Lane Detection and Scene Interpretation by Particle Filter in Airport Areas

Meymandi-Nejad, Claire; Kaddaoui, Salwa; Devy, Michel; Herbulot, Ariane

doi:10.5220/0007406105170524

Cited by 2 publications

(4 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We decided to implement these functions as parts of the methods instead of considering them as a preprocessing, because methods do not share the same color assumption. The particle filter method is based on [9] which includes the color assumption as part of the whole process, while the color assumption used for our implementation of the Hough Transform method is specific to our application and based on technical specifications defined in the xyz color space. The Hough transform takes as an input a binary image obtained from features extraction.…”

Section: Methodsmentioning

confidence: 99%

“…The first method we proposed for this comparison is an algorithm using the particle filter principle and presented in [9]. The philosophy of this method is to consider a pixel as a particle and a line of the image as an instant t. The particle filter is launched from the bottom line to the top line of the image.…”

Section: First Method: Particle Filtermentioning

confidence: 99%

“…We do not detail the IPM transform but it can be found in [9]. The result of the IPM transform can be observed in Figure 2.…”

Section: Preprocessing: the Ipm Transformmentioning

confidence: 99%

See 2 more Smart Citations

Aircraft Navigation on Taxiways

Meymandi-Nejad

Perrotin

Herbulot

et al. 2020

Proceedings of the 2020 4th International Symposium on Computer Science and Intelligent Control

Self Cite

View full text Add to dashboard Cite

While working on aircraft navigation on taxiways, the line detection is one of the main challenging problems to be solved. This subject has been widely studied in the literature in the automotive field. In this paper, we propose a comparison of three line detection algorithms based on methods validated in the automotive field but transposed in aeronautics where this subject has not been widely addressed. Some problematics appear: the tarmac environment differs from the usual road model and the camera's position impacts the visibility on the image. The first method presented here uses a particle filter while the second one is based on the Hough transform. In the second method, we perform a color-based detection and introduce a method to compute the reference color, using technical specifications for airport markings. The last method is the LaneNet neural network. Criteria such as the precision or the max range of the detection are computed and exploited to discuss the algorithms relevance. The comparison is performed on both simulated images (from a product of the OKTAL-SE company) and real ones (from Airbus Operations S.A.S.).

show abstract

Section: Methodsmentioning

confidence: 99%

Section: First Method: Particle Filtermentioning

confidence: 99%

See 1 more Smart Citation

Aircraft Navigation on Taxiways

Meymandi-Nejad

Perrotin

Herbulot

et al. 2020

Proceedings of the 2020 4th International Symposium on Computer Science and Intelligent Control

Self Cite

View full text Add to dashboard Cite

show abstract

“…In order to validate this study, we decided to compare the results for two line detection algorithms: a method based on the Hough Transform as presented in (Hota et al, 2009), called HT in Table 4, and a Particle Filter (PF) implementation (Meymandi-Nejad et al, 2019), on real images only. Both use a color assumption.…”

Section: Quantitative Validation On Line Detection Algorithmsmentioning

confidence: 99%

Colorimetric Space Study: Application for Line Detection on Airport Areas

Meymandi-Nejad

Perrotin

Herbulot

et al. 2021

Proceedings of the 7th International Conference on Vehicle Technology and Intelligent Transport Systems

Self Cite

View full text Add to dashboard Cite

We propose an adaptive color reference refinement process for color detection in an aeronautical application: the detection of taxiway markings based on images acquired from an aircraft. Road markings detection is a key functionality for autonomous driving, and is actively studied in the literature. However, few studies have been conducted on aeronautics. Road markings are often detected by using color priors, sensitive to perturbations. Color-based algorithms are still favored in this context as the markings color provides important information. Our proposed method aims at reducing the impact of weather conditions, shadowing and illumination variations on color-based markings detection algorithms. Our approach adapts a given color reference in order to define a new flexible yet robust color reference while maximizing its difference to other colors in the image. It is achieved through a statistical analysis of color similarity over a set of images, computed on several color spaces and distance functions, in order to select the most relevant ones. We validate our approach by analyzing the quantitative improvement induced by this method using two color-based markings detection algorithms, based on the Hough Transform and the Particle Filter.

show abstract

Lane Detection and Scene Interpretation by Particle Filter in Airport Areas

Cited by 2 publications

References 6 publications

Aircraft Navigation on Taxiways

Aircraft Navigation on Taxiways

Colorimetric Space Study: Application for Line Detection on Airport Areas

Contact Info

Product

Resources

About