Active shooter detection and robust tracking utilizing supplemental synthetic data
This addresses public safety concerns related to gun violence by developing a system to detect and track shooters, but it is incremental as it builds on existing detection and tracking methods with synthetic data enhancements.
The paper tackled the problem of detecting and tracking active shooters by proposing to detect shooters as a whole instead of just guns, improving tracking robustness when guns are obscured, and used synthetic data from Unreal Engine with domain randomization and transfer learning to train a system based on YOLOv8 and Deep OC-SORT that runs on edge hardware like Raspberry Pi and Jetson Nano.
The increasing concern surrounding gun violence in the United States has led to a focus on developing systems to improve public safety. One approach to developing such a system is to detect and track shooters, which would help prevent or mitigate the impact of violent incidents. In this paper, we proposed detecting shooters as a whole, rather than just guns, which would allow for improved tracking robustness, as obscuring the gun would no longer cause the system to lose sight of the threat. However, publicly available data on shooters is much more limited and challenging to create than a gun dataset alone. Therefore, we explore the use of domain randomization and transfer learning to improve the effectiveness of training with synthetic data obtained from Unreal Engine environments. This enables the model to be trained on a wider range of data, increasing its ability to generalize to different situations. Using these techniques with YOLOv8 and Deep OC-SORT, we implemented an initial version of a shooter tracking system capable of running on edge hardware, including both a Raspberry Pi and a Jetson Nano.