Detecting interpretable and accurate scale-invariant keypoints

Förstner, Wolfgang; Dickscheid, Timo; Schindler, Frank

doi:10.1109/iccv.2009.5459458

Cited by 82 publications

(70 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although the authors comment that the homographies are not perfect [9], the data set is used as ground truth for highaccuracy evaluations [6], [9], [12]. In addition to inaccurate homography matrices, the image data of the set is not suitable in several cases.…”

Section: Introductionmentioning

confidence: 99%

“…Commonly, the most important criterion for the accuracy of affine invariant detectors is the repeatability criterion [6], [10], [12], [20], [22], [23], [24] using the reference test set in [12]. The data set contains sequences of still images with changes in illumination, rotation, perspective, and scale.…”

Section: Introductionmentioning

confidence: 99%

“…[5], [6], affine transformation [7], [8], [9], [10], [11], [12], [13], [14], [15], and perspective transformation [16].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Increasing the accuracy of feature evaluation benchmarks using differential evolution

Cordes

Rosenhahn

Östermann

2011

2011 IEEE Symposium on Differential Evolution (SDE)

View full text Add to dashboard Cite

Abstract-The accuracy evaluation of image feature detectors is done using the repeatability criterion. Therefore, a wellknown data set consisting of image sequences and homography matrices is processed. This data serves as ground truth mapping information for the evaluation and is used in many computer vision papers.An accuracy validation of the benchmarks has not been done so far and is provided in this work. The accuracy is limited and evaluations of feature detectors may result in erroneous conclusions.Using a differential evolution approach for the optimization of a new, feature-independent cost function, the accuracy of the ground truth homographies is increased. The results are validated using comparisons between the repeatability rates before and after the proposed optimization. The new homographies provide better repeatability results for each detector. The repeatability rate is increased by up to 20%.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Increasing the accuracy of feature evaluation benchmarks using differential evolution

Cordes

Rosenhahn

Östermann

2011

2011 IEEE Symposium on Differential Evolution (SDE)

View full text Add to dashboard Cite

show abstract

“…as ground truth for high-accuracy evaluations, sometimes using very small overlap error thresholds [3,8,9]. Apart from feature evaluation there are applications [10] which use a dense representation of the images.…”

Section: Introductionmentioning

confidence: 99%

High-Resolution Feature Evaluation Benchmark

Cordes

Rosenhahn

Östermann

2013

Computer Analysis of Images and Patterns

View full text Add to dashboard Cite

Abstract. Benchmark data sets consisting of image pairs and ground truth homographies are used for evaluating fundamental computer vision challenges, such as the detection of image features. The mostly used benchmark provides data with only low resolution images. This paper presents an evaluation benchmark consisting of high resolution images of up to 8 megapixels and highly accurate homographies. State of the art feature detection approaches are evaluated using the new benchmark data. It is shown that existing approaches perform differently on the high resolution data compared to the same images with lower resolution.

show abstract

“…However, there are a lot of problems in unmanned aerial vehicle (UAV) imaging, such as irregular image overlapping, or large rotation deviation angle, so some di culties will be encounterd when the common method and software are used for the UAV images. in other words, a great deal of labor force and material resources are needed [14][15][16].…”

Section: Introductionmentioning

confidence: 99%

Comparisons of feature extraction algorithm based on unmanned aerial vehicle image

Shi

2017

Open Physics

View full text Add to dashboard Cite

Feature point extraction technology has become a research hotspot in the photogrammetry and computer vision. The commonly used point feature extraction operators are SIFT operator, Forstner operator, Harris operator and Moravec operator, etc. With the high spatial resolution characteristics, UAV image is di erent from the traditional aviation image. Based on these characteristics of the unmanned aerial vehicle (UAV), this paper uses several operators referred above to extract feature points from the building images, grassland images, shrubbery images, and vegetable greenhouses images. Through the practical case analysis, the performance, advantages, disadvantages and adaptability of each algorithm are compared and analyzed by considering their speed and accuracy. Finally, the suggestions of how to adapt di erent algorithms in diverse environment are proposed.

show abstract

Detecting interpretable and accurate scale-invariant keypoints

Cited by 82 publications

References 16 publications

Increasing the accuracy of feature evaluation benchmarks using differential evolution

Increasing the accuracy of feature evaluation benchmarks using differential evolution

High-Resolution Feature Evaluation Benchmark

Comparisons of feature extraction algorithm based on unmanned aerial vehicle image

Contact Info

Product

Resources

About