A MultiScale Particle Filter Framework for Contour Detection

Widynski, Nicolas; Mignotte, Maurice

doi:10.1109/tpami.2014.2307856

Cited by 23 publications

(16 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To evaluate our algorithm and to estimate this important internal parameter, we replicated the scenario proposed in [6][7][8][9][10][11][12][13][14][15][16]73], using the BSDS300 and the F-measure. 3 In order to ensure the integrity of the evaluation, the internal parameter N s of our algorithm is tuned on the train image set (pre-defined by the author of the BSDS300), by doing a local discrete grid search routine, with a fixed step size, on the parameter space and in a given range of parameter values (namely, N s 2 ½30 À 300 [step size : 30].…”

Section: Set Upmentioning

confidence: 99%

“…In addition, the BSDS300 has also allowed to especially understand and to quantify the relative importance of color and texture in the contour detection process [6], the benefit of contour grouping [7,8] and multiscale models and features over monoscale approaches [10,12], the interest of combining regions (or global information) and boundary cues [9,11,13,14], the benefit of learning the prior (and transition) distribution of pieces of contour shapes [15] or the advantage of learning to classify [16,17] to name a few.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A biologically inspired framework for contour detection

Mignotte

2015

Pattern Anal Applic

Self Cite

View full text Add to dashboard Cite

In this paper, we present a simple and efficient biologically inspired edge detection algorithm which attempts to model some structural features of the Human Visual System. More precisely, our edge detection approach attempts to model the dynamic retina concept, i.e., the natural saccadic eye movement process which redirects the fovea's attention from one point of interest to another within the image along with the inherent topological log-polar transformation (with its space-variant resolution) of the retinal image into its cortical projection. The experiments, reported in this paper and conducted on the Berkeley Segmentation Dataset, demonstrate that the proposed biologically inspired contour detection method performs well compared to the best existing state-of-the-art edge and contour detection methods recently proposed in the literature.

show abstract

Section: Set Upmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A biologically inspired framework for contour detection

Mignotte

2015

Pattern Anal Applic

Self Cite

View full text Add to dashboard Cite

show abstract

“…These applications include, but are not limited to, visual tracking [25] [26], object detection [27], image segmentation [28], contour detection [29], video stabilization [30], and even point set registration [31], i.e. finding a spatial transformation that aligns two given point sets.…”

Section: Hil Functional Validationmentioning

confidence: 99%

Evolutionary Computing and Particle Filtering: A Hardware-Based Motion Estimation System

Rodríguez

Moreno

2015

IEEE Trans. Comput.

View full text Add to dashboard Cite

Abstract-Particle filters constitute themselves a highly powerful estimation tool, especially when dealing with non-linear non-Gaussian systems. However, traditional approaches present several limitations, which reduce significantly their performance. Evolutionary algorithms, and more specifically their optimization capabilities, may be used in order to overcome particle-filtering weaknesses. In this paper, a novel FPGA-based particle filter that takes advantage of evolutionary computation in order to estimate motion patterns is presented. The evolutionary algorithm, which has been included inside the resampling stage, mitigates the known sample impoverishment phenomenon, very common in particle-filtering systems. In addition, a hybrid mutation technique using two different mutation operators, each of them with a specific purpose, is proposed in order to enhance estimation results and make a more robust system. Moreover, implementing the proposed Evolutionary Particle Filter as a hardware accelerator has led to faster processing times than different software implementations of the same algorithm.

show abstract

“…Contour detection is an essential task for processing image [1]. This process also essentially required for segmentation [2], recognition, tracking etc.…”

Section: Introductionmentioning

confidence: 99%

A Multiscale Particle Filter and Multifeature Based Contour Detection

Swami¹,

Chaurasia²,

Kurmi³

2017

ijoaem

View full text Add to dashboard Cite

In this paper, a multi-scale particle filter (MSPF) based algorithm and multi-feature-based surround inhibition (MFBSI) algorithm are proposed for contour detection in natural images. The contour detection algorithms are jointly tracks at two edgelets as edge elements. This multi-scale edgelet structure gathers the semi-local information as Bayesian modelling. The model is further approximate by using Monte Carlo algorithm. The individual surround inhibition weights of the feature as, including luminance, luminance contrast, and orientation. The scale-guided strategy is used for features together. The final surround inhibition is modulated using the combined weights in the neuron. The luminance contrast and luminance are proven as an excellent contour extraction capability. The multiscale particle filter (MSPF) based approach provides a better contour for the object segmentation.

show abstract

A MultiScale Particle Filter Framework for Contour Detection

Cited by 23 publications

References 21 publications

A biologically inspired framework for contour detection

A biologically inspired framework for contour detection

Evolutionary Computing and Particle Filtering: A Hardware-Based Motion Estimation System

A Multiscale Particle Filter and Multifeature Based Contour Detection

Contact Info

Product

Resources

About