INDEPENDENT COMPONENTS OF OPTICAL FLOW IN A MULTIRESOLUTION IMAGE SEQUENCE

2008 ◽  
Vol 22 (05) ◽  
pp. 929-944 ◽  
Author(s):  
NAOYA OHNISHI ◽  
ATSUSHI IMIYA
Keyword(s):  
Mobile Robot ◽  
Optical Flow ◽  
Robot Vision ◽  
Image Sequence ◽  
Flow Fields ◽  
Image Sequences ◽  
Visual Navigation ◽  
Local Motion ◽  
Independent Components ◽  
Local Perception

In this paper, we present an algorithm for the hierarchical recognition of an environment using independent components of optical flow fields for the visual navigation of a mobile robot. For the computation of optical flow, the pyramid transform of an image sequence is used for the analysis of global and local motion. Our algorithm detects the planar region and obstacles in the image from optical flow fields at each layer in the pyramid. Therefore, our algorithm allows us to achieve both global perception and local perception for robot vision. We show experimental results for both test image sequences and real image sequences captured by a mobile robot. Furthermore, we show some aspects of this work from the viewpoint of information theory.

IMAGE SEQUENCES—TEN (OCTAL) YEARS—FROM PHENOMENOLOGY TOWARDS A THEORETICAL FOUNDATION

1988 ◽  
Vol 02 (03) ◽  
pp. 459-483 ◽  
Author(s):  
HANS-HELLMUT NAGEL
Keyword(s):  
Optical Flow ◽  
Autonomous Vehicles ◽  
Theoretical Foundation ◽  
Image Sequence ◽  
Flow Fields ◽  
Image Sensor ◽  
Image Sequences ◽  
Common Foundation ◽  
Feature Based ◽  
Spatio Temporal

Many investigations of image sequences can be understood on the basis of a few concepts for which computational approaches become increasingly available. The estimation of optical flow fields is discussed, exhibiting a common foundation for feature-based and differential approaches. The interpretation of optical flow fields is mostly concerned so far with approaches which infer the 3-D structure of a rigid point configuration in 3-D space and its relative motion with respect to the image sensor from an image sequence. The combination of stereo and motion provides additional incentives to evaluate image sequences, especially for the control of robots and autonomous vehicles. Advances in all these areas lead to the desire to describe the spatio-temporal development recorded by an image sequence not only at the level of geometry, but also at higher conceptual levels, for example by natural language descriptions.

Optical Flow-Based Monocular Vision/INS Integrated Navigation for Mobile Robot Indoors

2014 ◽  
Vol 538 ◽  
pp. 375-378 ◽  
Author(s):  
Xi Yuan Chen ◽  
Jing Peng Gao ◽  
Yuan Xu ◽  
Qing Hua Li
Keyword(s):  
Mobile Robot ◽  
Optical Flow ◽  
Global Positioning System ◽  
Autonomous Navigation ◽  
Image Sequences ◽  
Velocity Estimation ◽  
Monocular Vision ◽  
Integrated Navigation ◽  
Global Positioning ◽  
Flow Algorithm

This paper proposed a new algorithm for optical flow-based monocular vision (MV)/ inertial navigation system (INS) integrated navigation. In this mode, a downward-looking camera is used to get the image sequences, which is used to estimate the velocity of the mobile robot by using optical flow algorithm. INS is employed for the yaw variation. In order to evaluate the performance of the proposed method, a real indoor test has done. The result shows that the proposed method has good performance for velocity estimation. It can be applied to the autonomous navigation of mobile robots when the Global Positioning System (GPS) and code wheel is unavailable.

Active contours in optical flow fields for image sequence segmentation

2010 ◽  
Author(s):  
Thomas Sangild Sorensen ◽  
Karsten Ostergaard Noe ◽  
Christian P.V. Christoffersen ◽  
Martin Kristiansen ◽  
Kim Mouridsen ◽  
...  
Keyword(s):  
Optical Flow ◽  
Active Contours ◽  
Image Sequence ◽  
Flow Fields ◽  
Sequence Segmentation

scholarly journals Learning Multi-human Optical Flow

2020 ◽  
Vol 128 (4) ◽  
pp. 873-890 ◽  
Author(s):  
Anurag Ranjan ◽  
David T. Hoffmann ◽  
Dimitrios Tzionas ◽  
Siyu Tang ◽  
Javier Romero ◽  
...  
Keyword(s):  
Optical Flow ◽  
3D Model ◽  
Flow Fields ◽  
Human Action ◽  
Human Motion ◽  
Image Sequences ◽  
Training Data ◽  
Flow Networks ◽  
Wide Range ◽  
Human Flow

AbstractThe optical flow of humans is well known to be useful for the analysis of human action. Recent optical flow methods focus on training deep networks to approach the problem. However, the training data used by them does not cover the domain of human motion. Therefore, we develop a dataset of multi-human optical flow and train optical flow networks on this dataset. We use a 3D model of the human body and motion capture data to synthesize realistic flow fields in both single- and multi-person images. We then train optical flow networks to estimate human flow fields from pairs of images. We demonstrate that our trained networks are more accurate than a wide range of top methods on held-out test data and that they can generalize well to real image sequences. The code, trained models and the dataset are available for research.

Obstacles Perception for Serpentine Robot Based on Optical Flow Modules and Multi-Sensor Fusion

2011 ◽  
Vol 55-57 ◽  
pp. 1699-1704
Author(s):  
Jie Zhao ◽  
Zhen Feng Han ◽  
Gang Feng Liu ◽  
Yong Min Yang
Keyword(s):  
Mobile Robot ◽  
Optical Flow ◽  
Real Time ◽  
Sensor Fusion ◽  
Image Sequence ◽  
Higher Order ◽  
Experimental Results ◽  
New Approach ◽  
Environment Perception ◽  
Indoor And Outdoor

To move efficiently in an unknown environment, a mobile robot must use observations taken by various sensors to detect obstacles. This paper describes a new approach to detect obstacles for serpentine robot. It captures the image sequence and analyzed the optical flow modules to estimate the deepness of the scene. This avoids one or higher order differential in the traditional optical flow calculation. The data of ultrasonic sensor and attitude transducer sensor are fused into the algorithm to improve the real-time capability and the robustness. The detecting results are presented by fuzzy diagrams which is concise and convenient. Indoor and outdoor experimental results demonstrate that this method can provide useful and comprehensive environment perception for the robot.

Sign in / Sign up

Export Citation Format

Share Document