Data-driven approach to learning salience models of indoor landmarks by using genetic programming

In landmark-based way-finding, determining the most salient landmark from several candidates at decision points is challenging. To overcome this problem, current approaches usually rely on a linear model to measure the salience of landmarks. However, linear models are not always able to establish an accurate quantitative relationship between the attributes of a landmark and its perceived salience. Furthermore, the numbers of evaluated scenes and of volunteers participating in the testing of these models are often limited. With the aim of overcoming these gaps, we propose learning a non-linear salience model by means of genetic programming. We compared our proposed approach with conventional algorithms by using photographs of two hundred test scenes collected from two shopping malls. Two hundred volunteers who were not in these environments were asked to answer questionnaires about the collected photographs. The results from this experiment showed that in 76% of the cases, the most salient landmark (according to the volunteers' perception) was correctly predicted by our proposed approach. This accuracy rate is considerably higher than the ones achieved by conventional linear models.