Bio-inspired small target motion detector with a new lateral inhibition mechanism

Wang, Hongxin and Peng, Jigen and Yue, Shigang (2016) Bio-inspired small target motion detector with a new lateral inhibition mechanism. In: 2016 International Joint Conference on Neural Networks (IJCNN 2016), 24-29 July 2016, Vancouver, BC, Canada.

Full content URL: http://doi.org/10.1109/IJCNN.2016.7727824

Documents
Bio-inspired small target motion detector with a new lateral inhibition mechanism

Request a copy
[img] PDF
STMD.pdf - Whole Document
Restricted to Repository staff only

2MB
Item Type:Conference or Workshop contribution (Presentation)
Item Status:Live Archive

Abstract

In nature, it is an important task for animals to detect small targets which move within cluttered background. In recent years, biologists have found that a class of neurons in the lobula complex, called STMDs (small target motion detectors) which have extreme selectivity for small targets moving within visual clutter. At the same time, some researchers assert that lateral inhibition plays an important role in discriminating the motion of the target from the motion of the background , even account for many features of the tuning of higher order visual neurons. Inspired by the finding that complete lateral inhibition can only be seen when the motion of the central region is identical to the motion of the peripheral region, we propose a new lateral inhibition mechanism combined with motion velocity and direction to improve the performance of ESTMD model (elementary small target motion detector). In this paper, we will elaborate on the biological plausibility and functionality of this new lateral inhibition mechanism in small target motion
detection.

Keywords:Small Target Motion Detection, Lateral Inhibition, Cluttered Backgrounds
Subjects:G Mathematical and Computer Sciences > G730 Neural Computing
G Mathematical and Computer Sciences > G400 Computer Science
G Mathematical and Computer Sciences > G700 Artificial Intelligence
Divisions:College of Science > School of Computer Science
ID Code:33109
Deposited On:13 Sep 2018 12:31

Repository Staff Only: item control page