Multispectral constraints for optical flow computation

The goal of this paper is to offer a structured synopsis of the problems in image motion computation and analysis, and of the methods proposed, exposing the underlying models and supporting assumptions. A sufficient number of pointers to the literature will be given, concentrating mostly on recent contributions. Emphasis will be on tile detection, measurement and segmentation of image motion. Tracking, and deformable motion isssues will be also addressed. Finally, a number of related questions which could require more investigations will be presented.

show abstract

“…One uses several electromagnetic signals of different wavelengths (Markandey and Flinchbaugh, 1990), the R-B-G signals for instance.…”

Section: Local Optimisation: the Methods Of Multiplementioning

confidence: 99%

Computation and analysis of image motion: A synopsis of current problems and methods

Mitiche

Bouthémy

1996

Int J Comput Vision

226

111

View full text Add to dashboard Cite

show abstract

“…While the Horn & Schunck technique incorporates a smoothness constraint in the solution for the flow field, other differential flow computation techniques resort to explicit post-processing of the flow field to improve smoothness [4,5,8,13]. The post-processing techniques used are typically ad hoc.…”

Section: Experiments 3 (Target Size)mentioning

confidence: 99%

“…This is an important question that needs to be addressed. As shown in [4,5,8,13], post-processing of the flow fields is essential to obtain usable flow fields from real images. The flow fields obtained directly from the solution of the constancy equations are typically so noisy that they cannot be used directly for such vision tasks as moving target detection.…”

Section: Experiments 3 (Target Size)mentioning

confidence: 99%

<title>Optical flow techniques for moving target detection</title>

Russo

Markandey

Bui

et al. 1991

Sensor Fusion III: 3D Perception and Recognition

View full text Add to dashboard Cite

show abstract

“…Their results show that for some colourful objects like flowers, using colour information is effective, but for many other objects, it is not necessarily so. The same investigation has been made for multi-spectral images [7], which contain more precise spectral information; there is a possibility that the results were different. Moreover, in the case that infrared images are used as one band images, it is expected that more different gradients can be obtained, because those images reflect a different physical phenomenon i.e.…”

Section: ( I I )     mentioning

confidence: 99%

Effect of variation in colour gradient information for optic flow computations

Shobha¹,

Kadambi²,

Shankapal³

et al. 2014

IJET

View full text Add to dashboard Cite

Optic flow algorithms provide mapping of 3D velocities on 2D image space. Optic flow is computed on the pair of images which are in sequence and is normally gray scale images. Optic flow computation using Horn and Schunck assumes that brightness consistency is maintained. Colour optic flow has the advantage that optic flow vectors are obtained even when there is a variation of brightness in the input images. The use of colour bands for optic flow is investigated by considering gradients of colour bands and component gradients. Results of applying these two types of gradients to three colour models are presented and analyzed. Decision logic is proposed to select the best colour model for colour optic flow computation based on gradient analysis.

show abstract

Multispectral constraints for optical flow computation

Cited by 28 publications

References 7 publications

Computation and analysis of image motion: A synopsis of current problems and methods

Computation and analysis of image motion: A synopsis of current problems and methods

<title>Optical flow techniques for moving target detection</title>

Effect of variation in colour gradient information for optic flow computations

Contact Info

Product

Resources

About