The vision-aided Pedestrian Dead Reckoning (PDR) systems have become increasingly popular, thanks to the ubiquitous mobile phone embedded with several sensors. This is particularly important for indoor use, where other indoor positioning technologies require additional installation or bodyattachment of specific sensors. This paper proposes and develops a novel 3D Passive Vision-aided PDR system that uses multiple surveillance cameras and smartphone-based PDR. The proposed system can continuously track users’ movement on different floors by integrating results of inertial navigation and Faster R-CNNbased real-time pedestrian detection, while utilizing existing camera locations and embedded barometers to provide floor/height information to identify user positions in 3D space. This novel system provides a relatively low-cost and user-friendly solution, which requires no modifications to currently available mobile devices and also the existing indoor infrastructures at many public buildings for the purpose of 3D indoor positioning. This paper shows the case of testing the prototype in a four-floor building, where it can provide the horizontal accuracy of 0.16m and the vertical accuracy of 0.5m. This level of accuracy is even better than required accuracy targeted by several emergency services, including the Federal Communications Commission (FCC). This system is developed for both Android and iOSrunning devices.

Vision-aided inertial navigation has become a very popular method for indoor navigation recently. This popularity is basically due to the development of light-weighted and low-cost Micro Electro-Mechanical Systems (MEMS) as well as advancement and availability of Charged-Couple-Device (CCD) cameras in public indoor areas. While the use of inertial sensors and cameras are challenging due to drift accumulation and object detection in line of sight, respectively, the integration of these two sensors can compensate their drawbacks and provide more accurate positioning solutions. This study examines this hypothesis by evaluating the accuracy of the vision-aided systems for indoor positioning and tracking. The novel aspect of this study is to implement inertial and visual sensors in independent platforms other than attached together on the same platform. The other novelty is to integrate digitized floor plans for absolute position information. The mean accuracy of this positioning system is 11% higher than uncalibrated inertial positioning during experiment.

Walking speed is a significant aspect of evacuation efficiency, and this speed varies during fire emergencies due to individual physical abilities. However, in evacuations, it is not always possible to keep an upright posture, hence atypical postures, such as stoop walking or crawling, may be required for survival. In this study, a novel 3D passive vision-aided inertial system (3D PVINS) for indoor positioning was used to track the movement of 20 volunteers during an evacuation in a low visibility environment. Participants’ walking speeds using trunk flexion, trunk–knee flexion, and upright postures were measured. The investigations were carried out under emergency and non-emergency scenarios in vertical and horizontal directions, respectively. Results show that different moving directions led to a roughly 43.90% speed reduction, while posture accounted for over 17%. Gender, one of the key categories in evacuation models, accounted for less than 10% of the differences in speed. The speeds of participants under emergency scenarios when compared to non-emergency scenarios was also found to increase by 53.92–60% when moving in the horizontal direction, and by about 48.28–50% when moving in the vertical direction and descending downstairs. Our results also support the social force theory of the warming-up period, as well as the effect of panic on the facilitating occupants’ moving speed.

Currently, Pedestrian Dead Reckoning (PDR) systems are becoming an important tool in indoor navigation. This is mainly due to the development of affordable and portable Micro Electro-Mechanical Systems (MEMS) on smartphones and decreased requirement of additional infrastructures in indoor areas. The main drawback to this technology remains the problem of drift accumulation and the need for support from external positioning systems. Vision-aided inertial navigation is one possible solution to that problem. This solution has become more popular in indoor localization with improved satisfaction compared to individual PDR system. Previous studies have used fixed platforms and visual tracking employed feature-extraction-based methods. This paper proposes a distributed implementation of positioning system and uses deep learning for visual tracking. Meanwhile, as both inertial navigation and optical systems can provide only relative positioning information, this paper proposes a method to integrate digital maps with real geographical coordinates to supply absolute location. This hybrid system has been tested on two common operation systems of smartphones using iOS and Android systems, based on corresponding data collection apps respectively, in order to test the robustness of method. It also uses two different methods for calibration, by time synchronization of positions and heading calibration based on time steps. Results demonstrate that localization information collected from both operating systems can be significantly improved after integrating with visual tracking data.

In this paper, we focused on the dynamic evaluation of sustainable development capacity for mining cities in China. The indicator system of sustainable development capacity for mining cities was constructed from the aspects of resources, environment, economy and social development. BP neural network method was adopted to dynamically predict the capacity for sustainable development system of Panjin City. The dynamic results indicated that of factors influencing the sustainability in the future, economic level, mineral resources production and degree of coordination between industry and environment are very strong. Insufficient educational investment will dissatisfy the requirements of industrial transformation and socio-economic development. Furthermore, the promotion of optimization and upgrading of industrial structure in mining cities should base on the characteristics of resources and regional economy, meanwhile, mining cities should develop clean energy and improve investment environment. This paper laid an experience for the application of BP neural network model in socio-economic research field.

Fall prediction has become increasingly important as it can prevent injuries caused by ground-hitting. The leading time, i.e. the time between prediction and collision, plays an important role by securing sufficient time to activate protective systems. However, only a few studies have investigated the leading time, and many of them fail to satisfy the minimum requirement. Besides, few studies focused on both fall prediction and pedestrian tracking, especially in indoor environments. This study proposes a novel method, which can simultaneously track the user while predicting possible fall impacts by using embedded inertial sensors within smartphone for indoor environment, without additional data processing. The proposed system is developed by using smartphone-embedded inertial sensors, with additional support from vision-based inertial calibration and post-fall validation. The system has been tested in a single room, including two types of forward fall cases as recovering after falling and/or staying on ground. It has also introduced two confusing daily activities as bending and squatting to reach the ground and getting up later. The pilot results have shown that a fall could be predicted 670ms to 700ms before impact with calibrated inertial data. Besides, the system has preliminarily achieved a positioning accuracy of 0.06m and precision of 0.08m.