A Color Topographic Map Based on the Dichromatic Reflectance Model

Gouiffès, Michèle; Zavidovique, B.

doi:10.1155/2008/824195

Cited by 10 publications

(15 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Future work will consider parallel versions of LSL and its application to derivate algorithms like hysteresis thresholding, convex hull computation, geodesic reconstruction, black and white labeling with holes filling [3], and more specialized algorithms like level sets [18] and level lines labeling [9,10].…”

Section: Discussionmentioning

confidence: 99%

Light speed labeling: efficient connected component labeling on RISC architectures

Lacassagne

Zavidovique

2009

J Real-Time Image Proc

Self Cite

View full text Add to dashboard Cite

This article introduces two fast algorithms for connected component Labeling of binary images, a peculiar case of coloring. The first one, Selkow DT is pixel-based and a Selkow's algorithm combined with the decision tree optimization technique. The second one called light speed labeling is segment-based line-relative labeling and was especially thought for commodity RISC architectures. An extensive benchmark on both structured and unstructured images substantiates that these two algorithms, the way they were designed, run faster than Wu's algorithm claimed to be the world fastest in 2007. Also they both show greater data independency hence runtime predictability.

show abstract

Section: Discussionmentioning

confidence: 99%

Light speed labeling: efficient connected component labeling on RISC architectures

Lacassagne

Zavidovique

2009

J Real-Time Image Proc

Self Cite

View full text Add to dashboard Cite

show abstract

“…It depends on two characteristics related to the physical properties of the material: the penetration of the light and the scattering of the body's pigments [11]. Clothes are opaque bodies and reflect light in a way that difficult the detection of color transitions between the person and the background.…”

Section: Colored Level Linesmentioning

confidence: 99%

“…In contrast, when Saturation has small values, Hue is noisy or unstable, and thus it may be irrelevant [5]. The last means that Hue is ill-defined in the unsaturated cases, and this channel can generate irrelevant level lines [11].…”

Section: Hsv Transformed Spacementioning

confidence: 99%

Pedestrian Detection Using a Feature Space Based on Colored Level Lines

Negri

Lotito

2012

Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications

View full text Add to dashboard Cite

Abstract. This work gives the guidelines to develop a pedestrian detection system using a feature space based on colored level lines, called Movement Feature Space (MFS). Besides detecting the movement in the scene, this feature space defines the descriptors used by the classifiers to identify pedestrians. The multi-channel level lines approach has been tested on the HSV color space, which improves the one-channel (gray scale) level lines calculation. Locations hypotheses of pedestrian are performed by a cascade of boosted classifiers. The validation of these regions of interest is carry out by a Support Vector Machine classifier. Results give more than 78.5 % of good detections on urban video sequences.

show abstract

“…Defining color sets directly in the RGB space is one solution to answer this problem of noise sensitivity, as in [1]. These results are quite satisfying regarding compactness and quality but the technique is time and resources consuming (several labeling stages, in both image and color space), which is dissuasive for real-time computer vision applications.…”

Section: Existing Level Sets and Linesmentioning

confidence: 99%

“…Our present work proposes a novel version of the topographic map [1], more compact and less time-consuming while better preserving the quality and the information of the image.…”

Section: Introductionmentioning

confidence: 99%

Body sets and lines: A reliable representation of images

Gouiffès

Zavidovique

2010

2010 IEEE International Conference on Acoustics, Speech and Signal Processing

Self Cite

View full text Add to dashboard Cite

This paper proposes a novel definition of color lines and sets, based on the dichromatic model for lambertian objects. The ends of the body vectors are robustly detected, from the clearest to the darkest through to a multi-level 2D histogram analysis. Finally, instead of classically defining the topographic map along one sole luminance direction, our body lines are designed along each body vector. Compared to existing topographic maps, our method is more compact while better preserving the color quality. Furthermore, it is faster to compute than [1].

show abstract

A Color Topographic Map Based on the Dichromatic Reflectance Model

Cited by 10 publications

References 15 publications

Light speed labeling: efficient connected component labeling on RISC architectures

Light speed labeling: efficient connected component labeling on RISC architectures

Pedestrian Detection Using a Feature Space Based on Colored Level Lines

Body sets and lines: A reliable representation of images

Contact Info

Product

Resources

About