Continuation of Comprehensive Conjoint GPS, Sensor and Video Data (COVMAP 2)

COVMAP 2

During the last years the availability of spatial data has rapidly developed. Characteristic for this development is the involvement of a large number of users, who frequently use smart phones and mobile devices, to generate and make freely available Volunteered Geographic Information (VGI). Whereas GPS and gyroscope data (e.g. with fitness‐straps) are common, the huge amount of data, which are easily and typically collected in the form of videos, make video analysis based methods very demanding. On the other hand, only videos allow for a comprehensive scene interpretation. In this research project, we are interested in combining GPS, gyroscope and video data to analyze road and traffic situations for cyclists and pedestrians. Our standard setting (Fig. 1) is a smart phone attached to a bicycle, which records the GPS coordinates, videos, (online) local weather information and time. We will (a) use the GPS‐data for integration in a map, (b) local velocities and gyroscope data, as well as variations in the sensor data, will be used to identify important situations during a bicycle ride, and (c) video data will be used to understand these important situations which cause e.g. a delay in the ride. The analyzed data can then be used for map enhancement and path recommendation, but also for the identification of unclear road marks which is important for city planning and accident avoidance. Besides collecting experience with real‐time and event triggered data with a focus on a human‐centered application, the foundations can easily be extended toward traffic management after hazards, quality control of topographic datasets or environmental and health‐related data analysis using additional sensor information.

Publications

  1. Kluger, F., Ackermann, H., Brachmann, E., Yang, M. Y., & Rosenhahn, B. (2021, June). Cuboids Revisited: Learning Robust 3D Shape Fitting to Single RGB Images. CVPR. https://arxiv.org/pdf/2105.02047.pdf
  2. Kluger, F., Ackermann, H., Yang, M. Y., & Rosenhahn, B. (2020, June). Temporally Consistent Horizon Lines. ICRA. https://arxiv.org/pdf/1907.10014.pdf
  3. Kluger, F., Brachmann, E., Ackermann, H., Rother, C., Yang, M. Y., & Rosenhahn, B. (2020, June). CONSAC: Robust Multi-Model Fitting by Conditional Sample Consensus. CVPR. https://arxiv.org/pdf/2001.02643.pdf