Image Sequence Stabilization in Real Time

Duric, Zoran; Rosenfeld, Azriel

doi:10.1006/rtim.1996.0029

Cited by 41 publications

(14 citation statements)

References 12 publications

(12 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By contrast the prior use of differential approaches (e.g. [36,37]) have notable computational complexity, illumination sensitivity and potential aperture problems for the high magnitude/frequency vibration characteristics with which we are dealing (see Section 3). In addition, explicitly feature driven approaches (e.g.…”

Section: Proposed Methodologymentioning

confidence: 99%

See 1 more Smart Citation

Robust motion filtering as an enabler to video stabilization for a tele-operated mobile robot

Chereau

Breckon

2013

SPIE Proceedings

View full text Add to dashboard Cite

An increasing number of inspection and hazardous environment tasks use mobile robotic vehicles manually tele-operated via a live video feed from an on-board camera. The resulting video imagery frequently suffers from vibration artefacts compromising the accuracy and security of operation in addition to the viable duration for human tele-operation. Here we aim to automatically remove these unwanted visual effects using a novel real-time video stabilization approach. Prior work for hand-held and vehicle mounted cameras is ill-suited to the high-frequency, large magnitude (10-15% of image size) vibration encountered on the short wheelbase, non-suspended robotic platforms typically deployed for such tasks.Without prior knowledge of the robot ego-motion (or vibration characteristics) we develop a novel four stage filtering approach to identify robust Local Motion Vectors (LMV) for Global Motion Vector (GMV) estimation in successive video frames whilst preserving the required real-time responsiveness for tele-operation. Experimental results over a range of tele-operation scenarios show that the method provides both significant qualitative visual improvement and a quantitative reduction in measurable video image displacement (caused by vibration).

show abstract

Section: Proposed Methodologymentioning

confidence: 99%

“…The differential approach calculates the optical flow to estimate inter-frame motions of each pixel relying on an image brightness constancy assumption [24,36,37]. This approach is time consuming and not robust to the aperture problem (see Section 4.2).…”

Section: Motion Estimation and Filteringmentioning

confidence: 99%

Robust motion filtering as an enabler to video stabilization for a tele-operated mobile robot

Chereau

Breckon

2013

SPIE Proceedings

View full text Add to dashboard Cite

show abstract

“…Function here performs a contrast enhancement to the input pattern and is defined by if if (10) in which is a positive constant less than one. Function is the transfer function of neurons and is given by otherwise (11) where indicates the winner on layer and is a constant between zero and one. is the net input from layer to the th neuron, , in which is the weight from the th neuron to the th neuron.…”

Section: B Cart Neural Networkmentioning

confidence: 99%

“…The input video sequences are typically unstable because of movements and vibrations of the vehicle. Image stabilization techniques [11] are commonly used to attenuate the effect of nonsmooth motions of vehicles in video sequences. However, such techniques are generally time expensive and are not adequate for real-time applications.…”

Section: A Sensory Componentmentioning

confidence: 99%

Automatic change detection of driving environments in a vision-based driver assistance system

Fang

Chen

Fuh

2003

IEEE Trans. Neural Netw.

View full text Add to dashboard Cite

Abstract-Detecting critical changes of environments while driving is an important task in driver assistance systems. In this paper, a computational model motivated by human cognitive processing and selective attention is proposed for this purpose. The computational model consists of three major components, referred to as the sensory, perceptual, and conceptual analyzers. The sensory analyzer extracts temporal and spatial information from video sequences. The extracted information serves as the input stimuli to a spatiotemporal attention (STA) neural network embedded in the perceptual analyzer. If consistent stimuli repeatedly innervate the neural network, a focus of attention will be established in the network. The attention pattern associated with the focus, together with the location and direction of motion of the pattern, form what we call a categorical feature. Based on this feature, the class of the attention pattern and, in turn, the change in driving environment corresponding to the class are determined using a configurable adaptive resonance theory (CART) neural network, which is placed in the conceptual analyzer. Various changes in driving environment, both in daytime and at night, have been tested. The experimental results demonstrated the feasibilities of both the proposed computational model and the change detection system. Index Terms-Cognitive model, configurable adaptive resonance theory (CART) neural network, driver assistance system, sensory, perceptual, and conceptual analyzers, spatiotemporal attention (STA) neural network, system to detect change in driving environment.

show abstract

“…The differential approaches, primarily for computing optical flow [5] and based on the assumption of image brightness constancy, are known to be sensitive to both high-order derivative errors and the aperture problem. Matching techniques can be divided into two classes, block matching [6] and feature-based matching [7]. Block matching is intrinsically weak at handling motions involving rotation and scale change.…”

Section: Introductionmentioning

confidence: 99%

Video stabilization for a hand-held camera based on 3D motion model

Wang

Chou

Chen

et al. 2009

2009 16th IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

In this paper, a video stabilization technique is presented. There are four steps in the proposed approach. We begin with extracting feature points from the input image using the Lowe SIFT (Scale Invariant Feature Transform) point detection technique. This set of feature points is then matched against the set of feature points detected in the previous image using the Wyk et al. RKHS (Reproducing Kernel Hilbert Space) graph matching technique. We can calculate the camera motion between the two images with the aid of a 3D motion model. Expected and unexpected components are separated using a motion taxonomy method. Finally, a full-frame technique to fill up blank image areas is applied to the transformed image.

show abstract

Image Sequence Stabilization in Real Time

Cited by 41 publications

References 12 publications

Robust motion filtering as an enabler to video stabilization for a tele-operated mobile robot

Robust motion filtering as an enabler to video stabilization for a tele-operated mobile robot

Automatic change detection of driving environments in a vision-based driver assistance system

Video stabilization for a hand-held camera based on 3D motion model

Contact Info

Product

Resources

About