基于深度图像和稀疏表示的作战指挥手势识别  

Command Gestures Recognition Algorithm Based on Depth Image and Sparse Representation

作　　者：沈先耿 刘晓阳 哈达 

机构地区：[1]武警警官学院信息工程系,四川成都610213 [2]武警警官学院信息管理中心,四川成都610213

出　　处：《军械工程学院学报》2017年第3期40-45,共6页Journal of Ordnance Engineering College

摘　　要：针对不同光线条件下的作战环境中,肉眼无法对作战指挥手势进行快速、准确识别的问题,提出了一种基于深度图像和稀疏表示的作战指挥手势识别算法.首先采用深度图像与彩色图像分割相结合的方法,对图像中的作战指挥手势进行精确分割,而后采用稀疏表示的方法对分割出的作战指挥手势进行分类识别.实验表明,该算法的运行速度较快、识别率较高、在不同光线条件下的鲁棒性较好,具有良好的识别性能.Combatants＇ naked eyes cannot quickly and precisely identify command gestures in operational environments with different light conditions. To solve this problem, the paper proposes a command gestures recognition algorithm which is based on depth image and sparse representation. Firstly, the algorithm splits the command gestures by the method of depth image and color image. And then the paper recognizes the segmented hand gestures by using the method of sparse representation. Experiments show that the algorithm has high recognition rate and fast speed. In addition, the algorithm has better robustness under the condition of different illumination. It has a good recognition performance.

关 键 词：作战指挥手势 稀疏表示 手势分割 深度图像 手势识别 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]