Slow Flow: Exploiting High-Speed Cameras for Accurate and Diverse Optical Flow Reference Data

2017 ◽  
Author(s):  
Joel Janai ◽  
Fatma Guney ◽  
Jonas Wulff ◽  
Michael J. Black ◽  
Andreas Geiger
Keyword(s):  
Optical Flow ◽  
High Speed ◽  
Reference Data ◽  
Slow Flow

Mouth Shape Detection Based on Template Matching and Optical Flow for Machine Lip Reading

2013 ◽  
Vol 1 (1) ◽  
pp. 14-25 ◽  
Author(s):  
Tsuyoshi Miyazaki ◽  
Toyoshiro Nakashima ◽  
Naohiro Ishii
Keyword(s):  
Optical Flow ◽  
Template Matching ◽  
High Speed ◽  
Image Sequences ◽  
Previous Method ◽  
The Other ◽  
High Speed Camera ◽  
Improved Method ◽  
Time Period ◽  
Lip Reading

The authors describe an improved method for detecting distinctive mouth shapes in Japanese utterance image sequences. Their previous method uses template matching. Two types of mouth shapes are formed when a Japanese phone is pronounced: one at the beginning of the utterance (the beginning mouth shape, BeMS) and the other at the end (the ending mouth shape, EMS). The authors’ previous method could detect mouth shapes, but it misdetected some shapes because the time period in which the BeMS was formed was short. Therefore, they predicted that a high-speed camera would be able to capture the BeMS with higher accuracy. Experiments showed that the BeMS could be captured; however, the authors faced another problem. Deformed mouth shapes that appeared in the transition from one shape to another were detected as the BeMS. This study describes the use of optical flow to prevent the detection of such mouth shapes. The time period in which the mouth shape is deformed is detected using optical flow, and the mouth shape during this time is ignored. The authors propose an improved method of detecting the BeMS and EMS in Japanese utterance image sequences by using template matching and optical flow.

scholarly journals Controllers to Chase a High-Speed Evader Using a Pursuer with Variable Speed

2018 ◽  
Vol 8 (10) ◽  
pp. 1976 ◽  
Author(s):  
Jonghoek Kim
Keyword(s):  
Optical Flow ◽  
High Speed ◽  
Angular Rate ◽  
Relative Distance ◽  
Line Of Sight ◽  
Terminal Phase ◽  
Relative Speed ◽  
Variable Speed

This paper proposes a chasing controller to enable a pursuer to chase a high-speed evader such that the relative distance between the evader and the pursuer monotonically decreases as time passes. Our controller is designed to assure that the angular rate of Line-of-Sight joining the pair (the pursuer and the evader) is exactly zero at all time indexes. Assuming that the pursuee can readily observe optical flow, but only poorly detect looming, this pursuer’s movement is hardly detected by the pursuee. Consider the terminal phase when the pursuer is sufficiently close to the evader. As we slow down the relative speed of the pursuer with respect to the evader, we can reduce the probability of missing the high-speed evader. Thus, our strategy is to make the pursuer decrease its speed in the terminal phase, while ensuring that the distance between the evader and the pursuer monotonically decreases as time passes. The performance of our controller is verified utilizing MATLAB simulations.

scholarly journals Evolution of robust high speed optical-flow-based landing for autonomous MAVs

2020 ◽  
Vol 124 ◽  
pp. 103380 ◽  
Author(s):  
Kirk Y.W. Scheper ◽  
Guido C.H.E. de Croon
Keyword(s):  
Optical Flow ◽  
High Speed

Optical Flow and Texture Variables Useful for Detecting Changes in Simulated Self Motion

1983 ◽  
Vol 27 (12) ◽  
pp. 996-1000
Author(s):  
Dean H. Owen ◽  
Lawrence J. Hettinger ◽  
Shirley B. Tobias ◽  
Lawrence Wolpert ◽  
Rik Warren
Keyword(s):  
Optical Flow ◽  
Flow Pattern ◽  
High Speed ◽  
Flight Simulator ◽  
Practical Relevance ◽  
Motion Information ◽  
Flow Acceleration ◽  
Level Flight ◽  
Texture Density ◽  
Self Motion

Several methods are presented for breaking linkages among global optical flow and texture variables in order to assess their usefulness in experiments requiring observers to distinguish change in speed or heading of simulated self motion from events representing constant speed or level flight. Results of a series of studies testing for sensitivity to flow acceleration or deceleration, flow-pattern expansion variables, and the distribution of optical texture density are presented. Theoretical implications for determining the metrics of visual self-motion information, and practical relevance for pilot and flight simulator evaluation and for low-level, high-speed flight are discussed.

Modeling and Simulation Study on Crosswind Stability of the High-Speed Bus

2011 ◽  
Vol 42 (11) ◽  
pp. 44-50 ◽  
Author(s):  
Qin Dong-chen ◽  
Xu Yi-cun ◽  
Zhu Qiang ◽  
Yu Li
Keyword(s):  
Simulation Study ◽  
High Speed ◽  
Reference Data ◽  
Wind Pressure ◽  
Body System ◽  
Simulation Test ◽  
Pressure Center ◽  
Straight Line ◽  
Crosswind Stability ◽  
Multi Body

Based on multi-body system dynamics, the model of Yutong high-speed bus was built by ADAMS/Car software to analyse the influence of crosswind on the high-speed bus' handing stability. Seven discrete wind pressure centers effects on the chasis were taken into account, so the crosswind model with a shifting pressure center was achieved. After improving the standard of the crosswind sensitivity test that is prescribed by American ESV (Experimental safety vehicle), the crosswind simulation tests with pressure center's shift and the immobile pressure center were carried out. The high-speed straight-line simulation test without the crosswind was also completed. By comparing the results of the three tests, the test data in consideration of wind pressure center's shift was more reasonable and provided the reference data for improving the crosswind stability of the bus.

The incidence of slow flow after rotational atherectomy of calcified coronary arteries: A randomized study of low speed versus high speed

2016 ◽  
Vol 89 (5) ◽  
pp. 832-840 ◽  
Author(s):  
Kenichi Sakakura ◽  
Hiroshi Funayama ◽  
Yousuke Taniguchi ◽  
Yoshimasa Tsurumaki ◽  
Kei Yamamoto ◽  
...  
Keyword(s):  
Coronary Arteries ◽  
High Speed ◽  
Randomized Study ◽  
Rotational Atherectomy ◽  
Slow Flow ◽  
Low Speed

Real-Time Optical Flow Estimation Using Multiple Frame-Straddling Intervals

2012 ◽  
Vol 24 (4) ◽  
pp. 686-698 ◽  
Author(s):  
Lei Chen ◽  
◽  
Hua Yang ◽  
Takeshi Takaki ◽  
Idaku Ishii
Keyword(s):  
Optical Flow ◽  
Real Time ◽  
High Speed ◽  
Frame Rate ◽  
Low Speed ◽  
Flow Estimation ◽  
Optical Flow Estimation ◽  
Optical Flows ◽  
Multiple Frame ◽  
Measurable Range

In this paper, we propose a novel method for accurate optical flow estimation in real time for both high-speed and low-speed moving objects based on High-Frame-Rate (HFR) videos. We introduce a multiframe-straddling function to select several pairs of images with different frame intervals from an HFR image sequence even when the estimated optical flow is required to output at standard video rates (NTSC at 30 fps and PAL at 25 fps). The multiframestraddling function can remarkably improve the measurable range of velocities in optical flow estimation without heavy computation by adaptively selecting a small frame interval for high-speed objects and a large frame interval for low-speed objects. On the basis of the relationship between the frame intervals and the accuracies of the optical flows estimated by the Lucas–Kanade method, we devise a method to determine multiple frame intervals in optical flow estimation and select an optimal frame interval from these intervals according to the amplitude of the estimated optical flow. Our method was implemented using software on a high-speed vision platform, IDP Express. The estimated optical flows were accurately outputted at intervals of 40 ms in real time by using three pairs of 512×512 images; these images were selected by frame-straddling a 2000-fps video with intervals of 0.5, 1.5, and 5 ms. Several experiments were performed for high-speed movements to verify that our method can remarkably improve the measurable range of velocities in optical flow estimation, compared to optical flows estimated for 25-fps videos with the Lucas–Kanade method.

2P2-B08 Development of a Real-time Optical Flow Detection System based on High Speed Vision

2008 ◽  
Vol 2008 (0) ◽  
pp. _2P2-B08_1-_2P2-B08_2
Author(s):  
Taku TANIGUCHI ◽  
Ryo SUKENOBE ◽  
Kenkichi YAMAMOTO ◽  
Idaku ISHII
Keyword(s):  
Optical Flow ◽  
Real Time ◽  
High Speed ◽  
Detection System ◽  
Flow Detection
Sign in / Sign up

Export Citation Format

Share Document