The invention provides a traffic police gesture recognition method based on cloud communication and a support vector machine. The traffic police gesture recognition method comprises the following specific steps of: Step 1, collecting traffic police gesture data; Step 2, establishing an SVM recognition model of traffic police gestures; Step 3, carrying out optimization training by adopting a GA algorithm to obtain an optimal traffic police gesture recognition model; and Step 4, testing the optimal traffic police gesture recognition model based on an optimal multi-dimensional force sensor decoupling model. According to the traffic police gesture recognition method, wearable intelligent interaction equipment collects data of a traffic police intelligent coat sensor, the data is collected by acamera holder and is transmitted to a vehicle-mounted system through cloud communication, a recognition system is designed to optimize an SVM traffic police gesture recognition algorithm based on a genetic algorithm (GA), initialization is carried out by using a group of random solutions, the optimal solution is searched by updating the algebra, and the traffic police gesture recognition method has powerful global search capability in minimization and neural network design, so that the vehicle can obtain accurate traffic police gestures online in real time without being influenced by weatherand air definition, and the traffic police gesture recognition method has high traffic police gesture recognition precision and system robustness.

    本发明提出了一种基于云端通讯和支持向量机的交警手势识别方法,具体步骤如下:Step1:采集交警手势数据;Step2:搭建交警手势的SVM识别模型;Step3:GA算法优化训练获得最优交警手势识别模型;Step4:基于最优多维力传感器解耦模型测试。本发明可穿戴智能交互设备采集交警智能上衣传感器的数据,经云台收集经云端通讯传输到车载系统,识别系统设计基于遗传算法(GA)优化SVM交警手势识别算法,使用一组随机解决方案进行初始化,并通过更新代数搜索最优解,在最小化和神经网络设计中具有很强的全局搜索能力,使得车辆可以在线实时获得准确的交警手势,而不受天气、空气清晰度的影响,具有较高的交警手势识别精度和系统鲁棒性。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Traffic police gesture recognition method based on cloud communication and support vector machine


    Weitere Titelangaben:

    一种基于云端通讯和支持向量机的交警手势识别方法


    Beteiligte:
    YANG ZHONG (Autor:in) / SONG AIGUO (Autor:in) / XU BAOGUO (Autor:in) / TIAN XIAOMIN (Autor:in) / YU ZHENZHONG (Autor:in)

    Erscheinungsdatum :

    2020-07-07


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    IPC:    G06K Erkennen von Daten , RECOGNITION OF DATA / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS / H04L TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION , Übertragung digitaler Information, z.B. Telegrafieverkehr



    Traffic Police Gesture Recognition by Pose Graph Convolutional Networks

    Fang, Zhijie / Zhang, Wuqiang / Guo, Zijie et al. | IEEE | 2020



    TRAFFIC DIRECTION GESTURE RECOGNITION

    SIVARAMAN SAYANAN V | Europäisches Patentamt | 2018

    Freier Zugriff

    TRAFFIC DIRECTION GESTURE RECOGNITION

    SIVARAMAN SAYANAN V | Europäisches Patentamt | 2018

    Freier Zugriff

    Traffic direction gesture recognition

    SIVARAMAN SAYANAN V | Europäisches Patentamt | 2021

    Freier Zugriff