Evaluation of interest point detectors for scenes with changing lightening conditions

Zukal, Martin; Číka, Petr; Bürget, Radim

doi:10.1109/tsp.2011.6043663

Cited by 7 publications

(6 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We can compare the results from [25] and [26] with the experiment where the brightness of the image was changed and the repeatability of detectors was measured. Different datasets are used for evaluation in the aforementioned papers.…”

Section: Discussionmentioning

confidence: 99%

“…The Harris detector achieved better results than its scale-invariant counterpart which means that the HarrisLaplace detector tends to favor points that are scale invariant over the ones that are stable under change of brightness. In [26], the Fast Hessian and DoG detectors notably outperformed the Harris-Laplace detector especially when the image was darkened. These results were more or less confirmed also in our study.…”

Section: Discussionmentioning

confidence: 99%

“…As we deal with modifications that do not change scale of the image it can be expected that the results of the Harris and Harris-Laplace algorithm will be similar in terms of change of brightness. An evaluation of the Harris-Laplace, Fast Hessian and DoG detectors with respect to change of brightness was performed in [26]. The performance of interest point detectors for tracking purposes in image sequence was evaluated in [27].…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Towards an Optimal Interest Point Detector for Measurements in Ultrasound Images

Zukal¹,

Beneš²,

Číka³

et al. 2013

Measurement Science Review

Self Cite

View full text Add to dashboard Cite

This paper focuses on the comparison of different interest point detectors and their utilization for measurements in ultrasound (US) images. Certain medical examinations are based on speckle tracking which strongly relies on features that can be reliably tracked frame to frame. Only significant features (interest points) resistant to noise and brightness changes within US images are suitable for accurate long-lasting tracking. We compare three interest point detectors -Harris-Laplace, Difference of Gaussian (DoG) and Fast Hessian -and identify the most suitable one for use in US images on the basis of an objective criterion. Repeatability rate is assumed to be an objective quality measure for comparison. We have measured repeatability in images corrupted by different types of noise (speckle noise, Gaussian noise) and for changes in brightness. The Harris-Laplace detector outperformed its competitors and seems to be a sound option when choosing a suitable interest point detector for US images. However, it has to be noted that Fast Hessian and DoG detectors achieved better results in terms of processing speed.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Towards an Optimal Interest Point Detector for Measurements in Ultrasound Images

Zukal¹,

Beneš²,

Číka³

et al. 2013

Measurement Science Review

Self Cite

View full text Add to dashboard Cite

show abstract

“…There are also extensive works that evaluate the algorithms from which the ones by Mikolajczyk [4], [5] stand out.…”

Section: Introductionmentioning

confidence: 99%

“…The repeatability rate [4] is one of widely accepted measures for evaluation of the algorithms. We will, nevertheless, focus on a less popular measure referred to as the information content which measures the distinctiveness of the point.…”

Section: Introductionmentioning

confidence: 99%

Corner detectors: Evaluation of information content

Zukal

Číka

2012

2012 35th International Conference on Telecommunications and Signal Processing (TSP)

Self Cite

View full text Add to dashboard Cite

This paper aims at the comparison of different corner detectors in terms of information content. Specifically, the FAST, Harris, Harris-Laplace and KLT detector are tested. We prove a hypothesis that the neighborhood of points detected by interest point detectors conveys more information than randomly selected points. The information content was computed from the 8x8 neighborhood of the detected points using entropy. From the qualitative point of view, we have observed that the Harris detector performed best in this measurement and was closely followed by the KLT detector.

show abstract