SRHandNet: Real-Time 2D Hand Pose Estimation With Simultaneous Region Localization
SRHandNet: Real-Time 2D Hand Pose Estimation With Simultaneous Region Localization
复制标题
SRHandNet：具有同步区域定位功能的实时 2D 手势估计
DOI：
10.1109/tip.2019.2955280
复制
发表时间：
2019-11
影响因子：
10.6
通讯作者：
Peng Cong
中科院分区：
文献类型：
--
作者：
Wang Yangang;Zhang Baowen;Peng Cong
本文介绍了一种基于单目彩色图像进行实时2D手部姿态估计的新方法，称为SRHandNet。现有的方法不能及时有效地获得适当的结果，小手。我们的核心思想是同时回归的手感兴趣的区域（ROI）和手的关键点为一个给定的彩色图像，并迭代地采取手ROI作为反馈信息，以提高性能的手的关键点估计与一个单一的编码器-解码器网络架构。与以往的区域建议网络（RPN）不同，提出了一种新的轻量级包围盒表示方法--区域映射。提出的包围盒表示图与手部关键点热图一起被组合成统一的多通道特征图，其可以仅通过一个前向网络推理容易地获得，从而提高网络的运行效率。我们提出的SRHandNet可以在桌面环境下以40 fps的速度运行手部边界框检测和高达30 fps的准确手部关键点估计，而无需实现优化。实验证明了该方法的有效性。国家的最先进的结果也取得了竞争所有最近的方法。
This paper introduces a novel method for real-time 2D hand pose estimation from monocular color images, which is named as SRHandNet. Existing methods can not time efficiently obtain appropriate results for small hand. Our key idea is to simultaneously regress the hand region of interests (RoIs) and hand keypoints for a given color image, and iteratively take the hand RoIs as feedback information for boosting the performance of hand keypoints estimation with a single encoder-decoder network architecture. Different from previous region proposal network (RPN), a new lightweight bounding box representation, which is called region map, is proposed. The proposed bounding box representation map together with hand keypoints heatmaps are combined into the unified multi-channel feature maps, which can be easily acquired with only one forward network inference and thus improve the runtime efficiency of the network. Our proposed SRHandNet can run at 40fps for hand bounding box detection and up to 30fps accurate hand keypoints estimation under the desktop environment without implementation optimization. Experiments demonstrate the effectiveness of the proposed method. State-of-the-art results are also achieved out competing all recent methods.
登录
查看更多内容
影响因子：
22.7
作者：
Shotton, Jamie;Sharp, Toby;Moore, Richard
通讯作者：
Moore, Richard
DOI：
10.1109/tpami.2012.261
发表时间：
2013-12-01
影响因子：
23.6
作者：
Yang, Yi;Ramanan, Deva
通讯作者：
Ramanan, Deva
影响因子：
19.5
作者：
Russakovsky, Olga;Deng, Jia;Fei-Fei, Li
通讯作者：
Fei-Fei, Li
DOI：
10.1109/tpami.2016.2572683
发表时间：
2017-04-01
影响因子：
23.6
作者：
Shelhamer, Evan;Long, Jonathan;Darrell, Trevor
通讯作者：
Darrell, Trevor
DOI：
10.1007/978-3-030-01216-8_44
发表时间：
2018-03
期刊：
--
影响因子：
--
作者：
Lipeng Ke;Ming-Ching Chang;H. Qi;Siwei Lyu
通讯作者：
Lipeng Ke;Ming-Ching Chang;H. Qi;Siwei Lyu