FPGA-based detection of SIFT interest keypoints

Chang, Leonardo; Hernández-Palancar, José; Sucar, L. Enrique; Arias-Estrada, Miguel

doi:10.1007/s00138-012-0430-8

Cited by 29 publications

(12 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Various SIFT implementations exist on parallel architectures including GPUs and FPGAs. 29,30 While these implementations incorporate the entire SIFT procedure, descriptor construction itself is amenable to parallelization. In addition, we crudely adapted the DSP matching algorithm of Kim et al in this work without investigating the possibility of tailoring the algorithm to this application.…”

Section: Discussionmentioning

confidence: 99%

SIFT-based dense pixel tracking on 0.35 T cine-MR images acquired during image-guided radiation therapy with application to gating optimization

et al. 2015

View full text Add to dashboard Cite

Tracking results show high fidelity in assessing intrafractional motion observed on cine-MR acquisitions. Incorporating harmonic analysis during a training period improves the robustness of the tracking for challenging targets. The concomitant gating optimization procedure should allow for physicians to quantitatively assess gating effectiveness quickly just prior to treatment in a patient-specific manner.

show abstract

Section: Discussionmentioning

confidence: 99%

SIFT-based dense pixel tracking on 0.35 T cine-MR images acquired during image-guided radiation therapy with application to gating optimization

et al. 2015

View full text Add to dashboard Cite

show abstract

“…With this optimization, the proposed system was able to detect the features of an image of a size of 640  480 pixels in 31 milliseconds. In [4], the authors presented a partial implementation of the SIFT algorithm, where they only implemented a feature extraction part. The proposed architecture is able to detect points of interest from an image of 320 × 240 pixels in 11 ms.…”

Section: Related Workmentioning

confidence: 99%

SIFT Implementation based on LEON3 Processor

Rashid¹,

Kaâniche²

2021

Adv. sci. technol. eng. syst. j.

View full text Add to dashboard Cite

This paper proposes a new method of implementation of the part of SIFT (Scale-InvariantFeature Transform) algorithm used to extract the feature of an image of a size 256256 of pixels, which is mainly based on the using the LEON3 soft core processor .With this method it is possible to detect points of interest and so perform matching. This process allows several real time applications as robotic navigation, stereovision, object recognition etc. Obtained results show a very robustness in rotation, scale invariant as well as luminosity change. SIFT algorithm saw big success in various applications of computer vision. However, its high computation complexity has been a challenge for the most part of embedded implementations. This paper presents a partial implementation of the SIFT algorithm, which is to implement just the extraction of the characteristics that is based on the LEON3 processor. This implementation method overcomes the existing problems, in particular, the high dependence of existing implementations on the hardware architecture used. Indeed, the high flexibility of the processor allows the possibility to develop the application independent of the target board.

show abstract

“…A disadvantage of SIFT is the heavy computations required for the keypoints, where typical processing times are tenths of seconds to multiple seconds per frame in a normal CPU implementation. 24,25 Developments in graphics processing units…”

Section: Target Trackingmentioning

confidence: 99%

“…(GPUs) and field programmable gate arrays (FPGAs) have created opportunities for real-time algorithms. SIFT implementations have been developed for both GPUs [25][26][27] and FPGAs, 24 where the results demonstrate real-time SIFT calculations. SIFT features are composed of a keypoint that gives subpixel location and orientation of the feature, along with a descriptor that is calculated based on local pixel texture.…”

Section: Target Trackingmentioning

confidence: 99%

Multispectral detection and tracking of multiple moving targets in cluttered urban environments

2015

View full text Add to dashboard Cite

This paper presents an algorithm for target detection and tracking by fusion of multispectral imagery. In all spectral bands, we build a background model of the pixel intensities using a Gaussian mixture model, and pixels not belonging to the model are classified as foreground pixels. Foreground pixels from the spectral bands are weighted and summed into a single foreground map and filtered to give the fused foreground map. Foreground pixels are grouped into target candidates and associated with targets from a tracking database by matching features from the scale-invariant feature transform. The performance of our algorithm was evaluated with a synthetically generated data set of visible, near-infrared, midwave infrared, and long-wave infrared video sequences. With a fused combination of the spectral bands, the proposed algorithm lowers the false alarm rate while maintaining high detection rates. All 12 vehicles were tracked throughout the sequence, with one instance of a lost track that was later recovered.

show abstract

FPGA-based detection of SIFT interest keypoints

Cited by 29 publications

References 13 publications

SIFT-based dense pixel tracking on 0.35 T cine-MR images acquired during image-guided radiation therapy with application to gating optimization

SIFT-based dense pixel tracking on 0.35 T cine-MR images acquired during image-guided radiation therapy with application to gating optimization

SIFT Implementation based on LEON3 Processor

Multispectral detection and tracking of multiple moving targets in cluttered urban environments

Contact Info

Product

Resources

About