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 92
- Downloads 0
Mood Extraction Using Facial Features to Improve Learning Curves of Students in E-Learning Systems
Students’ interest and involvement during class lectures is imperative for grasping concepts and significantly improves academic performance of the students. Direct supervision of lectures by instructors is the main reas...
A Context-Sensitive Approach to Find Optimum Language Model for Automatic Bangla Spelling Correction
Automated spelling correction is an important phenomenon in typing that has intense effect on aiding both literate and semi-literate people while using keyboard or other similar devices. Such automated spelling correctio...
Assessment of Technology Transfer from Grid power to Photovoltaic: An Experimental Case Study for Pakistan
Pakistan is located on the world map where enough solar irradiance value strikes the ground that can be harnessed to vanish the existing blackout problems of the country. Government is focusing towards renewable integrat...
Knowledge discovery from database using an integration of clustering and classification
Clustering and classification are two important techniques of data mining. Classification is a supervised learning problem of assigning an object to one of several pre-defined categories based upon the attributes of the...
Improving DNA Computing Using Evolutionary Techniques
the field of DNA Computing has attracted many biologists and computer scientists as it has a biological interface, small size and substantial parallelism. DNA computing depends on DNA molecules’ biochemical reactions whi...