Visual correspondence using energy minimization and mutual information

Kim, Junhwan; Kolmogorov,; Zabih, Ramin

doi:10.1109/iccv.2003.1238463

Cited by 75 publications

(15 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where one image has undergone a radiometric transform to simulate an infrared/thermal image or similar). Here we illustrate both the limited applicability of these simulated data results [10,12,11,19,16], and the limited performance of approaches from prior cross-spectral work [21,22,31], in comparison to the use of dense gradient features with an appropriate optimisation approach.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Exemplar-Based Colour Constancy

Joze

Drew

2012

Procedings of the British Machine Vision Conference 2012

View full text Add to dashboard Cite

We address the problem of scene depth recovery within cross-spectral stereo imagery (each image sensed over a differing spectral range). We compare several robust matching techniques which are able to capture local similarities between the structure of crossspectral images and a range of stereo optimisation techniques for the computation of valid depth estimates in this case. Specifically we deal with the recovery of dense depth information from thermal (far infrared spectrum) and optical (visible spectrum) image pairs where large differences in the characteristics of image pairs make this task significantly more challenging than the common stereo case. We show that the use of dense gradient features, based on Histograms of Oriented Gradient (HOG) descriptors, for pixel matching in combination with a strong match optimisation approach can produce largely valid, yet coarse, dense depth estimates suitable for object localisation or environment navigation. The proposed solution is compared and shown to work favourably against prior approaches based on using Mutual Information (MI) or Local Self-Similarity (LSS) descriptors.

show abstract

Section: Introductionmentioning

confidence: 99%

“…A number of authors [10,12,11,19] propose using variants on an MI based approach for cross-spectral stereo matching based on results achieved on purely simulated cross-spectral data (i.e. where one image has undergone a radiometric transform to simulate an infrared/thermal image or similar).…”

Section: Introductionmentioning

confidence: 99%

Exemplar-Based Colour Constancy

Joze

Drew

2012

Procedings of the British Machine Vision Conference 2012

View full text Add to dashboard Cite

show abstract

“…With reference to this prior work on cross-spectral stereo, the previously discussed pseudoinfrared driven depth improvement approach proposed by Chiu et al [2,3] most closely follows the early work of a number of authors [5,6,7,11] using simulated cross-spectral data (i.e. where one image has undergone a radiometric transform to simulate an infrared image).…”

Section: Introductionmentioning

confidence: 99%

“…Subsequently, the resulting {w r , w g , w b } will be different for each and every scene making this approach computationally demanding for any practical use. Computational saving could possibly made by employing a fixed pseudoinfrared formulation such as [5,6,7,11] but this has been shown to compromise matching performance [15].…”

Section: Match Cost Computationmentioning

confidence: 99%

See 1 more Smart Citation

Improved Depth Recovery In Consumer Depth Cameras via Disparity Space Fusion within Cross-spectral Stereo

Garanderie

Breckon

2014

Proceedings of the British Machine Vision Conference 2014

View full text Add to dashboard Cite

The full-text may be used and/or reproduced, and given to third parties in any format or medium, without prior permission or charge, for personal research or study, educational, or not-for-prot purposes provided that:• a full bibliographic reference is made to the original source • a link is made to the metadata record in DRO • the full-text is not changed in any way The full-text must not be sold in any format or medium without the formal permission of the copyright holders.Please consult the full DRO policy for further details. AbstractWe address the issue of improving depth coverage in consumer depth cameras based on the combined use of cross-spectral stereo and near infrared structured light sensing. Specifically we show that fusion of disparity over these modalities prior to subsequent optimization, within the disparity space image, facilitates the recovery of scene depth information in regions where structured light sensing alone fails. This joint approach, leveraging disparity information from both structured light and cross-spectral stereo, facilitates the recovery of global scene depth comprising both texture-less object depth, where stereo sensing commonly fails, and highly reflective object depth, where structured light active sensing commonly fails. The proposed solution is illustrated using dense gradient feature matching and is shown to outperform prior approaches that use late-stage fused cross-spectral stereo depth as a facet of improved sensing for consumer depth cameras.

show abstract