GEINet: View-invariant gait recognition using a convolutional neural network
GEINet: View-invariant gait recognition using a convolutional neural network
复制标题
DOI：
10.1109/icb.2016.7550060
复制
发表时间：
2016-06
期刊：
影响因子：
--
通讯作者：
Kohei Shiraga;Yasushi Makihara;D. Muramatsu;T. Echigo;Y. Yagi
中科院分区：
文献类型：
--
作者：
Kohei Shiraga;Yasushi Makihara;D. Muramatsu;T. Echigo;Y. Yagi
提出了一种基于卷积神经网络的步态识别方法。受CNN在图像识别任务中的巨大成功的启发，我们输入了最流行的基于图像的步态表示，即步态能量图像(GEI)，作为CNN设计的用于步态识别的GEINet的输入。更具体地说，GEINet由卷积、合并和归一化层的两个连续的三元组以及两个后续的完全连接的层组成，这两个层输出了一组与个别训练对象的相似性。我们使用OU-ISIR大型种群数据集进行了实验，验证了该方法在协作和非协作环境下的跨视点步态识别的有效性。因此，我们证实，所提出的方法显著优于最先进的方法，特别是在验证场景中。
This paper proposes a method of gait recognition using a convolutional neural network (CNN). Inspired by the great successes of CNNs in image recognition tasks, we feed in the most prevalent image-based gait representation, that is, the gait energy image (GEI), as an input to a CNN designed for gait recognition called GEINet. More specifically, GEINet is composed of two sequential triplets of convolution, pooling, and normalization layers, and two subsequent fully connected layers, which output a set of similarities to individual training subjects. We conducted experiments to demonstrate the effectiveness of the proposed method in terms of cross-view gait recognition in both cooperative and uncooperative settings using the OU-ISIR large population dataset. As a result, we confirmed that the proposed method significantly outperformed state-of-the-art approaches, in particular in verification scenarios.