Multiple classifier-based spatiotemporal features for living activity prediction

Abstract

Nowadays, the action prediction technique plays an important role in many automatic systems. There are some proposed methods for this issue. However, they retain limitations such as accuracy and computational time, especially for applying in limited resource systems. This paper presents an approach to enhance the efficiency of the activity prediction task. The work processes on multiple classifiers using spatiotemporal features based on scalable feature descriptors, such as histogram of oriented gradients (HOG), histogram of oriented optical flow (HOF), and motion boundary histogram (MBH). In order to improve prediction accuracy, two layers of classified machine models are studied for applying on spatiotemporal features with the dynamic foreground extraction process. The first layer based on unsupervised classification is proposed to construct a dictionary of features, which supports for distinguishing and uniform the number of features. The next task is that supervised machine learning supports for final decision of action classes. The proposed approach was evaluated on several benchmark datasets, which are available online. The results demonstrate that the approach enhances accuracy and efficiency of the prediction system. ARTICLE HISTORY

Pedestrian Activity Prediction Based on Semantic Segmentation and Hybrid of Machines

“…In the other solution of pedestrian action prediction proposed [7,8,13], our most recent article [16] addresses the interaction between cars and pedestrians. However, in this proposal of paper, there are only 3 cases in which pedestrian action features are extracted, classified and predicted, including pedestrian crossing, pedestrian waiting and pedestrian walking.…”

Requirements engineering of Malaysian radiological medical emergency response simulator

“…Data generation activity provided individual terms of information; edited research participants' perceptions were later sorted, grouped and transcribed as categories determined by the ISDT key concepts (that referred to thematic coding procedure) (Avison & Fitzgerald, 2006). Contingency analysis or ranking, a survey-based method and a choice-based modelling focused on preferences modelling of the emergency planning key processes and activities described according to their attributes and levels (Asgary & Mousavi-Jahromi, 2011) (Hoang, 2017). Attribute valuation of the contingent ranking allows more than one direct route of valuation.…”

Human Activity Recognition Using Gaussian Mixture Hidden Conditional Random Fields

“…ere are four modules in a typical HAR system: preprocessing (segmentation), feature extraction, feature selection, and recognition as shown in Figure 1. Most of the existing works [18][19][20][21][22][23] focused on feature extraction and selection; however, very limited works have been done for the recognition module. Some studies exploited conventional techniques [24][25][26][27][28].…”