Pedestrian navigation activity recognition method based on two-stream transformer and contrastive learning.

Pedestrian positioning and navigation is an important emerging branch in the field of location-based service (LBS). Due to the loss of satellite signals, the traditional positioning method, such as GNSS, cannot meet the demand of indoor and outdoor seamless navigation. In order to provide the continuous and autonomous navigation information in indoor environment, we propose a novel Pedestrian Dead Reckoning (PDR) algorithm using Surface Electromyography (SEMG) sensors based on activities recognition. This PDR solution includes gait cycle detection, stride length estimation, pedestrian activities recognition, heading and position calculation. We extract several appropriate features from the raw SEMG signal to detect four different walking motions and then these activities information will aid the PDR system to complete the positioning. After the indoor walking tests, the results show that the PDR algorithm has a high positioning accuracy compared with the INS (Inertial Navigation System) algorithm. The step detection accuracy is 100%, the displacement errors in north and south are less than 1.2m and the distance error is less than 4%.

Indoor location-based service is a hot research topic whose application market size is expected to grow from <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\$ $ </tex-math></inline-formula> 41 billion by 2022 and <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\$ $ </tex-math></inline-formula> 58 billion by 2023. As a portable communication device, smartphones have inherent advantages (such as being an essential gadget in daily life, embedding various sensors, and having powerful computing and storage ability), which provides a great opportunity for human activity recognition and pedestrian navigation. Smartphone-based pedestrian inertial navigation systems (PINSs) utilize measurements from inertial sensors embedded in smartphones to reckon the pedestrian’s location. Compared with other indoor position technologies, PINS has the advantage of autonomy and continuity, and can achieve high-precision positioning in a short period. Though various PINS methods based on the smartphone have been proposed, up-to-date review papers that summarize relevant technologies, methods, and solutions of PINS are relatively less so far in the literature. This article aims to provide an elaborated, timely, and valuable survey of different infrastructure-free pedestrian positioning and navigation techniques, including pedestrian inertial navigation methods, performance evaluation, and applications. Finally, current challenges and future research trends are discussed. This work propels a better understanding of existing pedestrian inertial positioning methods. It is helpful for researchers to further design and develop more accurate and robust pedestrian positioning and navigation systems based on inertial sensors embedded in the smartphone.

In order to solve the discontinuity of navigation and positioning in indoor signal coverage blind areas, and false region judgment caused by positioning error, an integrated method combining Wireless Positioning System (WPS), Pedestrian Dead Reckoning (PDR) and Map Matching (MM) is presented in this paper. By using the combination of Kalman filtered WPS and PDR information, inertial information and geographic information, pedestrian position could be evaluated. Through experiment, this method effectively increased positioning accuracy of the system as well as greatly improved the user experience.

Smartphone based pedestrian inertial navigation system usually uses the Pedestrian Dead Reckoning (PDR) algorithm to achieve navigation and positioning. The traditional PDR algorithm requires inertial devices to remain a stationary position relative to the human body, however, in the field of smart pedestrian navigation, smartphone can’t always keep a stationary posture when it is being used. When the way of using smartphone has been changed, traditional PDR algorithm will give the wrong heading estimation which is caused by the change of smartphone’s attitude. Therefore, in order to satisfy the navigation demand for smartphone pedestrian inertial positioning especially when the using way changed, a Heading Compensation with Gravity Assisted (HCGA) method is proposed in this paper. This method will judge the change of smartphone’s attitude and compensate heading based on data from gravity sensor. The result of experiment shows that using HCGA method, it can be distinguished whether the change of heading caused by the attitude change automatically when the change of heading is detected, then compensate the result of heading. In this way, the influence of navigation solution caused by different handheld modes will be reduced.

Due to the unavailability of GPS indoors, various indoor pedestrian positioning approaches have been designed to estimate the position of the user leveraging sensory data measured from inertial measurement units (IMUs) and wireless signal receivers, such as pedestrian dead reckoning (PDR) and received signal strength (RSS) fingerprinting. This study is similar to the previous study in that it estimates the user position by fusing noisy positional information obtained from the PDR and RSS fingerprinting using the Bayes filter in the indoor pedestrian positioning system. However, this study differs from the previous study in that it uses an enhanced state estimation approach based on the ensemble transform Kalman filter (ETKF), called QETKF, as the Bayes filer for the indoor pedestrian positioning instead of the SKPF proposed in the previous study. The QETKF estimates the updated user position by fusing the predicted position by the PDR and the positional measurement estimated by the RSS fingerprinting scheme using the ensemble transformation, whereas the SKPF calculates the updated user position by fusing them using both the unscented transformation (UT) of UKF and the weighting method of PF. In the field of Earth science, the ETKF has been widely used to estimate the state of the atmospheric and ocean models. However, the ETKF algorithm does not consider the model error in the state prediction model; that is, it assumes a perfect model without any model errors. Hence, the error covariance estimated by the ETKF can be systematically underestimated, thereby yielding inaccurate state estimation results due to underweighted observations. The QETKF proposed in this paper is an efficient approach to implementing the ETKF applied to the indoor pedestrian localization system that should consider the model error. Unlike the ETKF, the QETKF can avoid the systematic underestimation of the error covariance by considering the model error in the state prediction model. The main goal of this study is to investigate the feasibility of the pedestrian position estimation for the QETKF in the indoor localization system that uses the PDR and RSS fingerprinting. Pedestrian positioning experiments performed using the indoor localization system implemented on the smartphone in a campus building show that the QETKF can offer more accurate positioning results than the ETKF and other ensemble-based Kalman filters (EBKFs). This indicates that the QETKF has great potential in performing better position estimation with more accurately estimated error covariances for the indoor pedestrian localization system.

Without the assistance of Global Positioning System (GPS), estimating the 3D position of indoor and outdoor pedestrians using a single wearable device is a daunting if not impossible task, especially if micro-sensors are used. Here, we present a novel 3D position estimation method using one integrated ankle sensing device, which consists of an accelerometer, a gyroscope, a magnetometer, and a barometer. Pedestrians' vertical position is estimated by fusing the acceleration and angular velocity as well as the height derived from barometer data. To estimate pedestrians' horizontal position, we proposed an adaptive multimodal stride length model and a multi-sensor-fusion-based heading angle estimation method, using the Pedestrian Dead Reckoning (PDR) mechanism. By introducing a vertical variable into the stride length model, this new model greatly improved the applicability and accuracy of PDR in horizontal position estimation. Based on this new model, PDR can be used not only for estimating the horizontal position of the pedestrian walking on flat areas but also for those walking up and down stairs. The effectiveness and applicability of our method in 3D position estimation have been demonstrated in several different experiments of indoor and outdoor scenes. The first is when a pedestrian walks on an indoor flat ground, following a spiral trajectory. The estimation accuracy of pedestrians' height position is 1.5cm and the ratio of horizontal walking estimation error is 1.02m with a total walking distance of 53.1m. The second is when a pedestrian walks up staircases from Floor 4 to Floor 8 in a building. The cumulative error of the estimated height is 0.23m with a total height of 14.4m, and the root mean square error of the estimated horizontal 2D position is 15cm compared to a total horizontal walking distance of 38.4m. The third case involves a pedestrian walking on audience stands of an outdoor stadium and returns to the starting position for a total distance of 94.4m. The estimation error from the sensing device is 0.92m in this case, with mean error of the estimated height position of each step at 3.3cm. Having the capability to provide centimeter-level position estimation of pedestrians, this sensing device can be applied for 3D body tracking and indoor/outdoor pedestrian positioning and navigation.

PurposeThe purpose of this paper is to relate to the real-time navigation and tracking of pedestrians in a closed environment. To restrain accumulated error of low-cost microelectromechanical system inertial navigation system and adapt to the real-time navigation of pedestrians at different speeds, the authors proposed an improved inertial navigation system (INS)/pedestrian dead reckoning (PDR)/ultra wideband (UWB) integrated positioning method for indoor foot-mounted pedestrians.Design/methodology/approachThis paper proposes a self-adaptive integrated positioning algorithm that can recognize multi-gait and realize a high accurate pedestrian multi-gait indoor positioning. First, the corresponding gait method is used to detect different gaits of pedestrians at different velocities; second, the INS/PDR/UWB integrated system is used to get the positioning information. Thus, the INS/UWB integrated system is used when the pedestrian moves at normal speed; the PDR/UWB integrated system is used when the pedestrian moves at rapid speed. Finally, the adaptive Kalman filter correction method is adopted to modify system errors and improve the positioning performance of integrated system.FindingsThe algorithm presented in this paper improves performance of indoor pedestrian integrated positioning system from three aspects: in the view of different pedestrian gaits at different speeds, the zero velocity detection and stride frequency detection are adopted on the integrated positioning system. Further, the accuracy of inertial positioning systems can be improved; the attitude fusion filter is used to obtain the optimal quaternion and improve the accuracy of INS positioning system and PDR positioning system; because of the errors of adaptive integrated positioning system, the adaptive filter is proposed to correct errors and improve integrated positioning accuracy and stability. The adaptive filtering algorithm can effectively restrain the divergence problem caused by outliers. Compared to the KF algorithm, AKF algorithm can better improve the fault tolerance and precision of integrated positioning system.Originality/valueThe INS/PDR/UWB integrated system is built to track pedestrian position and attitude. Finally, an adaptive Kalman filter is used to improve the accuracy and stability of integrated positioning system.

This research proposes an algorithm that improves the position accuracy of indoor pedestrian dead reckoning, by compensating the position error with a magnetic field map-matching technique, using multiple magnetic sensors and an outlier mitigation technique based on roughness weighting factors. Since pedestrian dead reckoning using a zero velocity update (ZUPT) does not use position measurements but zero velocity measurements in a stance phase, the position error cannot be compensated, which results in the divergence of the position error. Therefore, more accurate pedestrian dead reckoning is achievable when the position measurements are used for position error compensation. Unfortunately, the position information cannot be easily obtained for indoor navigation, unlike in outdoor navigation cases. In this paper, we propose a method to determine the position based on the magnetic field map matching by using the importance sampling method and multiple magnetic sensors. The proposed method does not simply integrate multiple sensors but uses the normalization and roughness weighting method for outlier mitigation. To implement the indoor pedestrian navigation algorithm more accurately than in existing indoor pedestrian navigation, a 15th-order error model and an importance-sampling extended Kalman filter was utilized to correct the error of the map-matching-aided pedestrian dead reckoning (MAPDR). To verify the performance of the proposed indoor MAPDR algorithm, many experiments were conducted and compared with conventional pedestrian dead reckoning. The experimental results show that the proposed magnetic field MAPDR algorithm provides clear performance improvement in all indoor environments.

This paper proposes improvement for performance of a low-cost Pedestrian Dead-Reckoning(PDR) System through calibration and analysis of sensor. It is applied that PDR System for estimating pedestrian's position in the area not being able to be received. also sensor's error is removed by using angle compensation technique and performance of system is improved by analysis of PDR system. Consequently, position of pedestrian is estimated by applying the improved value of sensor and result of angle analysis to PDR system. Experiments were conducted to verify the proposed system. Experimental results within 2% of range error, RMS position error of less than 3% showed superior performance.

Indoor positioning method for pedestrian dead reckoning based on multi-source sensors

Pedestrian dead reckoning (PDR) is an effective technology for pedestrian navigation. In PDR, the steps are detected with the measurements of self-contained sensors, such as accelerometers, and the position is updated with additional heading angles. A smartphone is usually equipped with a low-cost microelectromechanical system accelerometer, which can be utilized to implement PDR for pedestrian navigation. Since the PDR position errors diverge with the walking distance, the global navigation satellite system (GNSS) is usually integrated with PDR for more reliable position results. This paper implemented a smartphone PDR/GNSS via a Kalman filter and factor graph optimization (FGO). In the FGO, the PDR factor is modeled, and the states are correlated with a dead reckoning algorithm. The GNSS position is modeled as the “GNSS” factor to constrain the states at each step. With a graphic model representing the states and measurements, the state estimation is converted to a nonlinear least square problem, and we utilize the Georgia Tech Smoothing and Mapping graph optimization library to implement the optimization. We tested the proposed method on a Huawei Mate 40 Pro handset with a standard playground field test, and the field test results showed that the FGO effectively improved the smartphone position accuracy. We have released the source codes and hope that they will inspire other works on pedestrian navigation, i.e., constructing an adaptive multi-sensor integration system using FGO on a smartphone.

Because of the demand for seamless indoor and outdoor positioning of mass-market applications, several simple and efficient pedestrian dead reckoning (PDR) systems have been introduced. However, the performance of the PDR system would significantly decrease with the increase of recursion time, due to the influence of sensors and model error. This paper discusses the overview of the pedestrian navigation system and the implementation of key techniques of PDR, then proposes an improved PDR system with precise displacement estimation based on time-differenced carrier phase (TDCP) technique. Using the derived position change and heading from TDCP as updating information, the bias of stride and heading of the modeled PDR system will be estimated through a sliding window. The field test results demonstrate that the errors of gyroscope heading and compass heading show different characteristics, and there is a linearly increased error of gyroscope heading. The max errors of accumulated displacement of TDCP are about 5.32 m, and using pure PDR after trained by TDCP, the max error values of short-term and long-term navigation are approximately 5.97 and 14.88 m, respectively. From the point view of cumulative probability, for the probability of 80%, the horizontal errors of accumulated displacement of TDCP is only 3.78 m, and values of short-term and long-term navigation reach to 4.15 m and 11.78 m, respectively. These results indicate that the proposed algorithm is stable and practical to the continuous pedestrian navigation during the intermittent global navigation satellite system observation condition.

PDR (Pedestrian Dead Reckoning) is a very promising technology for indoor positioning. We held a technical challenge, entitled the UbiComp/ISWC 2015 PDR Challenge, consisting of the following three categories: a PDR algorithm category; a PDR Evaluation method category; and an exhibition. In this paper, we especially focus on several systems for the PDR algorithm category. A PDR skeleton was prepared for the participants. Using an Android skeleton, participants focus on implementing the PDR algorithm because of the skeleton's various functions, such as sensor data acquisition, trajectory visualization, and sensor data upload. The evaluation server evaluates the accuracy of each PDR algorithm automatically as often as sensor data is uploaded to the server and provides a trajectory image file so that participants can compare their PDR algorithms in real time.

Combining research areas of biomechanics and pedestrian dead reckoning (PDR) provides a very promising way for pedestrian positioning in environments where Global Positioning System (GPS) signals are degraded or unavailable. In recent years, the PDR systems based on a smartphone’s built-in inertial sensors have attracted much attention in such environments. However, smartphone-based PDR systems are facing various challenges, especially the heading drift, which leads to the phenomenon of estimated walking path passing through walls. In this paper, the 2D PDR system is implemented by using a pocket-worn smartphone, and then enhanced by introducing a map-matching algorithm that employs a particle filter to prevent the wall-crossing problem. In addition, to extend the PDR system for 3D applications, the smartphone’s built-in barometer is used to measure the pressure variation associated to the pedestrian’s vertical displacement. Experimental results show that the map-matching algorithm based on a particle filter can effectively solve the wall-crossing problem and improve the accuracy of indoor PDR. By fusing the barometer readings, the vertical displacement can be calculated to derive the floor transition information. Despite the inherent sensor noises and complex pedestrian movements, smartphone-based 3D pedestrian positioning systems have considerable potential for indoor location-based services (LBS).

Trajectory and transportation mode tracking has always been a hot topic since it can provide valuable information for both personal usage and city development. Smart phones equipped with various kinds of sensors are regarded as good tools to track users' trajectories for convenience. The Global Positioning System (GPS) receiver in smart phones is very useful for location services, however its location results become very inaccurate due to signal blockage and multipath effect in urban area. The Pedestrian Dead Reckoning (PDR) system only uses inertial sensors, however, its accumulation error becomes large as distances increased. In this paper, we propose a method that integrates PDR with a traffic mode based map matching to improve positioning accuracy. We firstly generate the hypothesis trajectory based on the activity detection result from PDR and traffic mode detection. Then the most possible trajectory is estimated by considering the walking length. The experimental result demonstrated that we achieve a 1.16m average positioning error in urban area.