Human body modelling for people localization and tracking from real image sequences

1995 ◽  
Author(s):  
A. Tesei
Keyword(s):  
Human Body ◽  
Image Sequences ◽  
Real Image ◽  
Localization And Tracking

scholarly journals INTEGRATION OF A GENERALISED BUILDING MODEL INTO THE POSE ESTIMATION OF UAS IMAGES

2016 ◽  
Vol XLI-B1 ◽  
pp. 1057-1064 ◽  
Author(s):  
J. Unger ◽  
F. Rottensteiner ◽  
C. Heipke
Keyword(s):  
Pose Estimation ◽  
Image Sequence ◽  
Image Sequences ◽  
Bundle Adjustment ◽  
Unmanned Aerial System ◽  
Real Image ◽  
Building Model ◽  
Current State ◽  
Image Orientation

A hybrid bundle adjustment is presented that allows for the integration of a generalised building model into the pose estimation of image sequences. These images are captured by an Unmanned Aerial System (UAS) equipped with a camera flying in between the buildings. The relation between the building model and the images is described by distances between the object coordinates of the tie points and building model planes. Relations are found by a simple 3D distance criterion and are modelled as fictitious observations in a Gauss-Markov adjustment. The coordinates of model vertices are part of the adjustment as directly observed unknowns which allows for changes in the model. Results of first experiments using a synthetic and a real image sequence demonstrate improvements of the image orientation in comparison to an adjustment without the building model, but also reveal limitations of the current state of the method.

scholarly journals Computer Vision Intelligent Approaches to Extract Human Pose and Its Activity from Image Sequences

Electronics ◽  
2020 ◽  
Vol 9 (1) ◽  
pp. 159
Author(s):  
Paulo J. S. Gonçalves ◽  
Bernardo Lourenço ◽  
Samuel Santos ◽  
Rodolphe Barlogis ◽  
Alexandre Misson
Keyword(s):  
Computer Vision ◽  
Human Body ◽  
Prediction Models ◽  
Image Sequences ◽  
Video Frame ◽  
Support Vector ◽  
Training Phase ◽  
Human Body Model ◽  
Body Model ◽  
Human Pose

The purpose of this work is to develop computational intelligence models based on neural networks (NN), fuzzy models (FM), support vector machines (SVM) and long short-term memory networks (LSTM) to predict human pose and activity from image sequences, based on computer vision approaches to gather the required features. To obtain the human pose semantics (output classes), based on a set of 3D points that describe the human body model (the input variables of the predictive model), prediction models were obtained from the acquired data, for example, video images. In the same way, to predict the semantics of the atomic activities that compose an activity, based again in the human body model extracted at each video frame, prediction models were learned using LSTM networks. In both cases the best learned models were implemented in an application to test the systems. The SVM model obtained 95.97% of correct classification of the six different human poses tackled in this work, during tests in different situations from the training phase. The implemented LSTM learned model achieved an overall accuracy of 88%, during tests in different situations from the training phase. These results demonstrate the validity of both approaches to predict human pose and activity from image sequences. Moreover, the system is capable of obtaining the atomic activities and quantifying the time interval in which each activity takes place.

Training a CNN to robustly segment the human body parts in range image sequences

2019 ◽  
Author(s):  
Lama Seoud ◽  
Jonathan Boisvert ◽  
Marc-Antoine Drouin ◽  
Michel Picard ◽  
Guy Godin
Keyword(s):  
Human Body ◽  
Image Sequences ◽  
Range Image ◽  
Body Parts

Recognition of Human Silhouette Based on Global Features

2010 ◽  
Vol 1 (4) ◽  
pp. 47-55 ◽  
Author(s):  
Milene Arantes ◽  
Adilson Gonzaga
Keyword(s):  
Human Body ◽  
Gait Recognition ◽  
Human Motion ◽  
Image Sequences ◽  
Video Sequences ◽  
Fusion Model ◽  
Global Features ◽  
Image Models ◽  
Human Joints ◽  
Human Silhouette

The aim of this paper is people recognition based on their gait. The authors propose a computer vision approach applied to video sequences extracting global features of human motion. From the skeleton, the authors extract the information about human joints. From the silhouette and the authors get the boundary features of the human body. The binary and gray-level-images contain different aspects about the human motion. This work proposes to recover the global information of the human body based on four segmented image models and applies a fusion model to improve classification. The authors consider frames as elements of distinct classes of video sequences and the sequences themselves as classes in a database. The classification rates obtained separately from four image sequences are then merged together by a fusion technique. The results were then compared with other techniques for gait recognition.

scholarly journals A Bayesian Framework for Human Body Pose Tracking from Depth Image Sequences

Sensors ◽  
2010 ◽  
Vol 10 (5) ◽  
pp. 5280-5293 ◽  
Author(s):  
Youding Zhu ◽  
Kikuo Fujimura
Keyword(s):  
Human Body ◽  
Bayesian Framework ◽  
Image Sequences ◽  
Depth Image ◽  
Pose Tracking
Sign in / Sign up

Export Citation Format

Share Document