Abstract To overcome the influence of view variations, a restrictive triplet network (RTN) is proposed to solve the problem of cross-view gait recognition in this paper. This network comprises five shared convolutional layers. The restrictive triplet loss is adopted to optimize RTN based on the triplet-based sample groups. These gait samples are selected by a special strategy, so as to make RTN converges faster. The model optimized by this method is adopted to extract the view-invariant feature for cross-view gait recognition. Besides, two additional networks named BDN and TDN are proposed to compare with RTN, which match the adjacent features at different convolutional layers. Finally, extensive evaluations are conducted based on the CASIA-B, OU-ISIR and USF dataset. Experimental results indicate that RTN performs best. Besides, the state-of-the-art methods are selected to compare with RTN. Among them, RTN achieves the best recognition score, which reaches 94.62% under singe view angle and 91.68% under cross-view angle, respectively. The results demonstrate that RTN is robust against view variations, which shows the great potential of RTN for practical applications in the future.

中文翻译：

---

基于限制性三元网络的跨视图步态识别

摘要 为了克服视图变化的影响，本文提出了一种限制性三元组网络（RTN）来解决跨视图步态识别问题。该网络包含五个共享的卷积层。采用限制性三元组损失来优化基于三元组的样本组的 RTN。这些步态样本是通​​过特殊策略选择的，从而使 RTN 收敛更快。采用该方法优化的模型提取视图不变特征用于跨视图步态识别。此外，还提出了两个名为 BDN 和 TDN 的附加网络与 RTN 进行比较，它们匹配不同卷积层的相邻特征。最后，基于 CASIA-B、OU-ISIR 和 USF 数据集进行了广泛的评估。实验结果表明 RTN 表现最好。除了，选择最先进的方法与 RTN 进行比较。其中，RTN取得了最好的识别分数，分别在单视角下达到了94.62%，在交叉视角下达到了91.68%。结果表明，RTN对视图变化具有鲁棒性，这表明RTN在未来的实际应用中具有巨大的潜力。