Route planning (RP) enables individuals to navigate in unfamiliar environments. Current RP methodologies generate routes that optimize criteria relevant to the traveling distance or time, whereas most of them do not consider personal preferences or needs. Also, most of the current smart wearable assistive navigation systems offer limited support to individuals with disabilities by providing obstacle avoidance instructions, but often neglecting their special requirements with respect to the route quality. Motivated by the mobility needs of such individuals, this study proposes a novel RP framework for assistive navigation that copes these open issues. The framework is based on a novel mixed 0–1 integer nonlinear programming model for solving the RP problem with constraints originating from the needs of individuals with disabilities; unlike previous models, it minimizes: (1) the collision risk with obstacles within a path by prioritizing the safer paths; (2) the walking time; (3) the number of turns by constructing smooth paths, and (4) the loss of cultural interest by penalizing multiple crossovers of the same paths, while satisfying user preferences, such as points of interest to visit and a desired tour duration. The proposed framework is applied for the development of a system module for safe navigation of visually impaired individuals (VIIs) in outdoor cultural spaces. The module is evaluated in a variety of navigation scenarios with different parameters. The results demonstrate the comparative advantage of our RP model over relevant state-of-the-art models, by generating safer and more convenient routes for the VIIs.

/pdf/a-route-planning-framework-for-smart-wearable-assistive-5hzw6vnq52.pdf

A route planning framework for smart wearable assistive navigation systems

Crowd behavior detection is important for the smart cities applications such as people gathering for different events. However, it is a challenging problem due to the internal states of the crowd itself and the surrounding environment. This paper proposes a novel crowd behavior detection framework based on a number of parameters. We first exploit a computer vision approach based on scale invariant feature transform (SIFT) to classify the crowd behavior either into panic or normalness. We then consider a number of other parameters from the surroundings namely crowd coherency, social interaction, motion information, randomness in crowd speed, internal chaos level, crowd condition, crowd temporal history, and crowd vibration status along with time stamp. Subsequently, these parameters are fed to deep learning model during training stage and the behavior of the crowd is detected during the testing stage. The experimental results show that proposed method renders significant performance in terms of crowd behavior detection.

/pdf/the-internet-of-things-for-crowd-panic-detection-4u3rfe1dof.pdf

The Internet of Things for Crowd Panic Detection

An indoor evacuation guidance system with an AR virtual agent

China has a population of 1.4 billion, ranking first in the world. With the increase in China's economic development and population, the construction of various types of buildings in China is also increasing, and associated safety hazards are gradually increasing. Therefore, it is necessary to study the safe evacuation of people inside and outside the building in emergency situations. In recent years, some scholars have used the traditional statistical method of literature review to analyze the research frontiers in the field of safety evacuation, but few scholars have used bibliometric methods to analyze and review the current situation of research in this field. Therefore, this paper adopts the analysis method combining bibliometrics and traditional literature review to summarize the research status of crowd evacuation published by Chinese scholars in the Web of Science core database, and uses VOSviewer to analyze the authors, institutions, and keywords of the literature search results, so as to identify their research hotspots. The results show that the last three years have been the peak period of crowd evacuation studies, with many disciplines involved in this field and they are closely related, led by the number of papers related to architecture. Simulation, model, behavior, among others, have been the most used keywords in this research field, and the research on path planning and exit selection behavior has also increased significantly. According to the keyword analysis, three hot spots of safety evacuation research, namely large-scale group evacuation, evacuation path planning and evacuation exit selection are analyzed in detail. 

Progress and prospects in crowd safety evacuation research in China

The anti-collision theory of adaptive Q algorithm and radio frequency identification(RFID) communication timing sequence were analyzed. Then a Markov chain model for simulating multi-tag identification process was established based on the following three definitions. The definitions are identifying efficiency, identifying speed and data state( Q, n ), where n is the total remanent tag number, and Q is the slot count. The identifying efficiency and speed were obtained from the model using Monte Carlo statistical method. A software-defined radio program was built to simulate the collision of RFID which could quantify the identifying efficiency and speed effectively. The consistency of model simulation result and test data proves the validity of the model and test method.

Radio frequency identification anti-collision test based on Markov chain model

The cultural museum is one of the places with a large flow of people. Once an emergency occurs, if the people are not evacuated in time, the consequences will be unimaginable. In the event of an emergency, the population speed and evacuation effect are linear in the case of a small population density. However, when the population density is large, the population speed and evacuation effect are nonlinear. The traditional method is aimed at evacuation control with a small density and a smooth change in a large flow of people. When the density is large, the evacuation speed cannot be too fast, and once the pedalling event occurs, the stability of the model is destroyed. In order to solve the above problems, this paper takes a large-scale crowd of cultural museum as the studied object and proposes a large-scale crowd evacuation method based on the mutation theory of RFID (radio frequency identification). The algorithm uses the mutation prediction RFID to judge the arrival rate change trend by the arrival rate reverse mutation rule, so that the modelling length can dynamically adapt to the RFID tag arrival rate change and overcome the contradiction between the prediction accuracy and the tracking speed. The accuracy of the algorithm to predict the flow of large-scale people is improved, making the evacuation model more relevant to the actual situation. Through the experiment tests on typical scenes, the evacuation control problems of four groups of people are analysed and discussed. The results prove that the evacuation method proposed in this paper can provide guidance for crowd evacuation in the cultural museum.

Ke Ma

Papers

Study on large-scale crowd evacuation method in cultural museum using mutation prediction RFID