A comparative analysis of SIFT, SURF, KAZE, AKAZE, ORB, and BRISK

Tareen, Shaharyar Ahmed Khan; Saleem, Zahra

doi:10.1109/icomet.2018.8346440

Cited by 383 publications

(180 citation statements)

References 24 publications

Supporting

Mentioning

173

Contrasting

Unclassified

Order By: Relevance

“…Many popular algorithms automatically recognize, extract, and match keypoints between frames without any a priori knowledge, using corner and blob recognition under similar illumination conditions [50]. Examples of widely used feature detection algorithms are: SIFT (Scale-Invariant Feature Transform; [29,30]), FAST (Features from Accelerated Segment Test; [51]), and SURF (Speeded-Up Robust Features; [31]).…”

Section: Canny Edge Detectormentioning

confidence: 99%

A Simple and Efficient Image Stabilization Method for Coastal Monitoring Video Systems

et al. 2019

View full text Add to dashboard Cite

Fixed video camera systems are consistently prone to importune motions over time due to either thermal effects or mechanical factors. Even subtle displacements are mostly overlooked or ignored, although they can lead to large geo-rectification errors. This paper describes a simple and efficient method to stabilize an either continuous or sub-sampled image sequence based on feature matching and sub-pixel cross-correlation techniques. The method requires the presence and identification of different land-sub-image regions containing static recognizable features, such as corners or salient points, referred to as keypoints. A Canny edge detector ( C E D ) is used to locate and extract the boundaries of the features. Keypoints are matched against themselves after computing their two-dimensional displacement with respect to a reference frame. Pairs of keypoints are subsequently used as control points to fit a geometric transformation in order to align the whole frame with the reference image. The stabilization method is applied to five years of daily images collected from a three-camera permanent video system located at Anglet Beach in southwestern France. Azimuth, tilt, and roll deviations are computed for each camera. The three cameras showed motions on a wide range of time scales, with a prominent annual signal in azimuth and tilt deviation. Camera movement amplitude reached up to 10 pixels in azimuth, 30 pixels in tilt, and 0.4° in roll, together with a quasi-steady counter-clockwise trend over the five-year time series. Moreover, camera viewing angle deviations were found to induce large rectification errors of up to 400 m at a distance of 2.5 km from the camera. The mean shoreline apparent position was also affected by an approximately 10–20 m bias during the 2013/2014 outstanding winter period. The stabilization semi-automatic method successfully corrects camera geometry for fixed video monitoring systems and is able to process at least 90% of the frames without user assistance. The use of the C E D greatly improves the performance of the cross-correlation algorithm by making it more robust against contrast and brightness variations between frames. The method appears as a promising tool for other coastal imaging applications such as removal of undesired high-frequency movements of cameras equipped in unmanned aerial vehicles (UAVs).

show abstract

Section: Canny Edge Detectormentioning

confidence: 99%

A Simple and Efficient Image Stabilization Method for Coastal Monitoring Video Systems

et al. 2019

View full text Add to dashboard Cite

show abstract

“…These processes result in a scale invariant sparse point cloud (see Figure 15B). Although SIFT is the most commonly feature extraction algorithm used in UAS processing software packages, different approaches, i.e., SURF, KAZE, AKAZE, ORB, and BRISK have been successfully used for image matching for mapping purposes [68][69][70]. In order to increase the density of the point cloud, a conceptual extension of stereo photogrammetry with the use of multiple images (MVS) instead of stereo-pairs, is implemented [71], resulting in the generation of a denser point cloud (see Figure 15C).…”

Section: Surface Reconstruction and Structure From Motion (Sfm)mentioning

confidence: 99%

UAS for Wetland Mapping and Hydrological Modeling

Jeziorska

2019

Remote Sensing

View full text Add to dashboard Cite

The miniaturization and affordable production of integrated microelectronics have improved in recent years, making unmanned aerial systems (UAS) accessible to consumers and igniting their interest. Researchers have proposed UAS-based solutions for almost any conceivable problem, but the greatest impact will likely be in applications that exploit the unique advantages of the technology: work in dangerous or difficult-to-access areas, high spatial resolution and/or frequent measurements of environmental phenomena, and deployment of novel sensing technology over small to moderate spatial scales. Examples of such applications may be the identification of wetland areas and use of high-resolution spatial data for hydrological modeling. However, because of the large—and growing—assortment of aircraft and sensors available on the market, an evolving regulatory environment, and limited practical guidance or examples of wetland mapping with UAS, it has been difficult to confidently devise or recommend UAS-based monitoring strategies for these applications. This paper provides a comprehensive review of UAS hardware, software, regulations, scientific applications, and data collection/post-processing procedures that are relevant for wetland monitoring and hydrological modeling.

show abstract

“…The absolute positioning of salient features on the ground (ex., crossroads) can be measured and served as a reference. If an orthoimage over the same area of interest is available, this image can be used as a reference, and ITPs can be computed by using any feature detection algorithm, such as AKAZE, ORB, etc (Tareen , Saleem, 2018). The detected ITPs can be further filtered to keep only the points on the ground, by using one of the following approaches:…”

Section: Construction Of Epipolar Imagesmentioning

confidence: 99%

Automated Chain for Large-Scale 3d Reconstruction of Urban Scenes From Satellite Images

Tripodi¹,

Duan²,

Trastour³

et al. 2019

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Automatic city modeling from satellite imagery is a popular yet challenging topic in remote sensing, driven by numerous applications such as telecommunications, defence and urban mamagement. In this paper, we present an automated chain for large-scale 3D reconstruction of urban scenes with a Level of Detail 1 from satellite images. The proposed framework relies on two key ingredient. First, from a stereo pair of images, we estimate a digital terrain model and a digital height model, by using a novel set of feature descriptors based on multiscale morphological analysis. Second, inspired by recent works in machine learning, we extract in an automatic way contour polygons of buildings, by adopting a fully convolutional network U-Net followed by a polygonization of the predicted mask of buildings. We demonstrate the potential of our chain by reconstructing in an automated way different areas of the world.

show abstract

A comparative analysis of SIFT, SURF, KAZE, AKAZE, ORB, and BRISK

Cited by 383 publications

References 24 publications

A Simple and Efficient Image Stabilization Method for Coastal Monitoring Video Systems

A Simple and Efficient Image Stabilization Method for Coastal Monitoring Video Systems

UAS for Wetland Mapping and Hydrological Modeling

Automated Chain for Large-Scale 3d Reconstruction of Urban Scenes From Satellite Images

Contact Info

Product

Resources

About