Robust Computer Vision: An Interdisciplinary Challenge

Meer, Peter; Stewart, Charles; Tyler, David E.

doi:10.1006/cviu.1999.0833

Cited by 55 publications

(33 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A robust method should provide reliability in the presence of various types of noise and can tolerate a certain portion of outliers [9,10]. Interested readers may refer to [11] for a recent review on robust methods in computer vision.…”

Section: Robust Motion Estimationmentioning

confidence: 99%

Robust panorama from MPEG video

Morrison

et al. 2003

2003 International Conference on Multimedia and Expo. ICME '03. Proceedings (Cat. No.03TH8698)

View full text Add to dashboard Cite

A novel approach to image mosaicking from MPEG video is presented in this paper. The motion vectors in both P-and Bframes are used for global motion estimation. The bi-directional information in B-frames provides multiple routes to warp a frame to its previous anchor frame. A Least Median of Squares based algorithm is adopted for robust motion estimation. In the case of a large proportion of outliers, we detect possible algorithm failure and perform re-estimation along a different route. Based on the motion parameters between consecutive frames, the static background panorama and dynamic foreground panorama are constructed from warped images over a whole video sequence.

show abstract

Section: Robust Motion Estimationmentioning

confidence: 99%

Robust panorama from MPEG video

Morrison

et al. 2003

2003 International Conference on Multimedia and Expo. ICME '03. Proceedings (Cat. No.03TH8698)

View full text Add to dashboard Cite

show abstract

“…In that case, as demonstrated in (Mizera and Müller, 1999), certain M-estimators attain the maximum possible breakdown point. However, if X cannot be assumed non-random, the breakdown point of M-estimators drops towards zero (Meer et al, 2000). This underlines how important the way computer vision problems are formulated is.…”

Section: Introductionmentioning

confidence: 99%

Modeling Non-Gaussian Noise for Robust Image Analysis

Ieng¹,

Tarel²,

Charbonnier³

2007

Proceedings of the Second International Conference on Computer Vision Theory and Applications

View full text Add to dashboard Cite

Abstract:Accurate noise models are important to perform reliable robust image analysis. Indeed, many vision problems can be seen as parameter estimation problems. In this paper, two noise models are presented and we show that these models are convenient to approximate observation noise in different contexts related to image analysis. In spite of the numerous results on M-estimators, their robustness is not always clearly addressed in the image analysis field. Based on Mizera and Müller's recent fundamental work, we study the robustness of M-estimators for the two presented noise models, in the fixed design setting. To illustrate the interest of these noise models, we present two image vision applications that can be solved within this framework: curves fitting and edge-preserving image smoothing.

show abstract

“…In this initial paper robust M-estimators [5] are employed because they give a solid statistical basis for detailed analysis and have even been considered to be a unifying banner for these estimation techniques [8]. The estimation of the standard deviation of the inlier data (scale) using the Median Absolute Deviation (MAD) means that no tuning is required.…”

Section: Introductionmentioning

confidence: 99%

Improvements in robust 2D visual servoing

Marchand

Comport

Chaumette

2004

IEEE International Conference on Robotics and Automation, 2004. Proceedings. ICRA '04. 2004

View full text Add to dashboard Cite

Abstract-A fundamental step towards broadening the use of real world image-based visual servoing is to deal with the important issues of reliability and robustness. In order to address this issue, a closed loop control law is proposed that simultaneously accomplishes a visual servoing task and is robust to a general class of image processing errors. This is achieved with the application of widely accepted statistical techniques of robust M-estimation. Furthermore improvement have been added in the weight computation process: memory, initialization. Indeed, when the error between current visual features and desired ones are large, which occurs when large robot displacement are required, M-estimator may not detect outliers. To address this point, the method we propose to initialize the confidence in each feature is based on the LMedS estimators. Experimental results are presented which demonstrate visual servoing tasks which resist severe outlier contamination.

show abstract

Robust Computer Vision: An Interdisciplinary Challenge

Cited by 55 publications

References 13 publications

Robust panorama from MPEG video

Robust panorama from MPEG video

Modeling Non-Gaussian Noise for Robust Image Analysis

Improvements in robust 2D visual servoing

Contact Info

Product

Resources

About