ID 原文 译文
57958 通过车载单元的防篡改装置与可信中心协同完成车辆的身份匿名和消息的签名，进一步增强方案的安全性，同时减轻可信中心的负载;通过批量验证，提高车载网匿名认证效率. The security of the scheme is further enhanced and the load of the trusted center is reduced by collaborating between the tamper-proof device of the onboard unit and the trusted center，the efficiency of the anonymous authentication of the onboard network is improved by batch verification.
57959 安全性和效率分析结果表明，所提方案不仅满足匿名性、不可伪造性和不可否认性等安全特性，而且具有更好的时间复杂度和空间复杂度. Security and efficiencyanalysis show that the scheme not only satisfies the security characteristics of anonymity，unforgeabilityand non-repudiation，but also has better time complexity and space complexity.
57960 仿真结果显示，所提方案在有效性和可行性方面均取得了较好的效果 The simulation resultsshow that the scheme has certain advantages in both effectiveness and feasibility.
57961 针对提高快递包裹的分拣效率和识别准确率，提出了一种基于深度神经网络复杂场景下的机器人拣选方法. A robotic sorting method based on deep neural network in complex scene is proposed to improve the sorting efficiency and recognition accuracy of parcels. The sorting method consists of three mainparts.
57962 首先，提出一种改进的目标检测算法，通过将多层浅层特征图与最终的特征图进行融合，提取更加细节的特征，以提升识别的速度与精度; Firstly，the improved object detection algorithm is proposed. More detailed features are extractedby combining the multi-layer shallow layer with the final feature map to improve the speed and accuracy ofrecognition.
57963 其次，提出了一种基于关键点的级联卷积最优拣选位置检测网络模型，对包裹最优拣选位置进行实时预测估计; Then，an optimal grab position detection network based on cascading convolution of keypoints is proposed to realize real-time estimation of the optimal sorting position of the parcel.
57964 最后，结合目标包裹最优拣选框与场景的深度信息和基于三维信息的目标姿态估计算法实现机器人拣选，并通过实验验证了该方法的有效性. Finally，bycombining with the target capture optimal frame and the depth information of the scene，the robotic sorting operation can be completed by the target pose estimation algorithm based on the three-dimensional information，and the effectiveness of the method is verified by experiments.
57965 针对在几何处理领域有着广泛应用的三角形网格参数化问题，研究了基于重心映射的三角形网格参数化方法. The parameterization of triangle meshes has numerous applications in the field of geometry processing.
57966 利用 geometry-processing-js 类库中的半边数据结构，采用均匀拉普拉斯权重、拉普拉斯－贝尔特拉米权重和中值权重 3 种加权方案，实现了重心映射法，并根据三角形的形变量分析了参数化结果. Using the halfedge-based data structure provided by geometry-processing-js，this paper researches on the mesh parameterization and its implementation based on barycentric mapping，as well as threeweight sets applied in barycentric mapping，namely，the uniform Laplacian weights，the Laplace-Beltramiweights，and the mean value weights.
57967 结果表明，中值权重为重心映射法的最优加权方案. A comparison between the results of parameterization is givenbased on the distortion caused to the triangles，and a conclusion is given that the mean value weights provide the best weighting scheme for barycentric mapping.