Abstract
Most current gait recognition methods suffer from poor interpretability and high computational cost. To improve interpretability, we investigate gait features in the embedding space based on Koopman operator theory. The transition matrix in this space captures complex kinematic features of gait cycles, namely the Koopman operator. The diagonal elements of the operator matrix can represent the overall motion trend, providing a physically meaningful descriptor. To reduce the computational cost of our algorithm, we use a reversible autoencoder to reduce the model size and eliminate convolutional layers to compress its depth, resulting in fewer floating-point operations. Experimental results on multiple datasets show that our method reduces computational cost to 1% compared to state-of-the-art methods while achieving competitive recognition accuracy 98% on non-occlusion datasets.
Abstract (translated)
目前的步进识别方法通常存在 poor interpretability 和 high computational cost 的问题,为了改善 interpretability,我们基于 Koopman 操作理论研究了步进特征在嵌入空间中的表示。在这个空间中,过渡矩阵捕获了步进周期中的复杂运动特征,即 Koopman 操作。操作矩阵的对角元素可以表示整个运动趋势,提供了具有物理意义的描述符。为了降低算法的计算成本,我们使用可逆自编码器减少模型大小,消除卷积层以压缩深度,从而减少了浮点操作。多个数据集的实验结果显示,与我们最先进的方法相比,我们的算法将计算成本降低到 1% 以下,而在包含遮挡数据集上的竞争性识别准确率达到 98%。
URL
https://arxiv.org/abs/2309.14764
