Pleasant Route Suggestion based on Color and Object Rates

Beyond the Shortest Route: A Survey on Quality-Aware Route Navigation for Pedestrians

“…Finally, while not specifically aimed at helping users avoid exposure to a specific harmful substance or environment, researchers have also proposed a route recommendation algorithm which encourages users to walk along paths to increase their contact with nature (parks, woods, gardens etc.) [39] and decrease chances of contact with unhealthy environments. This was based on the rationale that such locations have been found to help lower blood pressure and cortisone for pedestrians, while unpleasant environments increase blood pressure, muscle tension and may even contribute to suppressing the immune system of pedestrians [40]- [42].…”

“…This information is generally used as the main cost function for a given path. Social media data in combination with machine learning techniques have also been used in cases where the impact or presence of the harmful substances is less clear (such as when determining which path has potential to stimulate cravings [38] or help in relaxation [39]). Finally, systems which encourage physical exercise tend to rely on the path length to judge whether a route meets the exercise criteria of the user, by using information such as the time a user is willing to spend or the amount of calories they wish to lose to calculate the appropriate distance for meaningful exercise.…”

“…In later studies, the authors developed an urban smell dictionary which they hinted could be used to identify routes which are pleasing in the olfactory sense [66]. Instead of crowd-sourced data, other systems used information collected from Google Street View, Twitter and OpenStreetMap to determine which routes were bright, contained beautiful views [39] were fashionable [15] or passed through locations that provide a high level of sociability, quietness and are close to nature [67]. Another study in this category proposed a route recommendation algorithm aimed at providing hikers with a sense of solitude while hiking, by generating routes which would allow them to avoid meeting other people along the trail [68].…”

“…For example, tag data obtained from OpenStreetMap could be used to determine whether the route contains locations which are noisy (for example, whether there are nearby streets tagged as ''highways'') or scenic (such as locations tagged as ''gardens'' or ''woods'') [67]. In other cases, data from social media such as geo-tagged tweets or photos from Flickr and Google Street View could be analyzed and used to determine whether a route has potential to provide a pleasurable walking experience [39], [66]. For example, image analysis could be carried out to determine the color ratio, object ratio, and color brightness at different points along the route, with the assumption that a pleasant route would have much nature and contain green and bright views [39].…”

“…In other cases, data from social media such as geo-tagged tweets or photos from Flickr and Google Street View could be analyzed and used to determine whether a route has potential to provide a pleasurable walking experience [39], [66]. For example, image analysis could be carried out to determine the color ratio, object ratio, and color brightness at different points along the route, with the assumption that a pleasant route would have much nature and contain green and bright views [39]. Crowd-sourced data could also be used to help determine which street characteristics are related to pleasant route qualities by analyzing the presence of words and visual textures in streets rated as pleasant and unpleasant by users [66].…”