Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung IOSB

[Bachelor / Hiwi] Metrics and Measurements for Crowded Scenarios

The Fraunhofer Institute of Optronics, System Technologies and Image Exploitation IOSB is one of the biggest institutes for applied research in the field of image acquisition and exploitation in Europe. The department Video Exploitation Systems (VID) devotes itself to automatical signal processing of moving imagery sensors in complex and non-cooperative scenarios. Such sensors are applied within the fields of reconnaissance or surveillance as integrated components in aerial, spaceborn or land-based platforms. VID develops and deploys computer vision algorithms for autonomous and interactive systems.

Figure 1:  People can distribute differently all over certain areas which brings various challenges to the application of methods like human pose estimation, crowd counting or simply pedestrian detection and localisation

Description

Crowd monitoring is an important task for planning and conducting events such as public festivals, as e.g. the Hamburg Port Anniversairy, the Cannstatter Volksfest or Das Fest in Karlsruhe but also in urban areas and inner cities. To assure the safety of visitors, organizers typically perform simulations before the actual event takes place. However, to evaluate the performance of such a simulation the real behavior of people has to be measured. This is a quite tackling task, due to various difficulties coming up when working with image data of larger areas.

Your Task

Based on the literature given below and an already existing idea, you will do an extensive literature research on methods and metrics to measure the crowdedness of a situation. Based on your results, you first will be deriving and creating your own metric and impelement it for future application. Furthermore, you will take certain real-world and synthetic situations given to you, in order to investigate and evaluate all of these metrics exhaustively.

Requirements

  • SubjectComputer Science, Mathematics, Electrical Engineering, Applied Physics or comparable
  • Good programming skills (ideally Python and C++)
  • Basic understanding of computer vision and machine learning
  • Ability to work independently
  • Willingness and joy to explore new fields on your own and to bring your ideas to life

Literature

[1] Li et al.: “CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark” https://arxiv.org/abs/1812.00324