2P1-J05 Ego-motion Estimation and Obstacle Detection using Optical Flow(Robot Vision(2))

2012 ◽  
Vol 2012 (0) ◽  
pp. _2P1-J05_1-_2P1-J05_4
Author(s):  
Atsushi SANADA ◽  
Kazuo ISHII
Keyword(s):  
Motion Estimation ◽  
Optical Flow ◽  
Robot Vision ◽  
Obstacle Detection

Research of On-Road Obstacle Detection and Risk Degree Demonstration by Analyzing Difference between Model Flow Field and Observed Optical Flow Field

2009 ◽  
Vol 129 (5) ◽  
pp. 792-799
Author(s):  
Takashi Yamanaka ◽  
Masayuki Kashima ◽  
Kiminori Sato ◽  
Mutsumi Watanabe ◽  
Jun Ogata
Keyword(s):  
Flow Field ◽  
Optical Flow ◽  
Obstacle Detection ◽  
Optical Flow Field ◽  
Model Flow ◽  
Risk Degree

scholarly journals Ego-Motion Estimation Using Recurrent Convolutional Neural Networks through Optical Flow Learning

Electronics ◽  
2021 ◽  
Vol 10 (3) ◽  
pp. 222
Author(s):  
Baigan Zhao ◽  
Yingping Huang ◽  
Hongjian Wei ◽  
Xing Hu
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Motion Estimation ◽  
Optical Flow ◽  
Feature Representation ◽  
Sequential Learning ◽  
Navigation Systems ◽  
Motion State ◽  
Training Schemes ◽  
Sequential Images

Visual odometry (VO) refers to incremental estimation of the motion state of an agent (e.g., vehicle and robot) by using image information, and is a key component of modern localization and navigation systems. Addressing the monocular VO problem, this paper presents a novel end-to-end network for estimation of camera ego-motion. The network learns the latent subspace of optical flow (OF) and models sequential dynamics so that the motion estimation is constrained by the relations between sequential images. We compute the OF field of consecutive images and extract the latent OF representation in a self-encoding manner. A Recurrent Neural Network is then followed to examine the OF changes, i.e., to conduct sequential learning. The extracted sequential OF subspace is used to compute the regression of the 6-dimensional pose vector. We derive three models with different network structures and different training schemes: LS-CNN-VO, LS-AE-VO, and LS-RCNN-VO. Particularly, we separately train the encoder in an unsupervised manner. By this means, we avoid non-convergence during the training of the whole network and allow more generalized and effective feature representation. Substantial experiments have been conducted on KITTI and Malaga datasets, and the results demonstrate that our LS-RCNN-VO outperforms the existing learning-based VO approaches.

scholarly journals Optical flow analysis reveals that Kinesin-mediated advection impacts the orientation of microtubules in the Drosophila oocyte

2020 ◽  
Vol 31 (12) ◽  
pp. 1246-1258 ◽  
Author(s):  
Maik Drechsler ◽  
Lukas F. Lang ◽  
Layla Al-Khatib ◽  
Hendrik Dirks ◽  
Martin Burger ◽  
...  
Keyword(s):  
Motion Estimation ◽  
Optical Flow ◽  
Cytoplasmic Streaming ◽  
Flow Analysis ◽  
Flow Motion ◽  
A Cell

Here we introduce an optical flow motion estimation approach to study microtubule (MT) orientation in the Drosophila oocyte, a cell displaying substantial cytoplasmic streaming. We show that MT polarity is affected by the regime of these flows and, furthermore, that the presence of flows is necessary for MTs to adopt their proper polarity.

A Low-Cost Monocular Vision-Based Obstacle Avoidance Using SVM and Optical Flow

2018 ◽  
Vol 06 (04) ◽  
pp. 267-275
Author(s):  
Ajay Shankar ◽  
Mayank Vatsa ◽  
P. B. Sujit
Keyword(s):  
Optical Flow ◽  
Autonomous Navigation ◽  
Low Cost ◽  
Obstacle Detection ◽  
Monocular Vision ◽  
Support Vector ◽  
Svm Classifier ◽  
Range Finding ◽  
Image Patches ◽  
Computational Resources

Development of low-cost robots with the capability to detect and avoid obstacles along their path is essential for autonomous navigation. These robots have limited computational resources and payload capacity. Further, existing direct range-finding methods have the trade-off of complexity against range. In this paper, we propose a vision-based system for obstacle detection which is lightweight and useful for low-cost robots. Currently, monocular vision approaches used in the literature suffer from various environmental constraints such as texture and color. To mitigate these limitations, a novel algorithm is proposed, termed as Pyramid Histogram of Oriented Optical Flow ([Formula: see text]-HOOF), which distinctly captures motion vectors from local image patches and provides a robust descriptor capable of discriminating obstacles from nonobstacles. A support vector machine (SVM) classifier that uses [Formula: see text]-HOOF for real-time obstacle classification is utilized. To avoid obstacles, a behavior-based collision avoidance mechanism is designed that updates the probability of encountering an obstacle while navigating. The proposed approach depends only on the relative motion of the robot with respect to its surroundings, and therefore is suitable for both indoor and outdoor applications and has been validated through simulated and hardware experiments.

Sign in / Sign up

Export Citation Format

Share Document