Potential of UAV-Based Pattern Classification with Convolutional Neural Network on Moderate/Low Quality UAV Data

This work serves as demonstrator, how low/medium quality UAV data can be integrated for agricultural pattern classification with convolutional neural network (CNN). The study also illustrates the potential sources of error in spectral and texture information that arise during image acquisition and p...

Full description

Saved in:
Bibliographic Details
Main Authors: Arslanova, Linara, Hese, Soren, Metz, Friederike, Schmullius, Christiane, Thau, Christian, Scheibler, Friedemann, Heckel, Kai, Folsch, Marcel, Urban, Marcel, Schultz, Michael
Format: Conference Proceeding
Language:English
Subjects:
agricultural pattern mapping
Autonomous aerial vehicles
CNN classification
Crops
data quality
Geoscience and remote sensing
Image processing
Pattern classification
Reflectivity
Soil
UAV imagery
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This work serves as demonstrator, how low/medium quality UAV data can be integrated for agricultural pattern classification with convolutional neural network (CNN). The study also illustrates the potential sources of error in spectral and texture information that arise during image acquisition and processing, which can be improved during image processing and correct choice of mosaicking parameters.CNN classification of six agricultural patterns of interest (weed infested area, dry and vital crop area, dry and vital lodged crop area, bare soil area) of corn, rapeseed, winter wheat and spring barley fields. The performance of the classification is assessed on images with different units (reflectance and DN) and images with different sun lightening conditions, shadows and 'blur' effects (moderate/low quality data).
ISSN:2153-7003
DOI:10.1109/IGARSS52108.2023.10282406