OpenCL-Accelerated Object Classification in Video Streams using Spatial Pooler of Hierarchical Temporal Memory
Journal Title: International Journal of Advanced Computer Science & Applications - Year 2017, Vol 8, Issue 2
Abstract
The paper presents a method to classify objects in video streams using a brain-inspired Hierarchical Temporal Memory (HTM) algorithm. Object classification is a challeng-ing task where humans still significantly outperform machine learning algorithms due to their unique capabilities. A system which achieves very promising performance in terms of recogni-tion accuracy have been implemented. Unfortunately, conducting more advanced experiments is very computationally demanding; some of the trials run on a standard CPU may take as long as several days for 960x540 video streams frames. Therefore, authors decided to accelerate selected parts of the system using OpenCL. In particular, authors seek to determine to what extent porting selected and computationally demanding parts of a core may speed up calculations. The classification accuracy of the system was examined through a series of experiments and the performance was given in terms of F1 score as a function of the number of columns, synapses, min overlap and winners set size. The system achieves the highest F1 score of 0.95 and 0.91 for min overlap=4 and 256 synapses, respectively. Authors have also conduced a series of experiments with different hardware setups and measured CPU/GPU acceleration. The best kernel speed-up of 632x and 207x was reached for 256 synapses and 1024 columns. However, overall acceleration including transfer time was significantly lower and amounted to 6.5x and 3.2x for the same setup.
Authors and Affiliations
Maciej Wielgosz, Marcin Pietron
Keywords
Related Articles
- EP ID EP249204
- DOI 10.14569/IJACSA.2017.080245
- Views 121
- Downloads 0
A Survey on Models and Query Languages for Temporally Annotated RDF
In this paper, we provide a survey on the models and query languages for temporally annotated RDF. In most of the works, a temporally annotated RDF ontology is essentially a set of RDF triples associated with temporal co...
Image Processing based Task Allocation for Autonomous Multi Rotor Unmanned Aerial Vehicles
Nowadays studies based on unmanned aerial vehicles draws attention. Especially image processing based tasks are quite important. In this study, several tasks were performed based on the autonomous flight, image processin...
A Comprehensive Collaborating Filtering Approach using Extended Matrix Factorization and Autoencoder in Recommender System
Recommender system is an approach where users get suggestions based on their previous preferences. Nowadays, people are overwhelmed by the huge amount of information that is being present in any system. Sometimes, it is...
Jigsopu: Square Jigsaw Puzzle Solver with Pieces of Unknown Orientation
In this paper, we consider the square jigsaw puzzle problem in which one is required to reassemble the complete image from a number of unordered square puzzle pieces. Here we focus on the special case where both location...
Brainwaves for User Verification using Two Separate Sets of Features based on DCT and Wavelet
This paper discusses the effectiveness of brain waves for user verification using electroencephalogram (EEG) recordings of one channel belong to single task. The feature sets were previously introduced as features for EE...