Multiple layers of contrasted images for robust feature-based visual tracking

Xi Wang 1 Marc Christie 1 Eric Marchand 2
1 MIMETIC - Analysis-Synthesis Approach for Virtual Human Simulation
UR2 - Université de Rennes 2, Inria Rennes – Bretagne Atlantique , IRISA_D6 - MEDIA ET INTERACTIONS
2 RAINBOW - Sensor-based and interactive robotics
Inria Rennes – Bretagne Atlantique , IRISA_D5 - SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE
Abstract : Feature-based SLAM (Simultaneous Localization and Mapping) techniques rely on low-level contrast information extracted from images to detect and track keypoints. This process is known to be sensitive to changes in illumination of the environment that can lead to tracking failures. This paper proposes a multi-layered image representation (MLI) that computes and stores different contrast-enhanced versions of an original image. Keypoint detection is performed on each layer, yielding better robustness to light changes. An optimization technique is also proposed to compute the best contrast enhancements to apply in each layer. Results demonstrate the benefits of MLI when using the main keypoint detectors from ORB, SIFT or SURF, and shows significant improvement in SLAM robustness.
Document type :
Conference papers
Liste complète des métadonnées

Cited literature [19 references]  Display  Hide  Download

https://hal.inria.fr/hal-01822789
Contributor : Eric Marchand <>
Submitted on : Monday, June 25, 2018 - 2:36:42 PM
Last modification on : Thursday, November 15, 2018 - 11:59:02 AM
Document(s) archivé(s) le : Wednesday, September 26, 2018 - 2:29:33 PM

File

MLI_ICIP2018_FinalVersion.pdf
Files produced by the author(s)

Identifiers

Citation

Xi Wang, Marc Christie, Eric Marchand. Multiple layers of contrasted images for robust feature-based visual tracking. ICIP’18 - 25th IEEE International Conference on Image Processing, Oct 2018, Athens, Greece. pp.241-245, ⟨10.1109/ICIP.2018.8451810⟩. ⟨hal-01822789⟩

Share

Metrics

Record views

442

Files downloads

197