Search Region Prediction for Motion Estimation Based on Neural Network Vector Quantization

2006 ◽  
pp. 460-467
Author(s):  
DaeHyun Ryu ◽  
HyungJun Kim
Keyword(s):  
Neural Network ◽  
Motion Estimation ◽  
Vector Quantization ◽  
Search Region

Motion search region prediction using neural network vector quantization

2002 ◽  
Author(s):  
D.H. Ryu ◽  
C.R. Kim ◽  
S.W. Kim ◽  
T.W. Choi ◽  
J.C. Kim
Keyword(s):  
Neural Network ◽  
Vector Quantization ◽  
Search Region ◽  
Motion Search

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.

Vector Quantization Training By A Self-Organizing Neural Network

1988 ◽  
Author(s):  
Thomas W. Ryan ◽  
Charles A. Cotter
Keyword(s):  
Neural Network ◽  
Vector Quantization ◽  
Self Organizing

Cardiac motion estimation using pyramid, warping, and cost volume neural network

2021 ◽  
Author(s):  
Catharine V. Graves ◽  
Ramon A. Moreno ◽  
Marina F. S. Rebelo ◽  
Adriano Bordignom ◽  
Cesar H. Nomura ◽  
...  
Keyword(s):  
Neural Network ◽  
Motion Estimation ◽  
Cardiac Motion

scholarly journals Diagnosa Penyakit Demam Berdarah Dengue (DBD) menggunakan Metode Learning Vector Quantization (LVQ)

2020 ◽  
Vol 4 (3) ◽  
pp. 56
Author(s):  
Firman Tawakal ◽  
Ahmedika Azkiya
Keyword(s):  
Neural Network ◽  
Typhoid Fever ◽  
Vector Quantization ◽  
Dengue Hemorrhagic Fever ◽  
Hemorrhagic Fever ◽  
Learning Vector Quantization ◽  
Mean Square ◽  
Northern Australia ◽  
Neural Network Learning ◽  
Network Learning

Dengue Hemorrhagic Fever is a disease that is carried and transmitted through the mosquito Aedes aegypti and Aedes albopictus which is commonly found in tropical and subtropical regions such as in Indonesia to Northern Australia. in 2013 there are 2.35 million reported cases, which is 37,687 case is heavy cases of DHF. DHF’s symthoms have a similarity with typhoid fever, it often occur wrong handling. Therefore we need a system that is able to diagnose the disease suffered by patients, so that they can recognize whether the patient has DHF or Typhoid. The system will be built using Neural Network Learning Vector Quantization (LVQ) based on the best training results. This research is to diagnose Dengue Hemorrhagic Fever using LVQ with input parameters are hemoglobin, leukocytes, platelets, and heritrocytes. Based on result, the best accuracy is 97,14% with Mean Square Error (MSE) is 0.028571 with 84 train data and 36 test data. Conclution from the research is LVQ method can diagnose DHF Keywords: Dengue Hemorrhagic Fever; Learning Vector Quantization; classification; Neural Network;

Emotion Recognition From Speech Using Perceptual Filter and Neural Network

2020 ◽  
pp. 78-91 ◽  
Author(s):  
Revathi A. ◽  
Sasikaladevi N.
Keyword(s):  
Neural Network ◽  
Emotion Recognition ◽  
Vector Quantization ◽  
Group Performance ◽  
Back Propagation ◽  
Critical Band ◽  
Emotion Classification ◽  
Back Propagation Algorithm ◽  
Propagation Algorithm ◽  
Speaker Independent

This chapter on multi speaker independent emotion recognition encompasses the use of perceptual features with filters spaced in Equivalent rectangular bandwidth (ERB) and BARK scale and vector quantization (VQ) classifier for classifying groups and artificial neural network with back propagation algorithm for emotion classification in a group. Performance can be improved by using the large amount of data in a pertinent emotion to adequately train the system. With the limited set of data, this proposed system has provided consistently better accuracy for the perceptual feature with critical band analysis done in ERB scale.

Sign in / Sign up

Export Citation Format

Share Document