Synthetic Video Generation for Evaluation of Sprite Generation

2010 ◽  
Vol 1 (2) ◽  
pp. 34-61 ◽  
Author(s):  
Yi Chen ◽  
Ramazan S. Aygün
Keyword(s):  
Ground Truth ◽  
Objective Evaluation ◽  
Camera Motion ◽  
Generation Algorithm ◽  
Motion Patterns ◽  
Subjective Evaluations ◽  
Sprite Generation ◽  
Ground Truth Image ◽  
Motion Parameters ◽  
Synthetic Video

Sprite generation is the process of aligning, warping, and blending of pixels that belong to an object in a video. The evaluation of the correctness of a sprite is usually accomplished by a combination of objective and subjective evaluations. Availability of ground-truth image would help mere objective evaluation. In this paper, the authors present video generation from an image based on various camera motion parameters to be used as ground-truth for the sprite evaluation. This paper introduces a framework for evaluation of sprite generation algorithms. Experiments under the proposed framework were performed on the synthetic videos of different camera motion patterns to reveal the components of the sprite generation algorithm to be improved.

Synthetic Video Generation for Evaluation of Sprite Generation

2012 ◽  
pp. 160-187
Author(s):  
Yi Chen ◽  
Ramazan S. Aygün
Keyword(s):  
Ground Truth ◽  
Objective Evaluation ◽  
Camera Motion ◽  
Generation Algorithm ◽  
Motion Patterns ◽  
Subjective Evaluations ◽  
Sprite Generation ◽  
Ground Truth Image ◽  
Motion Parameters ◽  
Synthetic Video

Sprite generation is the process of aligning, warping, and blending of pixels that belong to an object in a video. The evaluation of the correctness of a sprite is usually accomplished by a combination of objective and subjective evaluations. Availability of ground-truth image would help mere objective evaluation. In this paper, the authors present video generation from an image based on various camera motion parameters to be used as ground-truth for the sprite evaluation. This paper introduces a framework for evaluation of sprite generation algorithms. Experiments under the proposed framework were performed on the synthetic videos of different camera motion patterns to reveal the components of the sprite generation algorithm to be improved.

SPRITE GENERATION FROM MPEG VIDEO USING MOTION INFORMATION

2004 ◽  
Vol 04 (02) ◽  
pp. 263-280 ◽  
Author(s):  
R. VENKATESH BABU ◽  
K. R. RAMAKRISHNAN
Keyword(s):  
Moving Objects ◽  
Camera Motion ◽  
Motion Information ◽  
Video Object ◽  
Background Region ◽  
Frame Alignment ◽  
Sprite Generation ◽  
Open Issue ◽  
Motion Parameters ◽  
Camera Motion Estimation

Sprite coding, accepted by the emerging MPEG-4 standard is a very efficient method for representing the background video object. Still this sprite generation is an open issue due to the foreground objects which obstructs the accuracy of camera motion estimation and blurs the generated sprite. In this paper we propose a method for constructing the background sprite with partial decoding of the MPEG stream. Initially the Independently Moving Objects (IMO) are segmented out from the background by clustering the pre-processed motion vectors of MPEG video. The camera motion parameters are obtained from the motion information corresponding to the background region which is used for frame alignment.

A virtual test environment for validating spacecraft optical navigation

2013 ◽  
Vol 117 (1197) ◽  
pp. 1075-1101 ◽  
Author(s):  
S. M. Parkes ◽  
I. Martin ◽  
M. N. Dunstan ◽  
N. Rowell ◽  
O. Dubois-Matra ◽  
...  
Keyword(s):  
Small Body ◽  
European Space Agency ◽  
Ground Truth ◽  
Camera Motion ◽  
Test Environment ◽  
Space Applications ◽  
Vision Guidance ◽  
Space Agency ◽  
Wide Range ◽  
And Performance

Abstract The use of machine vision to guide robotic spacecraft is being considered for a wide range of missions, such as planetary approach and landing, asteroid and small body sampling operations and in-orbit rendezvous and docking. Numerical simulation plays an essential role in the development and testing of such systems, which in the context of vision-guidance means that realistic sequences of navigation images are required, together with knowledge of the ground-truth camera motion. Computer generated imagery (CGI) offers a variety of benefits over real images, such as availability, cost, flexibility and knowledge of the ground truth camera motion to high precision. However, standard CGI methods developed for terrestrial applications lack the realism, fidelity and performance required for engineering simulations. In this paper, we present the results of our ongoing work to develop a suitable CGI-based test environment for spacecraft vision guidance systems. We focus on the various issues involved with image simulation, including the selection of standard CGI techniques and the adaptations required for use in space applications. We also describe our approach to integration with high-fidelity end-to-end mission simulators, and summarise a variety of European Space Agency research and development projects that used our test environment.

scholarly journals Semantic segmentation of gonio-photographs via adaptive ROI localisation and uncertainty estimation

2021 ◽  
Vol 6 (1) ◽  
pp. e000898
Author(s):  
Andrea Peroni ◽  
Anna Paviotti ◽  
Mauro Campigotto ◽  
Luis Abegão Pinto ◽  
Carlo Alberto Cutolo ◽  
...  
Keyword(s):  
Region Of Interest ◽  
Ground Truth ◽  
Semantic Segmentation ◽  
Uncertainty Estimation ◽  
Depth Of Field ◽  
Clinical Settings ◽  
Proposed Model ◽  
Validation Experiment ◽  
Segmentation Accuracy ◽  
Ground Truth Image

ObjectiveTo develop and test a deep learning (DL) model for semantic segmentation of anatomical layers of the anterior chamber angle (ACA) in digital gonio-photographs.Methods and analysisWe used a pilot dataset of 274 ACA sector images, annotated by expert ophthalmologists to delineate five anatomical layers: iris root, ciliary body band, scleral spur, trabecular meshwork and cornea. Narrow depth-of-field and peripheral vignetting prevented clinicians from annotating part of each image with sufficient confidence, introducing a degree of subjectivity and features correlation in the ground truth. To overcome these limitations, we present a DL model, designed and trained to perform two tasks simultaneously: (1) maximise the segmentation accuracy within the annotated region of each frame and (2) identify a region of interest (ROI) based on local image informativeness. Moreover, our calibrated model provides results interpretability returning pixel-wise classification uncertainty through Monte Carlo dropout.ResultsThe model was trained and validated in a 5-fold cross-validation experiment on ~90% of available data, achieving ~91% average segmentation accuracy within the annotated part of each ground truth image of the hold-out test set. An appropriate ROI was successfully identified in all test frames. The uncertainty estimation module located correctly inaccuracies and errors of segmentation outputs.ConclusionThe proposed model improves the only previously published work on gonio-photographs segmentation and may be a valid support for the automatic processing of these images to evaluate local tissue morphology. Uncertainty estimation is expected to facilitate acceptance of this system in clinical settings.

Dynamics of Human Coronary Arterial Motion and Its Potential Role in Coronary Atherogenesis

2000 ◽  
Vol 122 (5) ◽  
pp. 488-492 ◽  
Author(s):  
Zhaohua Ding ◽  
Morton H. Friedman
Keyword(s):  
Coronary Arteries ◽  
Potential Role ◽  
Fluid Dynamic ◽  
Mechanical Forces ◽  
Motion Patterns ◽  
Coefficients Of Variation ◽  
Motion Parameters ◽  
Arterial Motion ◽  
Vessel Axis

Mechanical forces have been widely recognized to play an important role in the pathogenesis of atherosclerosis. Since coronary arterial motion modulates both vessel wall mechanics and fluid dynamics, it is hypothesized that certain motion patterns might be atherogenic by generating adverse wall mechanical forces or fluid dynamic environments. To characterize the dynamics of coronary arterial motion and explore its implications in atherogenesis, a system was developed to track the motion of coronary arteries in vivo, and employed to quantify the dynamics of four right coronary arteries (RCA) and eight left anterior descending (LAD) coronary arteries. The analysis shows that: (a) The motion parameters vary among individuals, with coefficients of variation ranging from 0.25 to 0.59 for axially and temporally averaged values of the parameters; (b) the motion parameters of individual vessels vary widely along the vessel axis, with coefficients of variation as high as 2.28; (c) the LAD exhibits a greater axial variability in torsion, a measure of curve “helicity,” than the RCA; (d) in comparison with the RCA, the LAD experiences less displacement p=0.009, but higher torsion p=0.03. These results suggest that: (i) the variability of certain motion parameters, particularly those that exhibit large axial variations, might be related to variations in susceptibility to atherosclerosis among different individuals and vascular regions; and (ii) differences in motion parameters between the RCA and LAD might relate to differences in their susceptibility to atherosclerosis. [S0148-0731(00)00405-2]

Nonparametric motion characterization for robust classification of camera motion patterns

2006 ◽  
Vol 8 (2) ◽  
pp. 323-340 ◽  
Author(s):  
Ling-Yu Duan ◽  
J.S. Jin ◽  
Qi Tian ◽  
Chang-Sheng Xu
Keyword(s):  
Camera Motion ◽  
Motion Patterns ◽  
Robust Classification ◽  
Motion Characterization

Robust Software for Computing Camera Motion Parameters

2008 ◽  
Vol 33 (1) ◽  
pp. 1-9 ◽  
Author(s):  
Robert Schreiber ◽  
Zeyu Li ◽  
Harlyn Baker
Keyword(s):  
Camera Motion ◽  
Motion Parameters

Assessment of Muscle Spasticity by a Simple Pendulum Test and Modeling

2006 ◽  
Vol 321-323 ◽  
pp. 1008-1011
Author(s):  
Jae Hoon Jun ◽  
Se Jin Kong ◽  
Chul Seung Kim ◽  
Gwang Moon Eom ◽  
Soon Hyuck Lee ◽  
...  
Keyword(s):  
Muscle Length ◽  
Severity Index ◽  
Objective Evaluation ◽  
Study Data ◽  
Nonlinear Feedback ◽  
Modeling Error ◽  
Simple Pendulum ◽  
Subjective Evaluations ◽  
Pendulum Test ◽  
Reflex System

The quantitative and objective evaluation of spasticity is desirable in rehabilitation and orthopedics where subjective evaluations are mostly used. In the present study, data from a simple pendulum test are used for the evaluation of the spasticity with the help of biomechanical modeling. The spasticity of a knee joint is modeled as nonlinear feedback of muscle lengthening velocity and the muscle length. Through the optimization of the modeling error, the feedback parameters are determined. The threshold of muscle lengthening velocity in the reflex system is suggested as a severity index of the spasticity.

Sign in / Sign up

Export Citation Format

Share Document