利用惯性传感器和AdaBoost算法的步态识别方法

针对现有方法在步态识别方面存在的动作信号分割、传感器方向不一致和相似动作识别精度不高等缺点，提出一种基于惯性传感器和AdaBoost算法的步态动作识别方法。首先，基于尺度空间技术，提出了一种鲁棒的步态检测方法将信号分为动作样本，以此来应对动作速度或强度的剧烈变化；然后，应用定位补偿匹配算法纠正传感器的倾斜，从而解决了传感器方向不一致的问题；最后，为了提高识别精度，基于AdaBoost算法自适应选取动作特征，再进行判别分析完成识别。对5个相似步态动作类进行识别实验，结果表明提出的算法具有较高的准确性。

Gait recognition based on inertial sensor and AdaBoost algorithm

In view of the disadvantages of current methods in gait recognition, such as motion signal segmentation, inconsistent sensor orientation and similar recognition accuracy, a novel gait recognition method based on inertial sensor and AdaBoost algorithm is proposed. First of all, based on the scale-space technique, a robust gait detection method is proposed to classify the signal into motion samples in order to cope with the dramatic changes in motion speed or intensity. Then, the position compensation compensation algorithm is applied to correct the tilt of the sensor, so as to solve the problem that the sensor orientation is inconsistent. Finally, in order to improve the recognition accuracy, the motion characteristics are adaptively selected based on the AdaBoost algorithm, and then the discriminant analysis is performed to complete the recognition. Five similar gait motion recognition experiments are carried out, the results show that the proposed algorithm has high accuracy.