CROWD-PAN-360: Crowdsourcing Based Context-Aware Panoramic Map Generation for Smartphone Users

Abstract

Recent advances in smartphones and location-aware services necessitate identifying logical locations of users, in terms of their surroundings, instead of raw location coordinates. In this paper, we have proposed CROWD-PAN-360 (CP360), a novel smartphone-based system to generate 360-degree panoramic map of a querying user for his unfamiliar surrounding using crowd-sourced images. The objects (logical locations) appearing in the images are identified using manually or automatically generated tags. The system is context-aware and it intelligently associates user location coordinates with several smartphone contexts, like acceleration and orientation. CP360 can significantly reduce GPS positional errors for even cheap low-end smartphones and can identify the user surroundings very efficiently. We extensively tested the system in both indoor and outdoor environments of IIT Roorkee campus using Android smartphones over a dataset of more than 6000 crowd-sourced images of nearly 70 objects (departments, hostels, cafeteria, etc.) and CP360 generates the panoramic map with an average accuracy of 92.2%.

Smartphones for public transport planning and recommendation in developing countries—A review

“…With tracking vehicles as a tool, there have been several studies on utilizing vehicle trajectories to generate road network maps. In Crowd‐pan‐360 (Raychoudhury, Shrivastav, Sandha, & Cao, 2014), the panoramic map of only surrounding areas is generated using crowdsourced images. The CP360 system obtains location, inertial sensor, and camera data to compute features like tilt, orientation, direction of travel, location of the user, and so on to generate the said panoramic map of the area.…”

A Social Approach to High-level Context Generation for Supporting Context-aware M-Learning

“…As the result, the generality of context-aware applications is limited. Another way is to encourage end-users to directly provide and define high-level context or involve in context development, such as Social Context-Aware Browser (Mizzaro & Vassena, 2011) and the CP360 system (Raychoudhury, Shrivastav, Sandha, & Cao, 2015). In these works, end-users directly and explicitly participate in developing or defining context, which means that more complex and implicit high-level context information is not exploited adequately.…”

Rich Common Crucial Feature for Crowdsourcing-Based Mobile Visual Location Recognition

“…With the ubiquitous smartphones, it is convenient to perform various location-based services, for example, location recognition systems. In these systems, GPS and Wi-Fi based localization methods have been widely used in outdoor environments [1], [2]. Although these systems are capable of capturing the preliminary physical coordinates (GPS information), it is poorly-recognized with respect to the logical meanings of scenes, e.g., buildings, landmarks, shops that the users are interested in.…”

“…Moreover, the localization accuracy is still not satisfactory in many realistic scenarios. For example, errors of localization of GPS often [1] range from 5 to 300 meters at some places with poor visibility. Comparing with these location recognition systems, the Mobile Visual Location Recognition (MVLR) [3] combines captured image and sensory data obtained from smartphone as a location query, which provides logical location information as an important supplement.…”