摘要：【中文】本发明实施例涉及机器学习技术领域，公开了一种基于机器学习的手语翻译方法及翻译设备，该方法包括：控制深度摄像头拍摄初始影像；采用连续手势识别框架识别初始影像中听障人士的手语信息；采用算法匹配模型匹配得到手语信息对应的若干文字词组；将若干文字词组智能组合为文字语句；输出手语信息对应的文字语句。可见，将听障人士所做出的手语动作实时准确地翻译为文字信息，使普通人理解听障人士所做出手语的含义，方便了听障人士在社会上进行沟通交流。 【EN】The embodiment of the invention relates to the technical field of machine learning, and discloses a sign language translation method and translation equipment based on machine learning, wherein the method comprises the following steps: controlling a depth camera to shoot an initial image; recognizing sign language information of the hearing-impaired person in the initial image by adopting a continuous gesture recognition framework; matching by adopting an algorithm matching model to obtain a plurality of character phrases corresponding to the sign language information; intelligently combining a plurality of character phrases into character sentences; and outputting the character sentence corresponding to the sign language information. Therefore, the sign language action made by the hearing-impaired person is accurately translated into the character information in real time, so that the ordinary people can understand the meaning of the sign language made by the hearing-impaired person, and the communication of the hearing-impaired person in the society is facilitated.

摘要：【中文】本发明公开了一种智能笔方法及装置，通过九轴传感器检测书写过程中智能笔的姿态，通过算法识别使用者写字姿势是否符合正确的书写姿势，包括书写过程中笔身的倾斜程度，握笔方向、手腕姿势等，当书写姿势错误时，通过声音报警，实时提醒使用者纠正书写姿势，还可把整个书写过程中智能笔的姿势数据保存上传给专用软件，进行图形、曲线的可视化显示，让使用者清晰的了解书写过程中的姿势变化过程，进行有针对性的错误姿势纠正。 【EN】The invention discloses an intelligent pen method and a device, wherein the posture of an intelligent pen in the writing process is detected through a nine-axis sensor, whether the writing posture of a user accords with the correct writing posture or not is identified through an algorithm, the algorithm comprises the inclination degree of a pen body, the pen holding direction, the wrist posture and the like in the writing process, when the writing posture is wrong, the user is reminded to correct the writing posture in real time through sound alarm, the posture data of the intelligent pen in the whole writing process can be stored and uploaded to special software, the visual display of graphs and curves is carried out, the user can clearly know the posture change process in the writing process, and the targeted wrong posture correction is carried out.

摘要：【中文】本发明实施例涉及虚拟现实技术领域，公开了一种可配置体感检测模块的体感检测方法及系统，该方法包括：监测是否接收到任一外部体感检测模块的植入指令；若接收到任一外部体感检测模块的植入指令，对外部体感检测模块进行供电；将外部体感检测模块添加至体感检测系统中，并将外部体感检测模块设为内部体感检测模块；根据若干内部体感检测模块检测到的空间坐标数据处理得到体感数据。可见，通过在体感检测的过程中实时地增减体感检测模块，使体感检测模块实现了可配置，从而体感检测设备在使用上更为便捷，具有较高的灵活性。 【EN】The embodiment of the invention relates to the technical field of virtual reality, and discloses a somatosensory detection method and a somatosensory detection system for a configurable somatosensory detection module, wherein the method comprises the following steps: monitoring whether an implantation instruction of any external somatosensory detection module is received; if an implantation instruction of any external somatosensory detection module is received, the external somatosensory detection module is powered; adding an external somatosensory detection module into the somatosensory detection system, and setting the external somatosensory detection module as an internal somatosensory detection module; and processing the space coordinate data detected by the internal body feeling detection modules to obtain body feeling data. Therefore, the somatosensory detection modules are increased or decreased in real time in the somatosensory detection process, so that the somatosensory detection modules can be configured, and the somatosensory detection equipment is more convenient and quick to use and has higher flexibility.

摘要：【中文】本发明公开了一种手势控制方法及设备，其中，所述的一种手势控制设备包括：九轴姿态检测模块、按键、蓝牙SOC中央处理模块、电源管理模块；利用所述手势控制设备捕捉识别手指姿态，结合设备按键状态，实现本发明手势控制方法的工作模式切换设置及各个工作模式中的手势功能，本发明操作简单、易学，可实现对智能终端设备上应用程序功能非接触式手势操作交互。 【EN】The invention discloses a gesture control method and device, wherein the gesture control device comprises the following steps: the system comprises a nine-axis attitude detection module, a key, a Bluetooth SOC central processing module and a power management module; the gesture control equipment is used for capturing and identifying the gesture of the finger, and the working mode switching setting and the gesture function in each working mode of the gesture control method are realized by combining the key state of the equipment.

摘要：【中文】本发明公开了一种运动轨迹记录方法与系统，本系统包括蓝牙SOC处理器S101、九轴运动检测模块S102、GPS/北斗双模卫星定位模块S103、电源模块S104和存储模块S105，所述模块S102、S103、S104、S105均与蓝牙SOC处理器S101连接，本发明采用九轴运动检测传感器惯性辅助定位与卫星定位相结合的方式实现运动轨迹记录，解决了智能穿戴设备中单一的卫星定位记录轨迹功耗高、可记录轨迹时间短的问题。 【EN】The invention discloses a motion trail recording method and a system, wherein the system comprises a Bluetooth SOC processor S101, a nine-axis motion detection module S102, a GPS/Beidou dual-mode satellite positioning module S103, a power supply module S104 and a storage module S105, wherein the modules S102, S103, S104 and S105 are all connected with the Bluetooth SOC processor S101, the motion trail recording is realized by adopting a mode of combining inertial auxiliary positioning and satellite positioning of a nine-axis motion detection sensor, and the problems of high power consumption and short track recording time of a single satellite positioning recording trail in intelligent wearable equipment are solved.

摘要：【中文】一种基于SLAM的计算机视觉大空间定位方法及系统，包括：拍摄模块拍摄用户视野范围内的场景影像，惯性测量模块检测用户姿态信息，传输模块将场景影像及用户姿态信息传输至服务器端，图像预处理模块处理得到场景坐标信息及用户躯干姿态，SLAM模块根据场景坐标信息及用户姿态信息构建即时地图，内容生成模块在即时地图中生成用户虚拟模型，得到虚拟现实大空间场景，传输模块将虚拟现实大空间场景传输至显示模块进行显示。可见，安装于用户终端的摄像头使得虚拟现实大空间方案的成本显著下降，且综合大空间中不同方位多用户所的拍摄视角，每一用户的动作姿态都被完整清晰地识别，用户的虚拟现实交互体验良好。 【EN】A computer vision large space positioning method and system based on SLAM includes: the system comprises a shooting module, an inertia measurement module, a transmission module, an image preprocessing module, an SLAM module, a content generation module, a display module and a content display module, wherein the shooting module shoots a scene image in a user visual field range, the inertia measurement module detects user posture information, the transmission module transmits the scene image and the user posture information to a server side, the image preprocessing module processes the scene coordinate information and the user trunk posture to obtain scene coordinate information, the SLAM module constructs an instant map according to the scene coordinate information and the user posture information, the content generation module generates a user virtual model in the instant map to obtain a virtual reality large-space scene, and the transmission. Therefore, the cost of the virtual reality large-space scheme is obviously reduced by the camera arranged on the user terminal, the shooting visual angles of multiple users in different directions in the large space are integrated, the action posture of each user is completely and clearly identified, and the virtual reality interaction experience of the user is good.

摘要：【中文】本发明涉及动作捕捉技术领域，公开了一种基于手持设备的动作捕捉方法及系统，该方法包括：同步拍摄高清彩色影像及深度影像，在高清彩色影像中选定动捕目标分析其目标特征；在深度影像中确定动捕目标的空间坐标，从而根据目标特征及空间坐标跟踪动捕目标，并进行跟踪拍摄得到动捕影像，处理动捕影像可得到动捕目标的骨骼动画。可见，无需依托于场地设备及专业人员，普通用户通过握持手持设备即可对动捕目标进行跟踪拍摄，完成动作捕捉，方案实施成本低，易用性强，便于面向大众进行推广应用。 【EN】The invention relates to the technical field of motion capture, and discloses a motion capture method and a motion capture system based on handheld equipment, wherein the method comprises the following steps: synchronously shooting a high-definition color image and a depth image, and selecting a dynamic capture target in the high-definition color image to analyze the target characteristics; and determining the space coordinates of the moving target in the depth image, tracking the moving target according to the target characteristics and the space coordinates, performing tracking shooting to obtain a moving image, and processing the moving image to obtain the skeleton animation of the moving target. Therefore, the ordinary user can track and shoot the moving target by holding the handheld device without depending on field equipment and professionals, motion capture is completed, the scheme is low in implementation cost and high in usability, and popularization and application to the public are facilitated.