Local Feature Performance Evaluation for Structure-From-Motion and Multi-View Stereo Using Simulated City-Scale Aerial Imagery

Gao, Ke; Aliakbarpour, Hadi; Fraser, Joshua; Nouduri, Koundinya; Bunyak, Filiz; Massaro, Richard; Seetharaman, Guna; Palaniappan, Kannappan

doi:10.1109/jsen.2020.3042810

Cited by 13 publications

(8 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Using these associated GPS coordinates, for each image we selected its k nearest neighbors using the following approach. For each pair of neighboring images, we extracted the SIFT keypoint locations and descriptors and computed putative matches using the two nearest neighbours in the descriptor space, dropping second neighbours whose score was not less than 80% of the first one as used by many others (e.g., [44], [45]). We used k = 4 and k = 8 for the drone and gantry experiments respectively.…”

Section: Methodsmentioning

confidence: 99%

MegaStitch: Robust Large-Scale Image Stitching

Zarei

Gonzalez

Merchant

et al. 2022

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

We address fast image stitching for large image collections while being robust to drift due to chaining transformations and minimal overlap between images. We focus on scientific applications where ground truth accuracy is far more important than visual appearance or projection error, which can be misleading. For common largescale image stitching use cases, transformations between images are often restricted to similarity or translation. When homography is used in these cases, the odds of being trapped in a poor local minimum and producing unnatural results increases. Thus, for transformations up to affine, we cast stitching as minimizing reprojection error globally using linear least squares with a few, simple constraints. For homography, we observe that the global affine solution provides better initialization for bundle adjustment compared to an alternative that initializes with a homography-based scaffolding, and at lower computational cost. We evaluate our methods on a very large translation dataset with limited overlap, as well as four drone datasets. We show that our approach is better compared to alternative methods such as MGRAPH in terms of computational cost, scaling to large numbers of images, and robustness to drift. We also contribute ground truth datasets for this endeavor.

show abstract

Section: Methodsmentioning

confidence: 99%

MegaStitch: Robust Large-Scale Image Stitching

Zarei

Gonzalez

Merchant

et al. 2022

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Local feature descriptors are widely used in image matching algorithms to align two or more images of a scene or an object taken from different viewpoints. Such algorithms are used in structure-from-motion (SfM) and multiview-stereo (MVS) estimations [1], object tracking [2], ID document localization [3] [4], and other practical tasks. The image matching algorithms that use local-feature descriptors are called feature-based image matching [5].…”

Section: Introductionmentioning

confidence: 99%

Fast Computation of RFD-Like Descriptors in Four Orientations

Trusov

Limonova²,

Arlazarov³

2023

IEEE Access

View full text Add to dashboard Cite

RFD-like binary descriptors have been designed to be fast and demonstrate good quality in image-matching tasks. One of those descriptors, RFDoc, produces state-of-the art results when applied to document localization systems. However, the computational efficiency of such descriptors strongly depends on their implementation. In this study, we consider the computation of RFD-like descriptors for an 8bit single-channel image; provide a detailed implementation of the baseline algorithm; demonstrate its weak points; and propose four modifications. In those modifications, we investigate two ways to accelerate the descriptor computations: 1) compute common operations globally for the entire input image instead of computing them locally for every patch; or 2) use lookup tables to replace the most computationally demanding operations and minimize the number of conversions between integer and floating point types. Experiments on the document identification and localization task on the MIDV-2020 dataset have shown that the modifications with lookup tables are noticeably faster than the baseline, achieving a 2-2.6 times acceleration on x86 and ARM CPUs. Based on experimental results, modifications with global operations may outperform the baseline algorithm if there are many intersecting patches that require descriptor computation. We also demonstrated that one can use any of the proposed algorithms without loss of image-matching quality and without necessity to retrain the parameters of RFD-like descriptors. Finally, we propose an efficient way to compute the descriptors for four orientations of a patch, which is a important for document location systems. The proposed method reduces a common computation part for four orientations to a single run; thus, four descriptors are computed 3 times faster than the direct computation of the descriptors for four patches, as shown experimentally.

show abstract

“…Corresponding features in each track are triangulated into a single 3D point. A sparse 3D point cloud is the result of triangulating corresponding features in all tracks [9]. More images can be incorporated into the current model using image registration.…”

Section: Introductionmentioning

confidence: 99%

Towards a Fair Evaluation of Feature Extraction Algorithms Robustness in Structure from Motion

Taha¹,

Zayed²,

El-Mashad³

2022

IJACSA

View full text Add to dashboard Cite

Structure from Motion is a pipeline for 3D reconstruction in which the true geometry of an object or a scene is inferred from a sequence of 2D images. As feature extraction is usually the first phase in the pipeline, the reconstruction quality depends on the accuracy of the feature extraction algorithm. Fairly evaluating the robustness of feature extraction algorithms in the absence of reconstruction ground truth is challenging due to the considerable number of parameters that affect the algorithms' sensitivity and the tradeoff between reconstruction size and error. The evaluation methodology proposed in this paper is based on two elements. The first is using constrained 3D reconstruction, in which only fixed numbers of extracted and matched features are passed to subsequent phases. The second is comparing the 3D reconstructions using size-error curves (introduced in this paper) rather than the value of reconstruction size, error, or both. The experimental results show that the proposed methodology is more transparent.

show abstract

Local Feature Performance Evaluation for Structure-From-Motion and Multi-View Stereo Using Simulated City-Scale Aerial Imagery

Cited by 13 publications

References 41 publications

MegaStitch: Robust Large-Scale Image Stitching

MegaStitch: Robust Large-Scale Image Stitching

Fast Computation of RFD-Like Descriptors in Four Orientations

Towards a Fair Evaluation of Feature Extraction Algorithms Robustness in Structure from Motion

Contact Info

Product

Resources

About