Improving UAV Ground Object Detection with Application of Machine Learning Mechanism

  • 李 駿宗

Student thesis: Master's Thesis

Abstract

The present main image surveillance methods can be divided into two categories aerial surveillance and ground surveillance The disadvantages of ground surveillance are the smaller detection range costing more time and environmental restriction Aerial surveillance is more suitable for a much larger spatial area and it has higher flexibility for complex environments This aerial surveillance system is mainly based on the machine learning algorithm to detect the objects which on the ground The process of proposed system are divided into two parts training process and testing process In system preparation the most important part of object detection is sample collection The system uses the common and obvious parts which in the vehicle behind as the the main characteristics such as wind screen wiper and lamps The collected samples are trained by using diverse train cascaded Haar-like feature classifier and LBP feature classifier in this thesis According the final experiment result it can improve effectively the detection rate false alarm rate and process speed after the image processing In this thesis three experiments are conducted including the data changes at different time different altitude and different attitude The final experiment results show the proposed detection system can run effectively on a dynamic platform all day with constant altitude to detect different vehicles The proposed detection system also can be applied on the UAVs or other flying devices in constant altitude or constant direction in order to be developed into further application such as real-time surveillance Keywords: Vehicle detection Gray level Blurring Median filter Machine learning Haar-like feature LBP feature AdaBoost Algorithm Cascading Classifier
Date of Award2016 Aug 15
Original languageEnglish
SupervisorChin-E. Lin (Supervisor)

Cite this

Improving UAV Ground Object Detection with Application of Machine Learning Mechanism
駿宗, 李. (Author). 2016 Aug 15

Student thesis: Master's Thesis