Real-Time, Cloud-Based Object Detection for Unmanned Aerial Vehicles
Real-time object detection is crucial for many applications of Unmanned Aerial Vehicles (UAVs) such asreconnaissance and surveillance, search-and-rescue, and infras-tructure inspection. In the last few years, Convolutional NeuralNetworks (CNNs) have emerged as a powerful class of modelsfor recognizing image content, and are widely considered inthe computer vision community to be the de facto standardapproach for most problems. However, object detection basedon CNNs is extremely computationally demanding, typicallyrequiring high-end Graphics Processing Units (GPUs) thatrequire too much power and weight, especially for a lightweightand low-cost drone. In this paper, we propose moving thecomputation to an off-board computing cloud, while keepinglow-level object detection and short-term navigation onboard. We apply Faster Regions with CNNs (R-CNNs), a state-of-the-art algorithm, to detect not one or two but hundreds of objecttypes in near real-time.