YOLO9000模型的车辆多目标视频检测系统研究

提出了一种基于Darknet框架下YOLO9000算法的车辆多目标检测方法。该方法在YOLO9000算法基础下,根据训练结果和车辆目标特征对YOLO9000网络模型进行改进,并对其算法参数进行调整,获得更为适合于当前道路视频检测的YOLO9000-md网络模型下车辆多目标检测方法。为验证检测方法的有效性和完备性,对其模型进行了验证对比分析,同时对视频车辆进行了检测实验,实验结果表明,基于YOLO9000-md网络结构的车辆多目标检测方法,验证检测正确率达到了96.15%,具有一定的鲁棒性和通用性,为今后进行基于视频的更加智能化和自动化的数据分析提供了可靠的理论依据。

A Detection Method of Multi-target for Vehicles based on YOLO9000 Model

A multi-vehicle detection method was proposed, which consists of YOLO 9000 under Darknet framework. The YOLO9000 structure was improved according to the the training results and vehicle target characteristics, the algorithm parameters are adjusted. Finally, The YOLO9000-md network model was obtain, which is found more suitable for road vehicles detection. In order to verify the validity and completeness of this method, the model was verified and contrasted. At the same time, the vehicles under video was tested. The experimental results show that, the accuracy rate reaches 96.15% based on the YOLO9000-md model, which has certain robustness and versatility. It provides a reliable theoretical basis for more intelligent and automated data analysis based on video in the future.