Most of the current inertial positioning systems can be categorized as the strapdown algorithm and the step-and-heading approach. However, for the strapdown algorithm using smartphone as a sensor device, the accuracy of the current MEMS based accelerometer are not enough for estimating relative movement. Also, for the step-and-heading approach, robust estimation of step length is always difficult. In this paper, we propose an end-to-end walking speed estimation method using Deep Learning to overcome these problems. By using our method, we can achieve a smartphone PDR with higher accuracy and better robustness to gait type.
Pedestrian Dead Reckoning(PDR) is one of the promising technology for
indoor localization. Most of the current PDR techniques can be categorized as the
strapdown algorithm and the step-and-heading algorithm [
In this paper, we propose an end-to-end walking speed estimation method for
smartphone PDR by using DualCNN-LSTM. By estimating pedestrian's
walking speed directly from accelerometer sensor data, we do not have to consider
about parameters such as step length, person's height nor type of gait. This
means we do not have to consider about user dependent information which
affects walking-speed parameters. To adapt machine learning algorithm for
end-toend speed estimation, we address two problems: 1) how we collect ground truth
data of pedestrian's speed and trajectory for training data, and 2) how we design
neural network for achieving high accuracy. To collect data for training, we
leverage Google Tango [
There are large amount of study which handles pedestrian localization systems
[
In addition, recent advancement of deep learning technology enables
end-toend machine learning on different domains [
Our long-term objective is to establish a method for end-to-end PDR which inputs accelerometer and gyro sensor data and outputs relative position movement. However, this paper focuses to estimate pedestrian's speed by end-to-end manner, and calculating trajectory with the speed and heading data. Thus, we propose speed-and-heading PDR algorithm. To best of our knowledge, recognizing heading can be achieved with high accuracy. Compared with heading, current PDR methods' inaccuracy is caused by failing estimation of step length and step counts. So we divide the problem into simpler components - one is the end-to-end horizontal walking speed estimation, and the other is the horizontal heading estimation. This method is different from conventional step-and-heading approach because we don't have to estimate the step count and the step length. Our end-to-end walking speed estimation method inputs accelerometer sensor data and directly outputs terminal movement speed.
To achieve the objective, we address two problems to be solved for end-toend speed estimation. First problem is how we prepare training data for end-toend speed estimation. To adapt machine learning for speed estimation, we need to collect dataset which includes pedestrian's (i.e., smartphone's) trajectory, accelerometer data, gyro sensor data, and speed. It is difficult to get these data from smartphone directly, so that we leverage Google Tango and analyze it's data for preparing speed as ground truth. Second problem is how we model neural network for estimating speed. We surveyed different methods of deep neural network for activity recognition area. Through the survey and our initial experiments with different models of networks, we decided to extend CNN-LSTM for end-to-end speed estimation (see Fig.1). 3.2
End-to-end machine learning of PDR requires ground truth data of the precise
terminal location with sensor inputs. In this paper, we employ Google Tango
enabled smartphone (Lenovo PHAB2 Pro) with original location data logger
software and HASC Logger [
Based on the collected data, we have to estimate pedestrian's speed. In this
paper, we focus two-dimensional trajectory. However, speed vector which is
calculated from Tango's location data cannot be used directly because Tango
exports data which includes 3 dimensional data. Therefore, we applied Karman
lter based method [
To model the walking speed, we employ CNN-LSTM [
Average route length 52.9m, SD:35.5m
activities from the idea of local and global feature extraction [
Fig. 3 shows the data ow of the sensor data input and the estimated horizontal speed output of DualCNN-LSTM. For each 100Hz sampling timing, we input 200 samples (2.0sec) into convolutional layer of the DualCNN-LSTM network. Inside of the network, short term feature and long term feature are extracted and combined into LSTM. We use PyTorch as a deep learning platform. 4
We have evaluated our proposed method with conventional automaton based
speed estimation method [
For the comparison, we use conventional state-machine based PDR. Step detection nite state automaton is shown in Fig. 4. State transition of automaton by norm is depicted in Fig. 5. Parameter set for the automaton is shown in table 3.
For the input of the state machine, we use 100Hz resampled 3 axis accelerometer sensor data and norm. We suppress the high-frequency noise of the sensor data by low-pass lter using FFT (higher than 8Hz for pocket, and others for 10Hz). Additionally, we limit the least time span of steps to be more than 0.5sec to avoid error detection. For the walking speed estimation, we use step length as person's stature 0.46. 4.2
In this paper, we report the detailed result of our PDR dataset for evaluation.
We divide the 5 subjects PDR dataset for 4 subjects for learning, and 1
subject for test, which results 198 learning les and 36 test les. For the evaluation
metrics, we employ the following metrics called PIEM(Path Independent
Evaluation Metrics) [
For AMDE, we calculate total distance error by using estimated walking speed and elapsed time. For MDEM and MDES, we rst create a scatter plot from moving distance error and ground truth distance, or elapsed time. Then we obtain the error rate from the slope of the line regressed by the least square estimate method. Result of the evaluation with our PDR dataset is shown in Table 4. All results of DualCNN-LSTM show better performance than Automaton based method. Effect of the type of gait is shown in Table 5. Automaton based method cannot handle the "stamp", so it increases estimation error. Fig. 6 and Fig. 7 show examples of the speed estimation results of conventional automaton based method and DualCNN-LSTM. Fig. 8 and Fig. 9 show the results of estimated moving paths with ground truth. To plot the moving path, we integrate estimated walking speed with moving direction which is calculated from horizontal angular velocity. Fig. 6 and Fig.8 is for "walk", and Fig. 7 and Fig.9 is for "stamp". Automaton based method cannot clearly distinguish the "stamp" with "walk", so it sometimes outputs incorrect speed in "stamp"(like in Fig. 7).
AMDE[m] 3.83 Overall MDEM[%] 6.26
MDES[%] 4.03
AMDE[m] 4.30 Hand MDEM[%] 6.24
MDES[%] 4.92
AMDE[m] 2.64 L-Pocket MDEM[%] 4.62
MDES[%] 2.53
AMDE[m] 4.55 R-Pocket MDEM[%] 7.92
MDES[%]8 4.64 We propose an end-to-end pedestrian walking speed estimation method using DualCNN-LSTM. By using Google Tango for collecting the corpus of pedestrian's 3D-location with sensor data, our learning method achieved higher precision such as 6.51% error rate.
Acknowledgment. This work is supported by JSPS KAKENHI Grant Number JP17H01762.