摘要：【中文】本公开公开了融合图像块内和块间纹理规则特征的图像水印方法及系统，包括对分块后的待嵌入图像进行DCT变换，提取DCT系数，组成待嵌入向量；基于图像块内和块间的纹理规则特征，得到纹理规则度调制因子，以此构建JND模型，计算JND基本阈值得到感知松弛向量；将待嵌入向量和感知松弛向量映射到给定投影向量上，分别获得待嵌入投影向量和感知松弛投影向量，通过感知松弛投影向量和嵌入强度得到量化步长；将水印根据量化步长嵌入到待嵌入投影向量中，对DCT系数进行IDCT变换后得到嵌入水印后的图像。分别度量图像块内的纹理规则特征和图像块间的纹理规则特征，在保证图像的视觉质量的同时，提高水印算法的鲁棒性。 【EN】The invention discloses an image watermarking method and system fusing texture rule characteristics in image blocks and among the blocks, which comprises the steps of carrying out DCT transformation on a blocked image to be embedded, extracting DCT coefficients and forming a vector to be embedded; obtaining a texture regularity modulation factor based on texture rule features in image blocks and among blocks, constructing a JND model according to the texture regularity modulation factor, and calculating a JND basic threshold to obtain a perception relaxation vector; mapping the vector to be embedded and the perception relaxation vector to a given projection vector, respectively obtaining the projection vector to be embedded and the perception relaxation projection vector, and obtaining a quantization step length through the perception relaxation projection vector and the embedding strength; and embedding the watermark into the projection vector to be embedded according to the quantization step length, and performing IDCT (inverse discrete cosine transform) conversion on the DCT coefficient to obtain the image embedded with the watermark. Texture rule features in image blocks and texture rule features among the image blocks are measured respectively, and the robustness of a watermark algorithm is improved while the visual quality of the image is guaranteed.

摘要：【中文】本发明公开了一种基于相关矩阵和词向量模型的兴趣点推荐方法。本发明通过参考自然语言处理中训练词向量模型进行用户和兴趣点的向量表示建模，该模型可从用户的签入序列中捕获兴趣点的地理影响。假设一个兴趣点受用户签到序列中其他兴趣点的影响。将每个兴趣点视为“单词”，将每个用户的顺序签到序列视为“句子”，并结合使用自言语言处理中的Skip‑gram词向量模型来训练兴趣点以及用户的潜在表示向量。本发明分别从用户和兴趣点的角度进行融合成一个更好的地理信息模型。为此，在该模型中使用了用户和兴趣点之间的地理距离和用户在相邻兴趣点上的签到频次。通过考虑到相邻兴趣点在模型推荐策略中的影响，解决了签到数据稀疏问题。 【EN】The invention discloses an interest point recommendation method based on a correlation matrix and a word vector model. The invention carries out vector representation modeling of the user and the interest points by referring to a training word vector model in natural language processing, and the model can capture the geographical influence of the interest points from the sign-on sequence of the user. Suppose that one point of interest is affected by other points of interest in the user's check-in sequence. Consider each point of interest as a "word," consider each user's sequential check-in sequence as a "sentence," and train the points of interest and the user's potential representation vectors using the Skip-gram word vector model in self-speech processing in conjunction. The invention fuses the user and the interest point into a better geographic information model respectively. To this end, the geographic distance between the user and the point of interest and the check-in frequency of the user on neighboring points of interest are used in the model. By considering the influence of adjacent interest points in the model recommendation strategy, the check-in data sparsity problem is solved.

摘要：【中文】本发明公开了一种心脏瓣膜稳态泄漏试验装置及其使用方法，属于医疗器械检验技术领域，该试验装置包括蓄水桶和贮水桶，蓄水桶和贮水桶之间通过管路相连通，管路上设置有用于安装人工心脏瓣膜的试件工装，以使得所述人工心脏瓣膜与管路相连通；试件工装的前侧安装有前端压力传感器，试件工装的后侧安装有后端压力传感器，蓄水桶连接有气源，贮水桶设置有称量其内部液体质量变化的称重装置。其工作方法包括校准、安装试件和测量静态泄漏量。本发明示例的技术方案，用于进行人工心脏瓣膜的稳态泄漏试验，操作方便，符合标准要求，结果准确可靠。 【EN】The invention discloses a heart valve steady-state leakage test device and a use method thereof, belonging to the technical field of medical instrument inspection, wherein the test device comprises a water storage barrel and a water storage barrel, wherein the water storage barrel is communicated with the water storage barrel through a pipeline, and a test piece tool for installing a heart valve prosthesis is arranged on the pipeline so as to communicate the heart valve prosthesis with the pipeline; the front end pressure sensor is installed to the front side of test piece frock, and rear end pressure sensor is installed to the rear side of test piece frock, and the water storage bucket is connected with the air supply, and the water storage bucket is provided with the weighing device who weighs its inside liquid mass change. The working method comprises the steps of calibrating, installing a test piece and measuring the static leakage amount. The technical scheme of the invention is used for performing the steady-state leakage test of the artificial heart valve, is convenient to operate, meets the standard requirement, and has accurate and reliable results.

摘要：【中文】本发明公开了基于空频域JND转换的图像水印嵌入、提取方法及系统，获取原始图像，将原始图像划分为若干图像块，计算每个图像块中待嵌入水印的DC系数；对DC系数进行对数转换，得到对数转换后的数据；根据最优量化步长，对对数转换后的数据进行抖动调制嵌入水印信息；对抖动调制后的数据，进行对数域逆变换，得到更新后的嵌入水印的DC系数；根据更新后的嵌入水印的DC系数，计算DC系数的修改量；对频域JND模型进行修正，将修正后的频域JND模型进行频域‑空域转换，得到空域JND模型；根据空域JND模型引导像素修改量，对空域中的像素值进行更新，实现水印信息的嵌入。 【EN】The invention discloses an image watermark embedding and extracting method and system based on a spatial frequency domain JND conversion, which comprises the steps of obtaining an original image, dividing the original image into a plurality of image blocks, and calculating a DC coefficient of a watermark to be embedded in each image block; carrying out logarithmic conversion on the DC coefficient to obtain data after logarithmic conversion; carrying out jitter modulation on the data subjected to the logarithmic conversion according to the optimal quantization step length and embedding watermark information; carrying out inverse transformation of a logarithm domain on the data after jitter modulation to obtain an updated DC coefficient embedded with the watermark; calculating the modification quantity of the DC coefficient according to the updated DC coefficient embedded with the watermark; correcting the frequency domain JND model, and performing frequency domain-spatial domain conversion on the corrected frequency domain JND model to obtain a spatial domain JND model; and updating the pixel value in the space domain according to the spatial domain JND model guide pixel modifier to realize the embedding of the watermark information.

摘要：【中文】本发明公开了结合语义分割的多描述编码方法及系统，包括：将原始图像与相对应的语义分割标签作为输入传至多描述特征生成网络；多描述特征生成网络利用图像上下文特征生成相似但又不完全相同的两个描述；生成的两个描述分别进入语义分割编码网络中编码，在该编码器中，描述首先上采样成与原始图像大小一致的上采样图像，之后与语义分割映射一起经过生成网络生成残差图像，残差图像又与上采样图像像素相加得到粗重构图像；生成的粗重构图像经信息道传输至多描述解码网络，而语义分割标签被标准编码器编码之后也传输至多描述解码网络，经解码得到最终重构图像。避免了因为传输过程中丢包问题导致的图像重构质量不理想的后果，更好的提高了编码效率。 【EN】The invention discloses a multi-description coding method and a system combining semantic segmentation, which comprises the following steps: the original image and the corresponding semantic segmentation labels are used as input and transmitted to a multi-description feature generation network; the multi-description feature generation network generates two similar but not identical descriptions by using the image context features; the two generated descriptions respectively enter a semantic segmentation coding network for coding, in the coder, the descriptions are firstly up-sampled into an up-sampled image with the size consistent with that of an original image, then the up-sampled image and the semantic segmentation mapping are processed through the generation network to generate a residual image, and the residual image and the up-sampled image are added to obtain a coarse reconstruction image; the generated rough reconstruction image is transmitted to a multiple description decoding network through an information channel, the semantic segmentation label is also transmitted to the multiple description decoding network after being encoded by a standard encoder, and a final reconstruction image is obtained through decoding. The method avoids the result of non-ideal image reconstruction quality caused by the problem of packet loss in the transmission process, and better improves the coding efficiency.

摘要：【中文】本发明公开了一种自动驾驶功能的测试评价方法、装置及系统，其中，该方法包括：获取自动驾驶技术的被测功能；根据自动驾驶技术的被测功能确定被测功能的至少一个影响参数；根据影响参数确定被测功能的启用情况和禁用情况；分别获取被测功能在启用情况下的第一运行参数以及在禁用情况下的第二运行参数；根据第一运行参数确定被测功能在启用情况下的第一评价分数；根据第二运行参数确定被测功能在禁用情况下的第二评价分数；根据第一评价分数和第二评价分数得到被测功能的评价结果。解决了现有的自动驾驶功能评价内容较片面导致的自动驾驶系统在全工况下的运行危险系数高的问题，进一步确保了自动驾驶功能的运行安全。 【EN】The invention discloses a method, a device and a system for testing and evaluating an automatic driving function, wherein the method comprises the following steps: acquiring a tested function of an automatic driving technology; determining at least one influencing parameter of the measured function according to the measured function of the automatic driving technology; determining enabling conditions and disabling conditions of the function to be tested according to the influence parameters; respectively acquiring a first operating parameter of a tested function under the enabling condition and a second operating parameter under the disabling condition; determining a first evaluation score of the tested function under the starting condition according to the first operation parameter; determining a second evaluation score of the tested function under the forbidden condition according to the second operation parameter; and obtaining an evaluation result of the tested function according to the first evaluation score and the second evaluation score. The problem that the existing automatic driving function evaluation content is higher than that of the automatic driving system caused by one-sided operation risk coefficient under all working conditions is solved, and the operation safety of the automatic driving function is further ensured.

摘要：【中文】本申请提供了一种表面具有仿生熔覆层的犁刀，犁壁的基体的外表面上设置有仿生熔覆层，仿生熔覆层的外形根据土壤动物的体表的非光滑表面分别制备了凹坑型、凸包型、鳞片型或棱条型；还包括犁铧，犁铧的基体的外表面上设置有铁基熔覆层；还提供了一种表面具有仿生熔覆层的犁刀的制备方法，采用激光3D打印方法制备仿生熔覆层，采用同步式激光熔覆方法制备铁基熔覆层；犁壁表面的仿生熔覆层具有良好的抗冲蚀磨粒磨损性能，犁铧表面的铁基熔覆层具有良好的抗冲击磨粒磨损性能，从而极大地提高了该犁刀在犁耕时的耐磨性与耐腐蚀性能，使得该犁刀具有使用寿命长、摩擦系数小、耕作阻力小等优点。 【EN】The application provides a coulter with a bionic cladding layer on the surface, wherein the bionic cladding layer is arranged on the outer surface of a matrix of a plough wall, and the shape of the bionic cladding layer is respectively prepared into a pit type, a convex hull type, a flake type or a ridge type according to the non-smooth surface of the body surface of a soil animal; the outer surface of the base body of the ploughshare is provided with an iron-based cladding layer; the preparation method of the coulter with the bionic cladding layer on the surface is also provided, the bionic cladding layer is prepared by adopting a laser 3D printing method, and the iron-based cladding layer is prepared by adopting a synchronous laser cladding method; the bionic cladding layer on the surface of the plough wall has good erosion abrasive wear resistance, and the iron-based cladding layer on the surface of the plough share has good impact abrasive wear resistance, so that the wear resistance and corrosion resistance of the plough coulter during ploughing are greatly improved, and the plough coulter has the advantages of long service life, small friction coefficient, small tillage resistance and the like.