Footsteps and inertial data-based road surface condition recognition method
Footsteps and inertial data-based road surface condition recognition method
复制标题
DOI：
10.1145/3365610.3365639
复制
发表时间：
2019-11
期刊：
影响因子：
--
通讯作者：
Hiroto Mitake;Hiroki Watanabe;M. Sugimoto
中科院分区：
文献类型：
--
作者：
Hiroto Mitake;Hiroki Watanabe;M. Sugimoto
我们提出了一种使用脚步和惯性数据识别路面状况的方法。在路面状况随季节、天气变化较大的地区，不良路况会引发跌倒等危险。如果能够提前确定路面状况，就可以通过选择安全路线和合适的鞋子来避免危险。在本研究中，我们重点关注根据路面条件（例如干燥路面、水坑、土壤和泥浆）而变化的脚步和惯性数据。我们实施了原型设备，并在 8 名参与者的六种路面条件下评估了所提出的方法。评估结果证实，低噪声环境下的识别准确率为83.0%。当存在噪声时，我们比较了结合脚步和惯性数据的标准方法和通过信噪比（SNR）改变脚步识别结果置信度的修订方法。评估结果还证实，使用修正后的方法，识别率最大提高了16.4%（信噪比为1 dB时，平均准确率从37.5%提高到53.9%）。
We propose a method to recognize road surface conditions using footsteps and inertial data. In areas where the road surface conditions change significantly with the seasons and weather, bad road conditions cause dangerous such as falls. If the road surface condition can be determined in advance, danger can be averted by selecting safe routes and suitable shoes. In this study, we focus on the footsteps and inertial data that change depending on road surface conditions, such as dry pavement, puddle, soil, and mud. We implemented the prototype device and evaluated the proposed method on six road surface conditions with eight participants. The evaluation results confirmed that the recognition accuracy was 83.0% in a low-noise environment. When there was noise, we compared the standard approach, which combines footsteps and inertial data, and the revised method, which changes the confidence of the result of footstep recognition by the signal-noise ratio (SNR). The evaluation results also confirmed that the recognition rate increased by a maximum of 16.4% using the revised method (when the SNR was 1 dB, the average accuracy was improved from 37.5% to 53.9%).