ePrints@IIScePrints@IISc Home | About | Browse | Latest Additions | Advanced Search | Contact | Help

Event-Based Time-To-Contact Estimation with Depth Image Fusion

Gupta, A and Sharma, P and Ghosh, D and Honkote, V and Ghose, D (2023) Event-Based Time-To-Contact Estimation with Depth Image Fusion. In: 3rd International Congress on Intelligent Systems, CIS 2022, 5 - 6 September 2022, Bangalore, pp. 65-77.

Full text not available from this repository. (Request a copy)
Official URL: https://doi.org/10.1007/978-981-19-9379-4_6


Reliable and fast sensing are the keys to implement effective high-speed obstacle avoidance strategies in modern quadrotors. A class of bio-inspired sensors, commonly called as event cameras, are suitable for this application. It can generate events at microsecond resolution. Output data rate of events depends on the texture and relative speed between the object and camera. Event cameras are good at capturing small changes, but data output lacks the low-level scene details. In this paper, we present an algorithm that fuses the low temporal resolution data from the depth camera with an event camera to compute time-to-contact (TTC) with an obstacle. In this approach, we use low-frequency information from depth camera to identify a dynamic obstacle and use event stream to perform TTC computation. This algorithm is integrated in Airsim simulator and tested with dynamic obstacle in various collision scenarios.

Item Type: Conference Paper
Publication: Lecture Notes in Networks and Systems
Publisher: Springer Science and Business Media Deutschland GmbH
Additional Information: The copyright for this article belongs to the Springer Science and Business Media Deutschland GmbH.
Keywords: Computer vision; Event camera; Robotics; Time-to-contact
Department/Centre: Division of Mechanical Sciences > Aerospace Engineering(Formerly Aeronautical Engineering)
Date Deposited: 13 Jul 2023 09:47
Last Modified: 13 Jul 2023 09:47
URI: https://eprints.iisc.ac.in/id/eprint/82410

Actions (login required)

View Item View Item