摘要：【中文】本发明实施例公开了一种飞机机翼的形变监测装置，包括：柔性电容组件，直流电源和电流监控模块；柔性电容组件贴合于机翼蒙皮的内侧，柔性电容组件的一个电极连接到直流电源的一端，另一个电极通过电流监控模块连接到直流电源的另一端；电流监控模块，被配置为监测柔性电容组件，直流电源和电流监控模块形成的回路中产生的电流。本发明实施例实现了驾驶员随时了解机翼的变形情况，从而避免因过载过大产生有害的机翼变形或破坏的问题。 【EN】The embodiment of the invention discloses a deformation monitoring device of an airplane wing, which comprises: the flexible capacitor assembly, the direct current power supply and the current monitoring module; the flexible capacitor assembly is attached to the inner side of the wing skin, one electrode of the flexible capacitor assembly is connected to one end of the direct-current power supply, and the other electrode of the flexible capacitor assembly is connected to the other end of the direct-current power supply through the current monitoring module; and the current monitoring module is configured to monitor the current generated in a loop formed by the flexible capacitor assembly, the direct current power supply and the current monitoring module. The embodiment of the invention realizes that a driver can know the deformation condition of the wing at any time, thereby avoiding the problem of harmful wing deformation or damage caused by overlarge overload.

摘要：【中文】本发明实施例公开了一种柔性振动装置，包括：振动模块，用于固定振动模块的固定模块，以及供电模块；振动模块为柔性电容组件，该柔性电容组件的一个电极连接到供电模块的一端，另一个电极连接到供电模块的另一端；供电模块，被配置为给振动模块供电，使得振动模块产生振动。本发明实施例解决了现有用于产生震动的偏心装置，由于重量较大，而飞机对于重量有严格要求，而导致不适合在飞机中大范围使用的问题。 【EN】The embodiment of the invention discloses a flexible vibration device, which comprises: the vibration module, the fixing module used for fixing the vibration module, and the power supply module; the vibration module is a flexible capacitor assembly, one electrode of the flexible capacitor assembly is connected to one end of the power supply module, and the other electrode of the flexible capacitor assembly is connected to the other end of the power supply module; a power supply module configured to supply power to the vibration module such that the vibration module generates vibration. The embodiment of the invention solves the problem that the existing eccentric device for generating vibration is not suitable for being used in an airplane in a large range due to the fact that the weight of the existing eccentric device is large and the airplane has strict requirements on the weight.

摘要：【中文】本发明实施例公开了一种飞机壁板的3D打印方法和飞机壁板，包括：设置每块飞机壁板的支撑件数量；根据每块飞机壁板的支撑件数量，对每块飞机壁板中支撑件的位置分布进行配置；根据对每块飞机壁板配置的支撑件数量和位置，对每块飞机壁板进行3D打印，打印出具有支撑结构的飞机壁板。本发明实施例解决了现有技术打印出的飞机壁板模型或试验件表面具有凹坑，造成结构表面不平整，影响模型件的美观或试验件的试验效果等问题；同时还不会增加打印件的重量和模型的厚度，不会给飞机壁板运输和固定带来不便因素。 【EN】The embodiment of the invention discloses a 3D printing method of an aircraft wallboard and the aircraft wallboard, which comprises the following steps: setting the number of supporting pieces of each aircraft wall plate; according to the number of the supporting pieces of each aircraft wall plate, the position distribution of the supporting pieces in each aircraft wall plate is configured; and 3D printing is carried out on each aircraft wall plate according to the number and the positions of the supporting pieces configured for each aircraft wall plate, and the aircraft wall plate with the supporting structure is printed. The embodiment of the invention solves the problems that the surface of an airplane wallboard model or a test piece printed by the prior art is provided with pits, so that the structural surface is uneven, the attractiveness of the model piece or the test effect of the test piece is influenced, and the like; meanwhile, the weight of a printed part and the thickness of the model cannot be increased, and inconvenience factors cannot be brought to transportation and fixation of an aircraft wallboard.

摘要：【中文】本发明提供了一种手部关键点三维坐标识别方法及装置，获取目标手部框彩色图像，所述目标手部框彩色图像为经过手部检测后得到的彩色图像；将所述目标手部框彩色图像输入手部关键点三维坐标识别网络模型中进行处理，得到所述目标手部关键点的三维坐标。本发明实现了基于彩色数据的手部关键点三维坐标的识别。 【EN】The invention provides a method and a device for identifying three-dimensional coordinates of key points of a hand, which are used for acquiring a target hand frame color image, wherein the target hand frame color image is a color image obtained after hand detection; and inputting the target hand frame color image into a three-dimensional coordinate recognition network model of the hand key point for processing to obtain the three-dimensional coordinate of the target hand key point. The invention realizes the identification of the three-dimensional coordinates of the key points of the hand based on the color data.

摘要：【中文】本发明提供了一种数据标注方法及装置，首先获取已经进行了初始关节点标注的待处理图像，然后确定出所述待处理图像中的初始关节点代表的关节点信息，基于该关节点信息，调整待处理图像，从而可以正确识别出待处理图像中的关节点，进而获取准确的骨架节点位置，使得深度学习算法的训练数据更准确，进而使用训练数据进行深度学习训练得到的用于识别骨架姿态的模型的识别准确度提高。 【EN】The invention provides a data labeling method and a data labeling device, which are characterized in that firstly, an image to be processed with initial joint point labeling is obtained, then joint point information represented by the initial joint points in the image to be processed is determined, the image to be processed is adjusted based on the joint point information, so that the joint points in the image to be processed can be correctly identified, and then, accurate skeleton node positions are obtained, so that training data of a deep learning algorithm is more accurate, and the identification accuracy of a model for identifying skeleton postures obtained by deep learning training by using the training data is improved.

摘要：【中文】本申请提出一种深度图像目标分割方法及装置，该方法包括：根据上肢深度图像中的掌心位置，确定所述上肢深度图像中的手掌区域质心位置和手臂区域质心位置；根据所述手掌区域质心位置和所述手臂区域质心位置，确定手掌底部边缘；根据所述手掌底部边缘，确定手臂前端边缘，并确定所述手臂前端边缘的中点位置；根据所述手掌底部边缘的中点位置，以及所述手臂前端边缘的中点位置，确定手掌区域与手臂区域之间的边界位置；基于所述手掌区域与手臂区域之间的边界位置，从所述上肢深度图像中分割出手掌图像区域。上述技术方案能够从上肢深度图像中分割出手掌图像区域，即实现了手掌图像区域的准确分割。 【EN】The application provides a depth image target segmentation method and a device, and the method comprises the following steps: determining a palm area mass center position and an arm area mass center position in the upper limb depth image according to the palm center position in the upper limb depth image; determining the bottom edge of the palm according to the centroid position of the palm area and the centroid position of the arm area; determining the edge of the front end of an arm according to the bottom edge of the palm, and determining the midpoint position of the edge of the front end of the arm; determining a boundary position between a palm region and an arm region according to the midpoint position of the bottom edge of the palm and the midpoint position of the front edge of the arm; and segmenting a palm image area from the upper limb depth image based on the boundary position between the palm area and the arm area. According to the technical scheme, the palm image region can be segmented from the upper limb depth image, namely, the palm image region is accurately segmented.

摘要：【中文】本发明实施例公开了一种双梁机翼的机翼梁刚度配置方法，包括：建立前后梁板元模型，前后梁板元模型分别包括多个分块板元；根据已建立的前后梁板元模型，设置多组前后梁板元厚度区间组，每组前后梁板元厚度区间组包括前梁板元厚度区间和后梁板元厚度区间；对每组前后梁板元厚度区间组对应的前后梁板元模型施加载荷，并进行拓扑优化分析，得到前后梁分块板元的厚度分布结果。本发明实施例解决了现有机翼前后梁的刚度设计，由于需要经过多次轮迭代后确定机翼前后梁的刚度比，而导致整个过程设计效率低下，耗费大量的时间和人力的问题。 【EN】The embodiment of the invention discloses a method for configuring the stiffness of a wing beam of a double-beam wing, which comprises the following steps: establishing a front beam and rear beam plate element model, wherein the front beam and rear beam plate element model respectively comprises a plurality of block plate elements; according to the established front and rear beam plate element model, a plurality of groups of front and rear beam plate element thickness interval groups are arranged, and each group of front and rear beam plate element thickness interval group comprises a front beam plate element thickness interval and a rear beam plate element thickness interval; and applying load to the front and rear beam plate element models corresponding to each front and rear beam plate element thickness interval group, and performing topological optimization analysis to obtain the thickness distribution result of the front and rear beam block plate elements. The embodiment of the invention solves the problems of low design efficiency and large consumption of time and manpower in the whole process due to the fact that the rigidity ratio of the front and rear spars of the wing needs to be determined after multiple times of wheel iteration in the existing rigidity design of the front and rear spars of the wing.

摘要：【中文】本申请提出一种行人识别方法及装置，该方法包括：分别获取对应目标行人的彩色图像和深度图像；分别从所述彩色图像中提取得到彩色图像特征，以及从所述深度图像中提取得到深度图像特征；根据所述彩色图像特征和所述深度图像特征，从预设的图像数据库中筛选出与所述目标行人匹配的图像。上述处理过程从彩色图像特征和深度图像特征两种维度进行与目标行人相匹配的图像筛选，该筛选过程考虑的特征数量和种类更多，能够识别到更多的目标行人信息，将更加丰富的目标行人信息用于目标行人匹配的图像的筛选，能够克服单纯依靠彩色图像特征进行目标行人图像筛选的缺陷和不足，从而提升行人识别效果。 【EN】The application provides a pedestrian identification method and a device, and the method comprises the following steps: respectively acquiring a color image and a depth image of a corresponding target pedestrian; respectively extracting color image features from the color image and extracting depth image features from the depth image; and screening an image matched with the target pedestrian from a preset image database according to the color image characteristic and the depth image characteristic. The processing process carries out image screening matched with the target pedestrians from two dimensions of the color image features and the depth image features, the quantity and the types of the features considered in the screening process are more, more target pedestrian information can be identified, richer target pedestrian information is used for screening images matched with the target pedestrians, the defect that the image screening of the target pedestrians is carried out only by relying on the color image features can be overcome, and therefore the pedestrian identification effect is improved.

摘要：【中文】本发明公开了一种检测发光小球特征信息的方法及装置，该方法包括：获取与待检测图像相匹配的彩色图像和深度图像；获得与彩色图像对应的二值图；依据二值图，确定发光小球的轮廓区域；根据发光小球的轮廓区域确定的局部区域，获得发光小球位置的二值图；对发光小球位置的二值图进行边缘像素提取，并计算得到发光小球的圆心和半径；利用深度图像和发光小球的轮廓区域，计算得到发光小球的深度值；输出发光小球的特征信息，发光小球的特征信息包括发光小球的圆心、半径和深度值。因此，在本发明中实现了基于一套算法可以获得发光小球的多个特征信息，降低检测算法运算的复杂性及提升算法精度。 【EN】The invention discloses a method and a device for detecting characteristic information of a luminous ball, wherein the method comprises the following steps: acquiring a color image and a depth image which are matched with an image to be detected; obtaining a binary image corresponding to the color image; determining the outline area of the luminous small ball according to the binary image; obtaining a binary image of the position of the luminous small ball according to a local area determined by the outline area of the luminous small ball; extracting edge pixels of the binary image of the position of the light-emitting small ball, and calculating to obtain the circle center and the radius of the light-emitting small ball; calculating the depth value of the luminous small ball by using the depth image and the outline area of the luminous small ball; and outputting the characteristic information of the luminous small ball, wherein the characteristic information of the luminous small ball comprises the circle center, the radius and the depth value of the luminous small ball. Therefore, the invention realizes that a plurality of characteristic information of the luminous balls can be obtained based on a set of algorithm, reduces the complexity of detection algorithm operation and improves the algorithm precision.

摘要：【中文】本申请公开了一种深度图像去噪方法及装置，该方法包括：在获取到待去噪的目标深度图像后，将目标深度图像中的每一像素点作为待去噪点，然后获取目标深度图像中每一单位深度切片图像中存在的待去噪点数量，接着，判断待去噪点数量是否小于预设数量阈值，若小于预设数量阈值，则将待去噪点数量所属单位深度切片图像中所有待去噪点的像素置为0，若不小于预设数量阈值，则获取待去噪点数量所属单位深度切片图像中与相邻待去噪点的像素百分比不满足预设条件的待去噪点作为噪声点，并将噪声点的像素置为0。可见，本申请是从x‑y平面和z方向对深度图像进行全面去噪，充分考虑了噪声的各种表现特性，从而能够达到较好的去噪效果，提高去噪效果的质量。 【EN】The application discloses a depth image denoising method and device, wherein the method comprises the following steps: after a target depth image to be denoised is obtained, taking each pixel point in the target depth image as a to-be-denoised point, then obtaining the number of to-be-denoised points existing in each unit depth slice image in the target depth image, then judging whether the number of to-be-denoised points is smaller than a preset number threshold, if so, setting all the pixels of the to-be-denoised points in the unit depth slice image to which the number of to-be-denoised points belongs to be 0, and if not, obtaining the to-be-denoised points in the unit depth slice image to which the number of to-be-denoised points belongs and the percentage of the pixels of the adjacent to-be-denoised points to be not meet a preset condition as noise points, and setting the pixels of the noise points to be 0. Therefore, the depth image is subjected to comprehensive denoising from the x-y plane and the z direction, various performance characteristics of noise are fully considered, and therefore a good denoising effect can be achieved, and the quality of the denoising effect is improved.