outputting a driving distraction judgment result. The method has the beneficial effects that by combining the Yolov7 model and the Retina model, the action and posture of the driver can be detected with high precision, and the driving behavior of the driver can be analyzed more accurately; on the basis of a lightweight network result, the detection efficiency is improved, and an algorithm can be deployed on a lightweight vehicle-mounted terminal; the change of the driving behavior of the driver can be found in time by processing and analyzing the behavior data in real time, and the driver can be reminded in time.
本发明公开了一种基于Yolov7‑Retina的驾驶分心检测方法,包括构建驾驶分心判别模型、模型训练、模型验证和驾驶分心实时监测,对实时视频进行检测并处理,将实时视频数据输入到训练验证后的驾驶分心实时判别模型,统计分心帧数及连续出现分心帧数的总时长;最终输出驾驶分心判别结果。有益效果:本发明通过结合Yolov7模型和Retina模型能够高精度地检测驾驶员的动作和姿态,更准确地分析其驾驶行为;能够基于轻量化网络结果,提高了检测效率,使得算法能于轻量化车载终端部署;通过实时处理和分析行为数据能够及时发现驾驶员的驾驶行为的变化,有助于及时对驾驶员进行提醒。
Driving distraction real-time detection method based on Yolov7-Retina
一种基于Yolov7-Retina的驾驶分心实时检测方法
2024-08-13
Patent
Electronic Resource
Chinese
IPC: | A61B DIAGNOSIS , Diagnostik / B60W CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION , Gemeinsame Steuerung oder Regelung von Fahrzeug-Unteraggregaten verschiedenen Typs oder verschiedener Funktion / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / G06V |
Lane changing behavior cognitive distraction detection method based on real-time driving
European Patent Office | 2024
|Real-Time Distraction Detection from Driving Data Based Personal Driving Model Using Deep Learning
Springer Verlag | 2022
|Real-time Vehicle Detection, Tracking and Counting System Based on YOLOv7
DataCite | 2023
|