An authorized traffic controller (ATC) has the highest priority for direct road traffic. In some irregular situations, the ATC supersedes other traffic control. Human drivers indigenously understand such situations and tend to follow the ATC; however, an autonomous vehicle (AV) can become confused in such circumstances. Therefore, autonomous driving (AD) crucially requires a human-level understanding of situation-aware traffic gesture recognition. In AVs, vision-based recognition is particularly desirable because of its suitability; however, such recognition systems have various bottlenecks, such as failing to recognize other humans on the road, identifying a variety of ATCs, and gloves in the hands of ATCs. We propose a situation-aware traffic control hand-gesture recognition system, which includes ATC detection and gesture recognition. Three-dimensional (3D) hand model-based gesture recognition is used to mitigate the problem associated with gloves. Our database contains separate training and test videos of approximately 60 min length, captured at a frame rate of 24 frames per second. It has 35,291 different frames that belong to traffic control hand gestures. Our approach correctly recognized traffic control hand gestures; therefore, the proposed system can be considered as an extension of the operational domain of the AV.
Bibliographical noteFunding Information:
Acknowledgments: This work was supported by the Brain Pool Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Science and ICT (NRF-2019H1D3A1A01071115).
Funding: This work was mainly funded by the Brain Pool Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Science and ICT (NRF-2019H1D3A1A01071115). This work was partially funded by the Institute of Information & Communications Technology Planning & Evaluation (IITP) grant funded by the Korean government (MSIT) (No.2020-0-00056, to create AI systems that act appropriately and effectively in novel situations that occur in open worlds).
© 2021 by the authors. Licensee MDPI, Basel, Switzerland.
All Science Journal Classification (ASJC) codes
- Analytical Chemistry
- Information Systems
- Atomic and Molecular Physics, and Optics
- Electrical and Electronic Engineering