Abstract
This paper presents an activity detection system using dendrite threshold logic neuron models. This method generates a dendrite weight matrix from the background image and detect the changes in the subsequent images through the trained neuron outputs. Using only one layer of dendrite neuron cells with simplistic threshold logic cells, an accuracy of 98% is reported in realistic imaging conditions. The real-time implementation of the system is done using OpenCV libraries to be deployed in raspberry pi platform.
| Original language | English |
|---|---|
| Title of host publication | 2015 International Conference on Advances in Computing, Communications and Informatics, ICACCI 2015 |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| Pages | 2307-2310 |
| Number of pages | 4 |
| ISBN (Print) | 9781479987917 |
| DOIs | |
| Publication status | Published - Sep 24 2015 |
| Event | International Conference on Advances in Computing, Communications and Informatics, ICACCI 2015 - Kerala, India Duration: Aug 10 2015 → Aug 13 2015 |
Other
| Other | International Conference on Advances in Computing, Communications and Informatics, ICACCI 2015 |
|---|---|
| Country | India |
| City | Kerala |
| Period | 8/10/15 → 8/13/15 |
Fingerprint
ASJC Scopus subject areas
- Signal Processing
- Hardware and Architecture
- Information Systems
- Computer Networks and Communications
Cite this
Activity detection with dendrite threshold model. / Bakirov, Daniyar; Dorzhigulov, Anuar; Swathikiran, S.; James, Alex Pappachen.
2015 International Conference on Advances in Computing, Communications and Informatics, ICACCI 2015. Institute of Electrical and Electronics Engineers Inc., 2015. p. 2307-2310 7275962.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Activity detection with dendrite threshold model
AU - Bakirov, Daniyar
AU - Dorzhigulov, Anuar
AU - Swathikiran, S.
AU - James, Alex Pappachen
PY - 2015/9/24
Y1 - 2015/9/24
N2 - This paper presents an activity detection system using dendrite threshold logic neuron models. This method generates a dendrite weight matrix from the background image and detect the changes in the subsequent images through the trained neuron outputs. Using only one layer of dendrite neuron cells with simplistic threshold logic cells, an accuracy of 98% is reported in realistic imaging conditions. The real-time implementation of the system is done using OpenCV libraries to be deployed in raspberry pi platform.
AB - This paper presents an activity detection system using dendrite threshold logic neuron models. This method generates a dendrite weight matrix from the background image and detect the changes in the subsequent images through the trained neuron outputs. Using only one layer of dendrite neuron cells with simplistic threshold logic cells, an accuracy of 98% is reported in realistic imaging conditions. The real-time implementation of the system is done using OpenCV libraries to be deployed in raspberry pi platform.
UR - http://www.scopus.com/inward/record.url?scp=84946228652&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84946228652&partnerID=8YFLogxK
U2 - 10.1109/ICACCI.2015.7275962
DO - 10.1109/ICACCI.2015.7275962
M3 - Conference contribution
SN - 9781479987917
SP - 2307
EP - 2310
BT - 2015 International Conference on Advances in Computing, Communications and Informatics, ICACCI 2015
PB - Institute of Electrical and Electronics Engineers Inc.
ER -