Abstract
Abstract
The developing of object detection for many purpose has come to various techniques. Some of those works also implement to solve our daily life problem. Those development which are state-of-the-art are mostly applicable with many pros than others. In this paper we use one of state-of-the-art of object detection to control a quadcopter i.e. Single Shot MultiBox Detector (SSD). SSD is used to detect an object as quadcopter target for approach mission. SSD also use to keep an eye of the target. The target is represented in shape of ROI location. This ROI or a bounding box location is used as feedback of the control system of quadcopter which will guide the quadcopter to approach. The mission is considered as success if the quadcopter is stopped at minimum range 1 meter toward target. This works shows the successful of object detection implementation by serving IMU responses and measured distance to object responses.
Subject
General Physics and Astronomy
Reference10 articles.
1. Faster R-CNN: Towards Real-time Object Detection with Region Proposal Networks;Shaoqing;International Conference on Neural Information Processing Systems,2015
2. The Pascal Visual Object Classes Challenge: A Retrospective;Everingham;International Journal of Computer Vision,2015
3. Microsoft COCO: Common Objects in Context;Lin,2014
4. Learning Multiple Layers of Features from Tiny Images;Alex,2012
Cited by
2 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献