A local method for contour matching and its parallel implementation

Boukir, Samia; Bouthémy, Patrick; Chaumette, F.; Juvin, D.

doi:10.1007/s001380050082

Cited by 14 publications

(13 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It allows local tracking of edge points. Our algorithm is inspired from the Moving Edge (ME) algorithm [8,9,15]. Contours are first sampled at a regular interval.…”

Section: Door Trackingmentioning

confidence: 99%

“…Different tracking techniques have been proposed in the literature: they mainly differ in geometric features that are used to describe the tracked objects, e.g. contours [6,7], straight lines or segments [8], etc. Since doors are characterized by straight lines, we used the 2D Moving Edges (ME) tracker [8,9] while implementing an oriented gradient mask.…”

Section: Introductionmentioning

confidence: 99%

“…contours [6,7], straight lines or segments [8], etc. Since doors are characterized by straight lines, we used the 2D Moving Edges (ME) tracker [8,9] while implementing an oriented gradient mask. The ME algorithm performs a one dimensional research on the normal of the contour at each sampled point and achieves real time performances.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Simple monocular door detection and tracking

Sekkal

Pasteau

Babel

et al. 2013

2013 IEEE International Conference on Image Processing

View full text Add to dashboard Cite

When considering an indoor navigation without using any prior knowledge of the environment, relevant landmark extraction remains an open issue for robot localization and navigation. In this paper, we consider indoor navigation along corridors. In such environments, when considering monocular cameras, doors can be seen as important landmarks. In this context, we present a new framework for door detection and tracking which exploits geometrical features of corridors. Since real-time properties are required for navigation purposes, designing solutions with a low computational complexity remains a relevant issue. The proposed algorithm relies on visual features such as lines and vanishing points that are further combined to discriminate the floor and wall planes and then to recognize doors within the image sequences. Detected doors are used to initialize a dedicated edge-based 2D door tracker. Experiments show that the framework is able to detect 82% of doors on our dataset while respecting real time constraints.

show abstract

“…It allows local tracking of edge points. Our algorithm is inspired from the Moving Edge (ME) algorithm [8,9,15]. Contours are first sampled at a regular interval.…”

Section: Door Trackingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Simple monocular door detection and tracking

Sekkal

Pasteau

Babel

et al. 2013

2013 IEEE International Conference on Image Processing

View full text Add to dashboard Cite

show abstract

“…Nevertheless, we will still use the word "contour" to refer to the list of tracked points for convenience. The ME algorithm can be implemented with convolution efficiency, thereby leading to real-time computation [4,5].…”

Section: Computing Normal Displacementsmentioning

confidence: 99%

“…The former approach considers features such as simple geometrical primitives (points, segments [4,15], circles [23],. .…”

Section: Introductionmentioning

confidence: 99%