scholarly journals Comparing Optical Flow Algorithms Using 6-DOF Motion of Real-World Rigid Objects

2012 ◽  
Vol 42 (6) ◽  
pp. 1752-1762 ◽  
Author(s):  
Marco Mammarella ◽  
Giampiero Campa ◽  
Mario L. Fravolini ◽  
Marcello R. Napolitano
Keyword(s):  
Optical Flow ◽  
Real World ◽  
Rigid Objects

scholarly journals Traffic extreme situations detection in video sequences based on integral optical flow

2019 ◽  
Vol 43 (4) ◽  
pp. 647-652 ◽  
Author(s):  
H. Chen ◽  
S. Ye ◽  
A. Nedzvedz ◽  
O. Nedzvedz ◽  
H. Lv ◽  
...  
Keyword(s):  
Optical Flow ◽  
Video Surveillance ◽  
Real World ◽  
Road Traffic ◽  
Video Sequences ◽  
Surveillance Systems ◽  
Directional Movement ◽  
Background Motion ◽  
Random Background ◽  
Integral Optical Flow

Road traffic analysis is an important task in many applications and it can be used in video surveillance systems to prevent many undesirable events. In this paper, we propose a new method based on integral optical flow to analyze cars movement in video and detect flow extreme situations in real-world videos. Firstly, integral optical flow is calculated for video sequences based on optical flow, thus random background motion is eliminated; secondly, pixel-level motion maps which describe cars movement from different perspectives are created based on integral optical flow; thirdly, region-level indicators are defined and calculated; finally, threshold segmentation is used to identify different cars movements. We also define and calculate several parameters of moving car flow including direction, speed, density, and intensity without detecting and counting cars. Experimental results show that our method can identify cars directional movement, cars divergence and cars accumulation effectively.

scholarly journals Nonrigid Optical Flow Ground Truth for Real-World Scenes With Time-Varying Shading Effects

2017 ◽  
Vol 2 (1) ◽  
pp. 231-238 ◽  
Author(s):  
Wenbin Li ◽  
Darren Cosker ◽  
Zhihan Lv ◽  
Matthew Brown
Keyword(s):  
Optical Flow ◽  
Real World ◽  
Ground Truth ◽  
Time Varying ◽  
Shading Effects

A linear algorithm for motion of rigid objects using features of parallel lines and optical flow

1991 ◽  
Vol 22 (14) ◽  
pp. 70-79 ◽  
Author(s):  
Takuto Joko ◽  
Koji Ito ◽  
Toshio Tsuji ◽  
Mutsuhiro Terauchi
Keyword(s):  
Optical Flow ◽  
Linear Algorithm ◽  
Rigid Objects ◽  
Parallel Lines

Can Stroboscopic Training Improve Judgments of Time-to-Collision?

2019 ◽  
Vol 62 (1) ◽  
pp. 152-165 ◽  
Author(s):  
Adam M. Braly ◽  
Patricia R. DeLucia
Keyword(s):  
Optical Flow ◽  
Real World ◽  
Moving Objects ◽  
Constant Error ◽  
Performance Degradation ◽  
Driver Training ◽  
Time To Collision ◽  
Repeated Practice ◽  
Improved Performance ◽  
Over Time

Objective: The aim of this study was to determine whether training with stroboscopic viewing could improve time-to-collision (TTC) judgments, which have importance in real-world tasks such as driving. Background: Prior research demonstrated that training with stroboscopic vision can improve motion coherence thresholds, improve anticipatory timing performance for laterally moving objects, and can protect against performance degradation over time. Method: Participants viewed computer simulations of an object that moved and then disappeared. In two separate experiments, the object approached the observer or moved laterally toward a target, representing different optical flow patterns. Participants judged TTC by pressing a button when they thought the object would hit them (approach), or the target (lateral). Performance was measured during four sessions—pretest, intervention, immediately after intervention, and 10 min after intervention. Results: Both stroboscopic training and repeated practice improved performance over time for approach motion (decrease in constant error) and stroboscopic training protected against performance degradation for lateral motion (no decrement in variable error), but only when TTC was 3.0 s. There was no difference between training and repeated practice. Conclusion: Under certain conditions, stroboscopic training may improve TTC judgments. However, effects of stroboscopic training depend on the nature of the optical flow pattern. Application: It is important to determine the conditions under which training can improve TTC judgments which have importance in real-world tasks such as driving. If individuals can be trained to judge TTC more accurately, they may benefit from driver training programs.

scholarly journals Unsupervised Recurrent All-Pairs Field Transforms for Particle Image Velocimetry

2021 ◽  
Vol 1 (1) ◽  
Author(s):  
Christian Lagemann ◽  
Michael Klaas ◽  
Wolfgang Schröder
Keyword(s):  
Experimental Data ◽  
Particle Image Velocimetry ◽  
Deep Learning ◽  
Optical Flow ◽  
Real World ◽  
Particle Image ◽  
State Of The Art ◽  
Flow Estimation ◽  
Optical Flow Estimation ◽  
Image Velocimetry

Convolutional neural networks have been successfully used in a variety of tasks and recently have been adapted to improve processing steps in Particle-Image Velocimetry (PIV). Recurrent All-Pairs Fields Transforms (RAFT) as an optical flow estimation backbone achieve a new state-of-the-art accuracy on public synthetic PIV datasets, generalize well to unknown real-world experimental data, and allow a significantly higher spatial resolution compared to state-of-the-art PIV algorithms based on cross-correlation methods. However, the huge diversity in dynamic flows and varying particle image conditions require PIV processing schemes to have high generalization capabilities to unseen flow and lighting conditions. If these conditions vary strongly compared to the synthetic training data, the performance of fully supervised learning based PIV tools might degrade. To tackle these issues, our training procedure is augmented by an unsupervised learning paradigm which remedy the need of a general synthetic dataset and theoretically boosts the inference capability of a deep learning model in a way being more relevant to challenging real-world experimental data. Therefore, we propose URAFT-PIV, an unsupervised deep neural network architecture for optical flow estimation in PIV applications and show that our combination of state-of-the-art deep learning pipelines and unsupervised learning achieves a new state-of-the-art accuracy for unsupervised PIV networks while performing similar to supervisedly trained LiteFlowNet based competitors. Furthermore, we show that URAFT-PIV also performs well under more challenging flow field and image conditions such as low particle density and changing light conditions and demonstrate its generalization capability based on an outof-the-box application to real-world experimental data. Our tests also suggest that current state-of-the-art loss functions might be a limiting factor for the performance of unsupervised optical flow estimation.

Replications can cause distorted belief in scientific progress

2018 ◽  
Vol 41 ◽  
Author(s):  
Michał Białek
Keyword(s):  
Real World ◽  
Scientific Progress ◽  
The Public ◽  
Psychological Science

AbstractIf we want psychological science to have a meaningful real-world impact, it has to be trusted by the public. Scientific progress is noisy; accordingly, replications sometimes fail even for true findings. We need to communicate the acceptability of uncertainty to the public and our peers, to prevent psychology from being perceived as having nothing to say about reality.

Sign in / Sign up

Export Citation Format

Share Document