Researchers develop high quality design methods for real-time video from weated aviation vehicles

Researchers at Tsukuba University have developed the SPADE (Simulator-assisted Performance Design Methodology for UAV-based Systems) approach for accurate quality assessment of irregular aviation vehicle (UAV) video surveillance systems. This work is published in the Journal Future Generation Computer Systems.

The computer-equipped UAV video surveillance system allows you to monitor real-time images of areas that are not easily accessible to humans. However, it is difficult to design a high-quality, reliable video surveillance system that properly integrates computers, UAVs, networks and surveillance software.

During the early design stage, it is a complicated task to assess quality and consider uncertain factors that may affect system performance before the system is implemented in the field.

SPADE creates a virtual environment that is very similar to the actual operating environment of a UAV video surveillance system. Using video data from UAVs flying in this virtual environment, SPADE allows for detailed quality assessments without any actual operation.

SPADE collects virtual images using a UAV flight simulator. The recorded images are processed by a real computer that measures the processing accuracy, performance and power consumption of the UAV.

These data have been introduced into the system’s state transition model for quality assessment and trade-off analysis. The spade method can assess the effect of differences in resolution between input images on the quality of the system for real-time object detection by UAVs.

Through this approach, various UAV video surveillance systems can be designed. Future research will develop methods to efficiently design complex large-scale systems with multiple UAVs operating in tuning.