Drone Chase: A Mobile and Automated Cross-Modality System for Continuous Drone Tracking is a work by Neel R. Vora, Yi Wu, Jian Liu, and Phuc Nguyen.
In this work DroneChase, an automated sensing system designed to monitor acoustic and visual signals captured from a nearby flying drone, is introduced. DroneChase is specifically engineered to track the trajectory of drones in various scenarios, including both line-of-sight and non-line-of-sight conditions, all while the drones are in motion.
While drone monitoring has been a subject of active research, many existing systems primarily address line-of-sight situations and struggle when dealing with obstructed conditions. Taking inspiration from humans’ ability to locate objects in their surroundings using visual and auditory cues, we have developed a mobile system combining information from multiple sensory modalities to achieve real-time drone detection and trajectory tracking.
The Raspberry Pi platform powers the system and gathers acoustic signals from six strategically positioned hexagonal channels, each spaced 5 cm apart. Additionally, it captures video data from an HD RGB camera. This monitoring setup is placed within a mobile vehicle, allowing it to effectively track drones, even when flying or hovering behind obstacles such as bushes or trees.
Its portability sets the DroneChase system apart, enabling continuous drone tracking. This means it can provide uninterrupted monitoring and tracking, even while on the move. Furthermore, the system’s performance is consistent in daylight and nighttime conditions, making it a versatile solution for tracking drones in various environmental settings.
Publication Date– June 2023
Drone Chase: A Mobile and Automated Cross-Modality System for Continuous Drone Tracking contains the following major sections:
- System Overview
- Related Work
- Conclusion and Future Work
This work is licensed under Attribution 4.0 International (CC BY 4.0).
C-UAS Hub does not own this content and provides a link for users below and at the bottom of the page to access the document in its original location. This allows the author(s) to track essential metrics related to their work. All credit goes to its rightful owner.
Authors: Neel R. Vora, Yi Wu, Jian Liu, and Phuc Nguyen
Image Credit: envatoelements by TDyuvbanova)