A Deep CNN-Based Framework For Enhanced Aerial Imagery Registration with Applications to UAV Geolocalization

Nassar, Ahmed; Amer, Karim; ElHakim, Reda; ElHelw, Mohamed

doi:10.1109/cvprw.2018.00201

Cited by 69 publications

(32 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For instance, Marcu et al [31] proposed a cascaded deep learning based semantic segmentation and regression framework for vision-based location map prediction. Ahmad Nassar et al [32] used a deep convolution neural network based method for aerial image matching and utilized it for localization of UAV. They exploited semantic shape matching and U-Net based segmentation to localize the current UAV frame onto a satellite map.…”

Section: Related Workmentioning

confidence: 99%

Assisting UAV Localization Via Deep Contextual Image Matching

Mughal

Khokhar²,

Shahzad

2021

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

In this paper, we aim to explore the potential of using onboard cameras and pre-stored geo-referenced imagery for Unmanned Aerial Vehicle (UAV) localization. Such a vision-based localization enhancing system is of vital importance, particularly in situations where the integrity of the global positioning system (GPS) is in question (i.e., in the occurrence of GPS outages, jamming, etc.). To this end, we propose a complete trainable pipeline to localize an aerial image in a pre-stored orthomosaic map in the context of UAV localization. The proposed deep architecture extracts the features from the aerial imagery and localizes it in a pre-ordained, larger, and geotagged image. The idea is to train a deep learning model to find neighborhood consensus patterns that encapsulate the local patterns in the neighborhood of the established dense feature correspondences by introducing semilocal constraints. We qualitatively and quantitatively evaluate the performance of our approach on real UAV imagery. The training and testing data is acquired via multiple flights over different regions. The source code along with the entire dataset, including the annotations of the collected images has been made public 1. Up-to our knowledge, such a dataset is novel and first of its kind which consists of 2052 high-resolution aerial images acquired at different times over three different areas in Pakistan spanning a total area of around 2 km 2 .

show abstract

Section: Related Workmentioning

confidence: 99%

Assisting UAV Localization Via Deep Contextual Image Matching

Mughal

Khokhar²,

Shahzad

2021

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Extremely remote regions such as deep sea [190,106], or space [181] can be efficiently explored with the help of intelligent robots making autonomous decisions. In sectors like defense, unmanned aerial vehicles or UAVs [154] are used to detect anomalies or threats in remote regions [119]. Segmentation algorithms have significant usage in satellite images for various geo-statistical analysis [109].…”

Section: Object Detectionmentioning

confidence: 99%

Understanding Deep Learning Techniques for Image Segmentation

et al. 2019

View full text Add to dashboard Cite

The machine learning community has been overwhelmed by a plethora of deep learning based approaches. Many challenging computer vision tasks such as detection, localization, recognition and segmentation of objects in unconstrained environment are being efficiently addressed by various types of deep neural networks like convolutional neural networks, recurrent networks, adversarial networks, autoencoders and so on. While there have been plenty of analytical studies regarding the object detection or recognition domain, many new deep learning techniques have surfaced with respect to image segmentation techniques. This paper approaches these various deep learning techniques of image segmentation from an analytical perspective. The main goal of this work is to provide an intuitive understanding of the major techniques that has made significant contribution to the image segmentation domain. Starting from some of the traditional image segmentation approaches, the paper progresses describing the effect deep learning had on the image segmentation domain. Thereafter, most of the major segmentation algorithms have been logically categorized with paragraphs dedicated to their unique contribution. With an ample amount of intuitive explanations, the reader is expected to have an improved ability to visualize the internal dynamics of these processes.

show abstract

“…A vision‐based framework for geolocating a UAV using its on‐board camera and satellite imagery was presented by Nassar et al. (2018). The proposed method allows navigation in Global Navigation Satellite System (GNSS) denied regions and improving existing GNSS modules.…”

Section: Previous Studiesmentioning

confidence: 99%

A new productive framework for point‐based matching of oblique aircraft and UAV‐based images

Baş

2021

The Photogrammetric Record

View full text Add to dashboard Cite

A novel productive framework for point‐based feature matching of oblique aircraft and UAV imagery is presented. The proposed framework makes use of the powerful AKAZE descriptor for feature extraction and an iterative scheme is developed to construct as many tentative matches as possible. During the iterations, cross checks, together with Lowe’s nearest‐next distance ratio test, are used to filter erroneous matches. In order to extract putative matches from the tentative matches, three robust approaches, including graph‐cut RANSAC, are evaluated along with the epipolar constraint enforced between the two datasets. The developed framework was validated using the ISPRS image orientation benchmark dataset and yielded successful results in terms of matching precision, even for some difficult cases. The results also outperformed the results of previously developed approaches in the same context.

show abstract

A Deep CNN-Based Framework For Enhanced Aerial Imagery Registration with Applications to UAV Geolocalization

Cited by 69 publications

References 45 publications

Assisting UAV Localization Via Deep Contextual Image Matching

Assisting UAV Localization Via Deep Contextual Image Matching

Understanding Deep Learning Techniques for Image Segmentation

A new productive framework for point‐based matching of oblique aircraft and UAV‐based images

Contact Info

Product

Resources

About