Online multimodal video registration based on shape matching

St-Charles, Pierre-Luc; Bilodeau, Guillaume-Alexandre; Bergevin, Robert

doi:10.1109/cvprw.2015.7301293

Cited by 14 publications

(55 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As shown in Table 2, our method is better than [13,14] for all but LITIV-8. This is because our method has three features: (1) the keypoints used in our method are more accurate.…”

Section: Experiments and Analysismentioning

confidence: 84%

“…To achieve this goal, we use the given global homography to update the best global homography according to the method of homography smoothing described in [13]. The total best global homography is lastly found by combining the results of coarse and precise registration:

θ_{t} = θ_{c} + θ_{p}, S_{t} = S_{c} \times S_{p} T y_{t} = S_{c} \times false(T y_{p} \times \cos false(θ_{c} false) + T x_{p} \times \sin false(θ_{c} false) false), T x_{t} = S_{c} \times false(T x_{p} \times \cos false(θ_{c} false) - T y_{p} \times \sin false(θ_{c} false) false)

where

S_{c}

and

θ_{c}

are the rotation and scale obtained in coarse registration, respectively, and

S_{p}

θ_{p}

T y_{p}

and

T x_{p}

are the scale, rotation, and the translations obtained in precise registration.…”

Section: Registration Frameworkmentioning

confidence: 99%

“…In our case, we used the binary polygons provided by [13], and then evaluated each method with overlap error:

O E = 1 - \frac{P_{l} \cap P_{r}}{P_{l} \cup P_{r}}

where

P_{l}

and

P_{r}

are the transformed infrared polygon and the visible polygon, respectively. In practice, the overlap error between the transformed infrared foreground and the visible foreground has been used in homography smoothing [13]. It was adopted to find the best global homography in our framework.…”

Section: Experiments and Analysismentioning

confidence: 99%

“…Compared to the reservoirs proposed in [13,14], ours can save a sufficient number of representative matches for registration.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A Hierarchical Framework Combining Motion and Feature Information for Infrared-Visible Video Registration

Sun

Zhang

et al. 2017

Sensors

View full text Add to dashboard Cite

In this paper, we propose a novel hierarchical framework that combines motion and feature information to implement infrared-visible video registration on nearly planar scenes. In contrast to previous approaches, which involve the direct use of feature matching to find the global homography, the framework adds coarse registration based on the motion vectors of targets to estimate scale and rotation prior to matching. In precise registration based on keypoint matching, the scale and rotation are used in re-location to eliminate their impact on targets and keypoints. To strictly match the keypoints, first, we improve the quality of keypoint matching by using normalized location descriptors and descriptors generated by the histogram of edge orientation. Second, we remove most mismatches by counting the matching directions of correspondences. We tested our framework on a public dataset, where our proposed framework outperformed two recently-proposed state-of-the-art global registration methods in almost all tested videos.

show abstract

“…As shown in Table 2, our method is better than [13,14] for all but LITIV-8. This is because our method has three features: (1) the keypoints used in our method are more accurate.…”

Section: Experiments and Analysismentioning

confidence: 84%

θ_{t} = θ_{c} + θ_{p}, S_{t} = S_{c} \times S_{p} T y_{t} = S_{c} \times false(T y_{p} \times \cos false(θ_{c} false) + T x_{p} \times \sin false(θ_{c} false) false), T x_{t} = S_{c} \times false(T x_{p} \times \cos false(θ_{c} false) - T y_{p} \times \sin false(θ_{c} false) false)

where

S_{c}

and

θ_{c}

are the rotation and scale obtained in coarse registration, respectively, and

S_{p}

θ_{p}

T y_{p}

and

T x_{p}

are the scale, rotation, and the translations obtained in precise registration.…”

Section: Registration Frameworkmentioning

confidence: 99%

“…In our case, we used the binary polygons provided by [13], and then evaluated each method with overlap error:

O E = 1 - \frac{P_{l} \cap P_{r}}{P_{l} \cup P_{r}}

where

P_{l}

and

P_{r}

Section: Experiments and Analysismentioning

confidence: 99%

“…Compared to the reservoirs proposed in [13,14], ours can save a sufficient number of representative matches for registration.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Hierarchical Framework Combining Motion and Feature Information for Infrared-Visible Video Registration

Sun

Zhang

et al. 2017

Sensors

View full text Add to dashboard Cite

show abstract

“…In previous works, various approaches have been introduced to solve the infrared-visible image registration problem, such as area-based methods [ 6 , 7 , 8 ] and feature-based methods [ 9 , 10 , 11 , 12 ]. These works led to some progress in improving registration quality or reducing computational time, but there are still some difficulties that need to be overcome.…”

Section: Introductionmentioning

confidence: 99%

An Automatic Multi-Target Independent Analysis Framework for Non-Planar Infrared-Visible Registration

Sun

Zhang

et al. 2017

Sensors

View full text Add to dashboard Cite

In this paper, we propose a novel automatic multi-target registration framework for non-planar infrared-visible videos. Previous approaches usually analyzed multiple targets together and then estimated a global homography for the whole scene, however, these cannot achieve precise multi-target registration when the scenes are non-planar. Our framework is devoted to solving the problem using feature matching and multi-target tracking. The key idea is to analyze and register each target independently. We present a fast and robust feature matching strategy, where only the features on the corresponding foreground pairs are matched. Besides, new reservoirs based on the Gaussian criterion are created for all targets, and a multi-target tracking method is adopted to determine the relationships between the reservoirs and foreground blobs. With the matches in the corresponding reservoir, the homography of each target is computed according to its moving state. We tested our framework on both public near-planar and non-planar datasets. The results demonstrate that the proposed framework outperforms the state-of-the-art global registration method and the manual global registration matrix in all tested datasets.

show abstract

Target Registration Based on Fusing Features of Visible and Two Wave Bands Infrared Images

Yan

Cai

et al. 2021

Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering

View full text Add to dashboard Cite

Online multimodal video registration based on shape matching

Cited by 14 publications

References 24 publications

A Hierarchical Framework Combining Motion and Feature Information for Infrared-Visible Video Registration

A Hierarchical Framework Combining Motion and Feature Information for Infrared-Visible Video Registration

An Automatic Multi-Target Independent Analysis Framework for Non-Planar Infrared-Visible Registration

Target Registration Based on Fusing Features of Visible and Two Wave Bands Infrared Images

Contact Info

Product

Resources

About