Department of Electrical and Electronic Engineering, Yonsei University, Seoul 03722, Korea.
Department of Artificial Intelligence Convergence, Kwangju Women's University, Gwangju 62396, Korea.
Sensors (Basel). 2021 Nov 17;21(22):7640. doi: 10.3390/s21227640.
Multi-person pose estimation has been gaining considerable interest due to its use in several real-world applications, such as activity recognition, motion capture, and augmented reality. Although the improvement of the accuracy and speed of multi-person pose estimation techniques has been recently studied, limitations still exist in balancing these two aspects. In this paper, a novel knowledge distilled lightweight top-down pose network (KDLPN) is proposed that balances computational complexity and accuracy. For the first time in multi-person pose estimation, a network that reduces computational complexity by applying a "Pelee" structure and shuffles pixels in the dense upsampling convolution layer to reduce the number of channels is presented. Furthermore, to prevent performance degradation because of the reduced computational complexity, knowledge distillation is applied to establish the pose estimation network as a teacher network. The method performance is evaluated on the MSCOCO dataset. Experimental results demonstrate that our KDLPN network significantly reduces 95% of the parameters required by state-of-the-art methods with minimal performance degradation. Moreover, our method is compared with other pose estimation methods to substantiate the importance of computational complexity reduction and its effectiveness.
多人姿态估计由于在活动识别、运动捕捉和增强现实等多个实际应用中的应用而受到广泛关注。尽管最近已经研究了提高多人姿态估计技术的准确性和速度的方法，但在平衡这两个方面仍然存在局限性。在本文中，提出了一种新颖的知识蒸馏轻量化自上而下的姿态网络 (KDLPN)，可以平衡计算复杂度和准确性。在多人姿态估计中，首次提出了一种通过应用“Pelee”结构和在密集上采样卷积层中打乱像素来减少通道数量来降低计算复杂度的网络。此外，为了防止由于计算复杂度降低而导致性能下降，应用知识蒸馏将姿态估计网络建立为教师网络。该方法在 MSCOCO 数据集上进行了性能评估。实验结果表明，我们的 KDLPN 网络在显著减少 95%的参数的同时，性能下降最小。此外，我们的方法与其他姿态估计方法进行了比较，以证明计算复杂度降低的重要性及其有效性。
