Research, design and construct an autonomous human detection and tracking quadcopter prototype

running a Deep learning model like Object detection costs a lot of computational power, especially for an embedded computer like a Raspberry Pi. However, my work keeps the processing speed of the whole system fast enough for real-time implementation by combining an expensive Deep learning model with an inexpensive image-processing based tracking technique. The proposed method can achieve 3 to 4 FPS on Raspberry Pi which is faster than 0.63 FPS of the detection algorithm.
The thesis "Research, Design and Construct an Autonomous Human Detection and Tracking Quadcopter Prototype" has submitted the paper to the “International Conference on System Science and Engineering 2019 (ICSSE 2019)”, entitled "Human Detection and Tracking for Autonomous Human-following Quadcopter" and presented in appendices.
Bạn đang xem trang mẫu tài liệu này.