Multi-Sensor Fusion Approach for Improving Map-Based Indoor Pedestrian Localization

Huang, Hsiang-Yun; Hsieh, Chia-Yeh; Liu, Kai-Chun; Cheng, Henrich; Hsu, Steen J.; Chan, Chia-Tai

doi:10.3390/s19173786

Cited by 14 publications

(12 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many sensor fusion algorithms have been utilized to bound the heading error, such as the extended Kalman filter (EKF) [12], complementary filter (CF) [13], and gradient descent algorithm (GDA) [14,15], by fusing gyroscopes with accelerometers and magnetometers. Map information has also been widely used to improve the PDR results via map-matching algorithms [16], especially the global wall orientation data [17,18]. The impact of map awareness on localization performance has been investigated in [19] from a theoretical perspective, evaluating different accuracy bounds.…”

Section: Related Workmentioning

confidence: 99%

Smartphone-Based 3D Indoor Pedestrian Positioning through Multi-Modal Data Fusion

Zhao

Cheng

Yang

et al. 2019

Sensors

View full text Add to dashboard Cite

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).

show abstract

Section: Related Workmentioning

confidence: 99%

Smartphone-Based 3D Indoor Pedestrian Positioning through Multi-Modal Data Fusion

Zhao

Cheng

Yang

et al. 2019

Sensors

View full text Add to dashboard Cite

show abstract

“…This operation is useful in many fields, but computing it directly from the definition is often too slow to be practical. An FFT rapidly computes such transformations by factorizing the DFT matrix into a product of sparse (mostly zero) factors [ 37 ].…”

Section: Methodsmentioning

confidence: 99%

Deep Learning-Based Human Activity Real-Time Recognition for Pedestrian Navigation

Zhang

et al. 2020

Sensors

View full text Add to dashboard Cite

Several pedestrian navigation solutions have been proposed to date, and most of them are based on smartphones. Real-time recognition of pedestrian mode and smartphone posture is a key issue in navigation. Traditional ML (Machine Learning) classification methods have drawbacks, such as insufficient recognition accuracy and poor timing. This paper presents a real-time recognition scheme for comprehensive human activities, and this scheme combines deep learning algorithms and MEMS (Micro-Electro-Mechanical System) sensors’ measurements. In this study, we performed four main experiments, namely pedestrian motion mode recognition, smartphone posture recognition, real-time comprehensive pedestrian activity recognition, and pedestrian navigation. In the procedure of recognition, we designed and trained deep learning models using LSTM (Long Short-Term Memory) and CNN (Convolutional Neural Network) networks based on Tensorflow framework. The accuracy of traditional ML classification methods was also used for comparison. Test results show that the accuracy of motion mode recognition was improved from 89.9 % , which was the highest accuracy and obtained by SVM (Support Vector Machine), to 90.74 % (LSTM) and 91.92 % (CNN); the accuracy of smartphone posture recognition was improved from 81.60 % , which is the highest accuracy and obtained by NN (Neural Network), to 93.69 % (LSTM) and 95.55 % (CNN). We give a model transformation procedure based on the trained CNN network model, and then obtain the converted . t f l i t e model, which can be run in Android devices for real-time recognition. Real-time recognition experiments were performed in multiple scenes, a recognition model trained by the CNN network was deployed in a Huawei Mate20 smartphone, and the five most used pedestrian activities were designed and verified. The overall accuracy was up to 89.39 % . Overall, the improvement of recognition capability based on deep learning algorithms was significant. Therefore, the solution was helpful to recognize comprehensive pedestrian activities during navigation. On the basis of the trained model, a navigation test was performed; mean bias was reduced by more than 1.1 m. Accordingly, the positioning accuracy was improved obviously, which is meaningful to apply DL in the area of pedestrian navigation to make improvements.

show abstract

“…PDR based indoor positioning systems are prone to error in localization because of sensors biases, drift, etc. Recent PDR based systems have introduced the multi-sensor fusion approaches and multiple positioning technology integrations [138][139][140] to reduce the integral and drift errors observed in PDR based systems. Qiu et al [141] proposed a multi-sensor fusion approach for alleviating the error present in traditional PDR based systems.…”

Section: Referencesmentioning

confidence: 99%

Indoor positioning and wayfinding systems: a survey

Kunhoth

Karkar

Al‐Maadeed

et al. 2020

Hum. Cent. Comput. Inf. Sci.

189

View full text Add to dashboard Cite

Navigation systems help users access unfamiliar environments. Current technological advancements enable users to encapsulate these systems in handheld devices, which effectively increases the popularity of navigation systems and the number of users. In indoor environments, lack of Global Positioning System (GPS) signals and line of sight with orbiting satellites makes navigation more challenging compared to outdoor environments. Radio frequency (RF) signals, computer vision, and sensor-based solutions are more suitable for tracking the users in indoor environments. This article provides a comprehensive summary of evolution in indoor navigation and indoor positioning technologies. In particular, the paper reviews different computer vision-based indoor navigation and positioning systems along with indoor scene recognition methods that can aid the indoor navigation. Navigation and positioning systems that utilize pedestrian dead reckoning (PDR) methods and various communication technologies, such as Wi-Fi, Radio Frequency Identification (RFID) visible light, Bluetooth and ultra-wide band (UWB), are detailed as well. Moreover, this article investigates and contrasts the different navigation systems in each category. Various evaluation criteria for indoor navigation systems are proposed in this work. The article concludes with a brief insight into future directions in indoor positioning and navigation systems.

show abstract

Multi-Sensor Fusion Approach for Improving Map-Based Indoor Pedestrian Localization

Cited by 14 publications

References 43 publications

Smartphone-Based 3D Indoor Pedestrian Positioning through Multi-Modal Data Fusion

Smartphone-Based 3D Indoor Pedestrian Positioning through Multi-Modal Data Fusion

Deep Learning-Based Human Activity Real-Time Recognition for Pedestrian Navigation

Indoor positioning and wayfinding systems: a survey

Contact Info

Product

Resources

About