TY  - MANSCPT
AU  - Aiman Fithri Bin Tharmizi
TI  - Auto object recognition classification based on unmanned aerial vehicle (UAV)/drone  orthophoto using fast RCNN
SN  - THE0010042 (Local)
PY  - 2023///
CY  - Kuantan Pahang
PB  - UMPSA
KW  - Center for Mathematical Sciences
KW  - Dissertations
KW  - Universities and colleges
KW  - Final Year Report
N1  - Center for Mathematical Sciences; Bachelor of Applied Science In Data Analytics With Honour -- Universiti Malaysia Pahang – 2023; Includes bibliographical references
N2  - Malaysia has seen an increase in the number of strange or random objects on its  roads in recent years. The increasing use of unmanned aerial vehicles (UAVs) for aerial  imaging has led to the availability of large amounts of aerial imagery data. This data  can be used for various applications, including object recognition and classification. In  this research, we propose an "Auto Object Recognition Classification Based on  Unmanned Aerial Vehicle (UAV)/Drone Orthophoto Using Fast RCNN" to automate  the process of object recognition and classification from UAV/drone orthophotos.  Therefore, this problem has caused many problems for road users, such as traffic, road  damage, and accidents. Some businesses still use manual object recognition, which  takes time and effort. The objective of this project is to analyse the orthophoto and  generate a classification of object detection by achieving an accuracy of 50% or above  and faster than manual digitization of the object. Convolutional neural network (CNN)  techniques will be used to train the system. MySpatial Sdn Bhd will provide the dataset  by detecting the object using object detection classification using drone orthophoto. The  proposed algorithm will use deep learning techniques and computer vision methods to  extract relevant features from the UAV/drone orthophotos and classify objects into  different categories. The algorithm will be implemented using Python and evaluated  based on its accuracy, efficiency, and scalability. The results of this research will  contribute to the development of more efficient and effective object recognition and  classification algorithms for UAV/drone orthophotos. The findings of this research will  be useful for various applications, including urban planning, environmental monitoring,  and disaster management. The proposed algorithm has the potential to provide accurate  and timely information for decision-making and resource allocation in these domains
ER  -