Robust digital image stabilization using the Kalman filter

Wang, Chuntao; Kim, Jinhyung; Byun, Keun-Yung; Ni, Jiangqun; Ko, Sung-Jea

doi:10.1109/tce.2009.4814407

Cited by 77 publications

(51 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Several smoothing methods based on filters have been used in video stabilization algorithms, such as Kalman filtering [22], Gaussian filtering [23], and particle filtering [24]. Once we extract affine transformation parameters (scale, rotation, and translation XY), a low-pass filter is used to get the motion intention.…”

Section: Video Freeze Detectionmentioning

confidence: 99%

“…Motion estimation is the process for determining parameters that relate the frame uncompensated with frame defined as the reference. Previous works on this problem propose two main approaches: one based on the optical flow [4] and the other based on the geometric transformation model [5] [6] [7]. In this article, we use the second proposal.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Motion intention optimization for multirotor robust video stabilization

Aguilar

Ángulo

Pardo

2017

2017 CHILEAN Conference on Electrical, Electronics Engineering, Information and Communication Technologies (CHILECON)

View full text Add to dashboard Cite

Abstract-In this paper we present an optimization algorithm for simultaneously detecting video freeze and obtaining the minimum number of the frame required in motion intention estimation for real time robust video stabilization on multirotor unmanned aerial vehicles. A combination of a filter and a threshold is used to the video freeze detection, and for optimizing the algorithm, we find the minimum number of frames for motion intention estimation without decrease the performance.

show abstract

Section: Video Freeze Detectionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Motion intention optimization for multirotor robust video stabilization

Aguilar

Ángulo

Pardo

2017

2017 CHILEAN Conference on Electrical, Electronics Engineering, Information and Communication Technologies (CHILECON)

View full text Add to dashboard Cite

show abstract

“…Having displacement in the x-axis, y-axis directions (d x , d y ), the state model and the measurement model are defined as (19) and (20), respectively.…”

Section: Adaptive Extended Kalman Filtermentioning

confidence: 99%

“…It comprises inter-frame predication and single-frame measurement of the discriminative power of features. They showed that this method can stabilize the tracking performance when objects go across complex backgrounds [18,19].…”

Section: Introductionmentioning

confidence: 99%

“…They used the rate of occlusion to adjust the error covariance of the Kalman filter, adaptively. The adaptive Kalman filter improves the tracking performance in situations such as changing lighting and partial and/or long-lasting occlusion in real-time applications [19]. This paper proposes the adaptive Kalman filter (AKF) to improve the performance of a vision-based head gesture interface to a video game.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Adaptive Kalman Filter Applied to Vision Based Head Gesture Tracking for Playing Video Games

Oskoei

2017

Robotics

View full text Add to dashboard Cite

This paper proposes an adaptive Kalman filter (AKF) to improve the performance of a vision-based human machine interface (HMI) applied to a video game. The HMI identifies head gestures and decodes them into corresponding commands. Face detection and feature tracking algorithms are used to detect optical flow produced by head gestures. Such approaches often fail due to changes in head posture, occlusion and varying illumination. The adaptive Kalman filter is applied to estimate motion information and reduce the effect of missing frames in a real-time application. Failure in head gesture tracking eventually leads to malfunctioning game control, reducing the scores achieved, so the performance of the proposed vision-based HMI is examined using a game scoring mechanism. The experimental results show that the proposed interface has a good response time, and the adaptive Kalman filter improves the game scores by ten percent.

show abstract