Walking Secure: Safe Routing Planning Algorithm and Pedestrian's Crossing Intention Detector Based on Fuzzy Logic App

Abstract

Improving road safety through artificial intelligence is now crucial to achieving more secure smart cities. With this objective, a mobile app based on the integration of the smartphone sensors and a fuzzy logic strategy to determine the pedestrian's crossing intention around crosswalks is presented. The app developed also allows the calculation, tracing and guidance of safe routes thanks to an optimization algorithm that includes pedestrian areas on the paths generated over the whole city through a cloud database (i.e., zebra crossings, pedestrian streets and walkways). The experimentation carried out consisted in testing the fuzzy logic strategy with a total of 31 volunteers crossing and walking around a crosswalk. For that, the fuzzy logic approach was subjected to a total of 3120 samples generated by the volunteers. It has been proven that a smartphone can be successfully used as a crossing intention detector system with an accuracy of 98.63%, obtaining a true positive rate of 98.27% and a specificity of 99.39% according to a receiver operating characteristic analysis. Finally, a total of 30 routes were calculated by the proposed algorithm and compared with Google Maps considering the values of time, distance and safety along the routes. As a result, the routes generated by the proposed algorithm were safer than the routes obtained with Google Maps, achieving an increase in the use of safe pedestrian areas of at least 183%.

Keywords: Android application; crossing intention detector; pedestrians; road safety; safe routes; smart cities.

Figure 1

(a) Application functionalities. (b) Application architecture.

Figure 2

Sensory fusion scheme.

Figure 3

Graphical comparison of two pedestrian gaits over a straight line for 10 s. (a) X-axis comparison. (b) Y-axis comparison. (c) Z-axis comparison.

Figure 4

Example of fuzzy labels used for rotation detection inputs.

Figure 5

Fuzzy sets used to determine how far the pedestrian is from the next pedestrian point of interest base on its options. (a) Sightseeing; (b) walking; (c) running.

Figure 6

Communication scheme used between the application and the smart crosswalk.

Figure 7

(a) Description of the test scenario. (b) Average results of the calibrated and uncalibrated rotation detector, where vertical lines represent the standard deviation for each average value.

Figure 8

(a) Route calculated by the app where it is observed how to avoid the incorrect use of a roundabout. (b) Route calculated by the app where it is depicted how to avoid circulating like a vehicle. (c) Route calculated by the app where pedestrian areas are used. (d) Route calculated by the app where the pedestrian walkway is used. (e) Route calculated by Google Maps where a pedestrian is introduced into a roundabout. (f) Route calculated by Google Maps where a pedestrian is introduced into an intersection without respecting the signals. (g) Route calculated by Google Maps where pedestrians are not introduced through pedestrian areas. (h) Route calculated by Google Maps where the pedestrian walkway is not used.