ID 原文 译文
40106 此外，基于深度学习的相关算法需要大量的计算量，在嵌入式平台上难以达到实时性。 In addition, computational cost of deep learning is too high to be realized on embedded platforms.
40107 因此，本文提出了一种新的轻量级多目标跟踪算法，以YOLOv3作为基础目标检测网络， Therefore, a new lightweight multiobjects tracking algorithm is proposed, which uses YOLOv3 as the basic object detection network.
40108 提出基于归一化层权重评价的层剪枝算法压缩检测网络计算量，以提高该算法在嵌入式平台上的运算速率。 A batch normalization layer weight evaluation based layer compression pruning algorithm is proposed to reduce the computational cost of the detection network such that the detection speed can be significantly improved on the embedded platform.
40109 同时，基于已有的跟踪结果，对当前帧检测结果进行校正，实现对漏检目标的补偿校正，用于提高检测的准确性。 Besides, according to the previous tracking results, the missing detection results can be corrected for the current frame, which improves the accuracy of the detection results.
40110 最后利用卷积神经网络来提取目标特征，融合目标特征及候选框与预测框间的交并补（Intersection-over-union，IoU），进行数据关联。 Furthermore, the convolutional neural network is employed to extract the object features. Object features and intersectionover-union(IoU)between the candidate frame and the prediction frame are combined for data association.
40111 实验结果表明，本文提出的轻量级多目标跟踪算法与已有的多目标跟踪算法相比取得了较好的跟踪结果， Experimental results show that the proposed lightweight multi-object tracking algorithm achieves a better result compared with others.
40112 且在仅损失较少精度的情况下保持较高的网络压缩率，适于嵌入式平台前端实现。 Especially, the network achieves a high compression rate with only slightly reducing the detection accuracy, which ensures the proposed network can be easily implemented on the embedded platform.
40113 鲁棒主成分分析（Robust principal component analysis，RPCA）模型中秩函数和L0范数的求解是非确定性多项式（Nondeterministic polynominal，NP）难问题，凸近似模型的求解通常会导致过收缩。 The robust principal component analysis(RPCA)model aims to estimate underlying low-rank and sparse structures from the degraded observation data. Both the rank function and the L0-norm minimization in the RPCA model are nondeterministic polynominal(NP）-hard problems, which usually are solved by the convex approximation model, so leading to the undesirable over-shrinkage problem.
40114 本文结合加权方法和Lp范数提出了一种基于双加权Lp范数的RPCA模型，利用加权Sp范数低秩项和加权Lp范数稀疏项分别对RPCA框架中的低秩恢复问题和稀疏恢复问题进行建模，使其更接近秩函数和L0范数最小化问题的解，提升了矩阵秩估计和稀疏估计的准确性。 This paper proposes a dual-weighted Lp-norm model based RPCA model by combining the weighting method and the Lp-norm. We use the weighted Sp-norm low-rank term and the weighted Lp-norm sparse term to model the low-rank and sparse recovery problems under the RPCA framework, respectively, which provides better approximations to the rank minimization and the L0-norm minimization, thus improving the accuracy of the rank estimation and the sparse estimation.
40115 为了验证模型性能，本文利用图像的非局部自相似性，结合相似图像块组的低秩性与椒盐噪声的稀疏性，将双加权Lp范数鲁棒主成分分析模型应用于去除椒盐噪声过程中。 To further demonstrate the performance of the proposed model, we apply the dual-weighted Lp-norm RPCA model to remove the salt-and-pepper noise by exploiting the image nonlocal self-similarity and combining the low rank of similar image patch matrices and the sparsity of salt-and-pepper noise.