Mosaic of a video shot with multiple moving objects

Fusiello, Andrea; Aprile, M.; Marzotto, R.; Murino, Vittorio

doi:10.1109/icip.2003.1246678

Cited by 6 publications

(4 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although not applied in the present work, pose-model feedback seems promising as a natural augmentation of the techniques described here. Research has also begun to mitigate the requirements for a static camera [9] and static background [42].…”

Section: Algorithmmentioning

confidence: 99%

A recognition-based motion capture baseline on the HumanEva II test data

Howe

2011

Machine Vision and Applications

View full text Add to dashboard Cite

The advent of the HumanEva standardized motion capture data sets has enabled quantitative evaluation of motion capture algorithms on comparable terms. This paper measures the performance of an existing monocular recognition-based pose recovery algorithm on select HumanEva data, including all the HumanEva II clips. The method uses a physically-motivated Markov process to connect adajacent frames and achieve a 3D relative mean error of 8.9 cm per joint. It further investigates factors contributing to the error, and finds that research into better pose retrieval methods offers promise for improvement of this technique and those related to it. Finally, it investigates the effects of local search optimization with the same recognition-based algorithm and finds no significant deterioration in the results, indicating that processing speed can be largely independent of the size of the recognition library for this approach.

show abstract

Section: Algorithmmentioning

confidence: 99%

A recognition-based motion capture baseline on the HumanEva II test data

Howe

2011

Machine Vision and Applications

View full text Add to dashboard Cite

show abstract

“…Mosaicing methods that require that the images to be registered are captured in advance, and take the whole set of images as the input, usually utilize some kind of global registration stage in the processing [3,2,13,5,1,10]. Global registration reduces the accumulated errors by simultaneously minimizing the misregistration between all overlapping pairs of images.…”

Section: The Methodsmentioning

confidence: 99%

“…For a good survey, see [15]. The methods can be roughly divided into two classes: direct methods such as [14,11,8] and feature-based methods such as [2,5,1,10]. Both of these have their pros and cons.…”

Section: Related Workmentioning

confidence: 98%

An image mosaicing module for wide-area surveillance

Heikkilä

2005

Proceedings of the Third ACM International Workshop on Video Surveillance &Amp; Sensor Networks

View full text Add to dashboard Cite

This paper presents a fully automatic image mosaicing method for needs of wide-area video surveillance. A pure featurebased approach was adopted for finding the registration between the images. This approach provides us with several advantages. Our method is robust against illumination variations, moving objects, image rotation, image scaling, imaging noise, and is relatively fast to calculate. We have tested the performance of the proposed method against several video sequences captured from real-world scenes. The results clearly justify our approach.

show abstract

“…The algorithm searches the optimal path in the frame-graph and constructs the final mosaic using the images along this path. Fusiello et al [14] also use graph-based global registration techniques to create super-resolution mosaic based on nonlinear least square optimization. Pfingsthorn et al [15] introduce a spectral image registration method based on Phased-Only Matched Filter (POMF).…”

Section: Related Workmentioning

confidence: 99%

Large Scale Image Mosaic Construction for Agricultural Applications

Isler

2016

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

We present a novel technique for stitching images including those obtained from aerial vehicles flying at low altitudes. Existing image stitching/mosaicking methods rely on inter-image homography computation based on a planar scene assumption. This assumption holds when images are taken from high-altitudes (hence the depth variation is negligible). It is often violated when flying at low altitudes. Further, to avoid scale and resolution changes, existing methods rely on primarily translational motion at fixed altitudes. Our method removes these limitations and performs well even when aerial images are taken from low altitudes by an aerial vehicle performing complex motions. It starts by extracting the ground geometry from a sparse reconstruction of the scene obtained from a small fraction of the input images. Next, it selects the best image (from the entire sequence) for each location on the ground using a novel camera selection criterion. This image is then independently rectified to obtain the corresponding portion of the mosaic. Therefore, the technique avoids performing costly joint-optimization over the entire sequence. It is validated using challenging input sequences motivated by agricultural applications.

show abstract

Mosaic of a video shot with multiple moving objects

Cited by 6 publications

References 8 publications

A recognition-based motion capture baseline on the HumanEva II test data

A recognition-based motion capture baseline on the HumanEva II test data

An image mosaicing module for wide-area surveillance

Large Scale Image Mosaic Construction for Agricultural Applications

Contact Info

Product

Resources

About