Autonomous Object Detection in Satellite Images Using Wfrcnn

Aburaed, Nour; Al-Saad, Mina; El, Marwa Chendeb; Mansoori, Saeed Al; Al-Ahmad, Hussain; Marshall, Stephen

doi:10.1109/ingarss48198.2020.9358948

Cited by 5 publications

(2 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, Fast RCNN uses the Selective Search method to find the Regions of Interest (ROIs), which is a time consuming process. To solve this problem, the authors in [15], [16] presented a Faster-RCNN (FRCNN) network, which is an upgraded version of Fast RCNN, through introducing Region Proposal Network (RPN). RPN is utilized to avoid Selective Search method, thus, it speeds up the training and detection processes, which in turns improves the overall performance of the model.…”

Section: B Faster-rcnnmentioning

confidence: 99%

Autonomous Palm Tree Detection from Remote Sensing Images - UAE Dataset

Al-Saad

Aburaed

Mansoori

et al. 2022

IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium

Self Cite

View full text Add to dashboard Cite

Autonomous detection and counting of palm trees is a research field of interest to various countries around the world, including the UAE. Automating this task saves effort and resources by minimizing human intervention and reducing potential errors in counting. This paper introduces a new High Resolution (HR) remote sensing dataset for autonomous detection of palm trees in the UAE. The dataset is collected using Unmanned Aerial Vehicles (UAV), and it is labeled properly in PASCAL VOC and YOLO formats after pre-processing and visually inspecting its quality. A comparative evaluation between Faster-RCNN and YOLOv4 networks is then conducted to observe the usability of the dataset in addition to the strengths and weaknesses of each network. The dataset is publicly available at https://github.com/NourO93/Palm-Tree-Dataset.

show abstract

Section: B Faster-rcnnmentioning

confidence: 99%

Autonomous Palm Tree Detection from Remote Sensing Images - UAE Dataset

Al-Saad

Aburaed

Mansoori

et al. 2022

IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium

Self Cite

View full text Add to dashboard Cite

show abstract

“…23 In that sense, FRCNN is considered as an upgraded version of RCNN. 24 The purpose of utilizing RPN is to avoid the slower Selective Search algorithm to select regions of interest and, thus, it speeds up the training process and boosts the overall performance of the model. 25…”

Section: Faster R-cnnmentioning

confidence: 99%

Airbus ship detection from satellite imagery using frequency domain learning

Al-Saad

Aburaed

Panthakkan

et al. 2021

Image and Signal Processing for Remote Sensing XXVII

Self Cite

View full text Add to dashboard Cite

Ship detection from remote sensing images has been a topic of interest that gradually gained attention over the years due to the wide variety of its applications in the field of maritime surveillance, such as oil discharge control, sea pollution monitoring, and harbour management. Even though there is an extensive amount of methods developed for ship detection, there are still several challenges that remain unsolved, especially in complex environments. These challenges include occlusions due to shadows, clouds, and fog. Nowadays, deep learning algorithms, especially Deep Convolutional Neural Networks (DCNNs), are considered as a powerful approach for automatically detecting ships in satellite imagery. In this paper, enhanced Faster R-CNN (FRCNN) model will be used to overcome the aforementioned unsolved challenges. The enhanced FRCNN, which combines high level features with low level features, will be trained and tested in the frequency domain using the publicly available satellite imagery dataset, Airbus Ship Detection, provided by Kaggle. The performance will be compared to the original FRCNN based on their Overall Accuracy (OA) and Mean Average Precision (mAP) metrics.

show abstract