A Review on Deep Learning in UAV Remote Sensing

  title={A Review on Deep Learning in UAV Remote Sensing},
  author={Lucas Prado Osco and Jos{\'e} Marcato Junior and Ana Paula Marques Ramos and L{\'u}cio Abdr{\'e} de Castro Jorge and Sarah Narges Fatholahi and Jonathan de Andrade Silva and Edson Takashi Matsubara and Hemerson Pistori and Wesley Nunes Gonçalves and Jonathan Li},
  journal={Int. J. Appl. Earth Obs. Geoinformation},
Deep Neural Networks (DNNs) learn representation from data with an impressive capability, and brought important breakthroughs for processing images, time-series, natural language, audio, video, and many others. In the remote sensing field, surveys and literature revisions specifically involving DNNs algorithms’ applications have been conducted in an attempt to summarize the amount of information produced in its subfields. Recently, Unmanned Aerial Vehicles (UAV) based applications have… Expand

Figures and Tables from this paper

Multiscale Object Detection from Drone Imagery Using Ensemble Transfer Learning
An implementation of ensemble transfer learning to enhance the performance of the base models for multiscale object detection in drone imagery and a test-time augmentation pipeline that combines different models and applies voting strategies to detect objects of various scales in UAV images. Expand
A Deep Learning Approach Based on Graphs to Detect Plantation Lines
A deep learning approach based on graphs to detect plantation lines in UAV-based RGB imagery presenting a challenging scenario containing spaced plants, which was compared against state-of-the-art deep learning methods and achieved superior performance. Expand
Convolutional Neural Networks to Estimate Dry Matter Yield in a Guineagrass Breeding Program Using UAV Remote Sensing
A convolutional neural network approach using UAV-RGB imagery to estimate dry matter yield traits in a guineagrass breeding program and HTP trait from ResNeXt50 pretrained achieved the best results for indirect selection regardless of the dry matter trait demonstrates that CNNs with remote sensing data are highly promising for HTP for dry matterield traits in forage breeding programs. Expand
Advancing Tassel Detection and Counting: Annotation and Algorithms
Three state-of-the-art DL techniques, CenterNet based on point annotation, task-aware spatial disentanglement (TSD), and detecting objects with recursive feature pyramids and switchable atrous convolution (DetectoRS) based on bounding box annotation, are modified to improve their performance and evaluated for tassel detection relative to Tasselnetv2+. Expand
Evolution of Non-Terrestrial Networks From 5G to 6G: A Survey
This article comprehensively surveys the evolution of NTNs highlighting its relevance to 5G networks and essentially, how it will play a pivotal role for the development of 6G and beyond wireless networks. Expand
Deep Learning for UAV-based Object Detection and Tracking: A Survey
  • Xin Wu, Wei Li, Danfeng Hong, Ran Tao, Qian Du
  • Computer Science
  • 2021
This is the pre-acceptance version, to read the final version please go to IEEE Geoscience and Remote Sensing Magazine on IEEE Xplore. Owing to effective and flexible data acquisition, unmannedExpand


A review of deep learning methods for semantic segmentation of remote sensing imagery
A summary of the fundamental deep neural network architectures and the most recent developments of deep learning methods for semantic segmentation of remote sensing imagery including non-conventional data such as hyperspectral images and point clouds are reviewed. Expand
A Comprehensive Survey of Deep Learning in Remote Sensing: Theories, Tools and Challenges for the Community
This work focuses on theories, tools, and challenges for the RS community, and focuses on unsolved challenges and opportunities as they relate to inadequate data sets, big data, and human-understandable solutions for modeling physical phenomena. Expand
A Study on the Detection of Cattle in UAV Images Using Deep Learning
Results revealed that many CNN architectures are robust enough to reliably detect animals in aerial images even under far from ideal conditions, indicating the viability of using UAVs for cattle monitoring. Expand
Deep learning for remote sensing image classification: A survey
A systematic review of pixel‐wise and scene‐wise RS image classification approaches that are based on the use of DL and a comparative analysis regarding the performances of typical DL‐based RS methods are provided. Expand
Survey of Deep-Learning Approaches for Remote Sensing Observation Enhancement
This paper provides a comprehensive review of deep-learning methods for the enhancement of remote sensing observations, focusing on critical tasks including single and multi-band super-resolution, denoising, restoration, pan-sharpening, and fusion, among others. Expand
Deep learning in environmental remote sensing: Achievements and challenges
The potential of DL in environmental remote sensing, including land cover mapping, environmental parameter retrieval, data fusion and downscaling, and information reconstruction and prediction, will be analyzed and a typical network structure will be introduced. Expand
Road Extraction from Unmanned Aerial Vehicle Remote Sensing Images Based on Improved Neural Networks
Improved neural networks are helpful in reducing the network size and developing the precision needed for road extraction in Unmanned Aerial Vehicle (UAV) remote sensing images. Expand
Deep learning in remote sensing applications: A meta-analysis and review
This review covers nearly every application and technology in the field of remote sensing, ranging from preprocessing to mapping, and a conclusion regarding the current state-of-the art methods, a critical conclusion on open challenges, and directions for future research are presented. Expand
Assessment of CNN-Based Methods for Individual Tree Detection on Images Captured by RGB Cameras Attached to UAVs
Three state-of-the-art object detection methods were evaluated: Faster Region-based Convolutional Neural Network (Faster R-CNN), YOLOv3 and RetinaNet, and delivered average precision around 92% with an associated processing times below 30 miliseconds. Expand
Landscape Classification with Deep Neural Networks
This work presents an efficient approach to train/apply DCNNs with/on sets of photographic images, using a powerful graphical method called a conditional random field (CRF) to generate DCNN training and testing data using minimal manual supervision, and synthesizes the findings to examine the general effectiveness of transfer learning to landscape-scale image classification. Expand