Reducing-Over-Time Tree for Event-based Data

Shane Harrigan; Sonya Coleman; Dermot Kerr; Y Pratheepan; Zheng Fang; Chengdong Wu

Reducing-Over-Time Tree for Event-based Data

Shane Harrigan
, Sonya Coleman
, Dermot Kerr
, Y Pratheepan
, Zheng Fang
, Chengdong Wu

Northeastern University China

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

227 Downloads (Pure)

Abstract

This paper presents a novel Reducing-Over-Time (ROT) binary tree structure for event-based vision data and sub- types of the tree structure. A framework is presented using ROT, that takes advantage of the self-balancing and self-pruning nature of the tree structure to extract spatial-temporal information. The ROT framework is paired with an established motion classification technique and performance is evaluated against other state-of-the-art techniques using four datasets. Additionally, the ROT framework as a processing platform is compared with other event-based vision processing platforms in terms of memory usage and is found to be one of the most memory efficient platforms available.

Original language	English
Title of host publication	The 25th IEEE International Conference on Pattern Recognition
Number of pages	8
Publication status	Accepted - 21 Jun 2020
Event	The 25th IEEE International Conference on Pattern Recognition - Milan, Italy Duration: 10 Jan 2021 → 15 Jan 2021 Conference number: 25th https://www.micc.unifi.it/icpr2020/

Conference

Conference	The 25th IEEE International Conference on Pattern Recognition
Abbreviated title	ICPR2020
Country/Territory	Italy
City	Milan
Period	10/01/21 → 15/01/21
Internet address	https://www.micc.unifi.it/icpr2020/

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 9 Industry, Innovation, and Infrastructure

Keywords

Bio-inspired
Neuromorphic
Computer Vision
Feature Extraction
Corner Detection
Edge Detection
Motion Recognition

Access to Document

Accepted Vers SHarriganAuthor Accepted Manuscript, 4.33 MB

Neuromorphic vision processing
Harrigan, S. (Author), Yogarajah, P. (Supervisor), Coleman, S. (Supervisor) & Kerr, D. (Supervisor), Dec 2020
Student thesis: Doctoral Thesis

File

Cite this

@inproceedings{c74d5bd1626a4a28a12457de4deaa962,

title = "Reducing-Over-Time Tree for Event-based Data",

abstract = "This paper presents a novel Reducing-Over-Time (ROT) binary tree structure for event-based vision data and sub- types of the tree structure. A framework is presented using ROT, that takes advantage of the self-balancing and self-pruning nature of the tree structure to extract spatial-temporal information. The ROT framework is paired with an established motion classification technique and performance is evaluated against other state-of-the-art techniques using four datasets. Additionally, the ROT framework as a processing platform is compared with other event-based vision processing platforms in terms of memory usage and is found to be one of the most memory efficient platforms available.",

keywords = "Bio-inspired, Neuromorphic, Computer Vision, Feature Extraction, Corner Detection, Edge Detection, Motion Recognition",

author = "Shane Harrigan and Sonya Coleman and Dermot Kerr and Y Pratheepan and Zheng Fang and Chengdong Wu",

year = "2020",

month = jun,

day = "21",

language = "English",

booktitle = "The 25th IEEE International Conference on Pattern Recognition",

note = " The 25th IEEE International Conference on Pattern Recognition, ICPR2020 ; Conference date: 10-01-2021 Through 15-01-2021",

url = "https://www.micc.unifi.it/icpr2020/",

}

TY - GEN

T1 - Reducing-Over-Time Tree for Event-based Data

AU - Harrigan, Shane

AU - Coleman, Sonya

AU - Kerr, Dermot

AU - Pratheepan, Y

AU - Fang, Zheng

AU - Wu, Chengdong

N1 - Conference code: 25th

PY - 2020/6/21

Y1 - 2020/6/21

N2 - This paper presents a novel Reducing-Over-Time (ROT) binary tree structure for event-based vision data and sub- types of the tree structure. A framework is presented using ROT, that takes advantage of the self-balancing and self-pruning nature of the tree structure to extract spatial-temporal information. The ROT framework is paired with an established motion classification technique and performance is evaluated against other state-of-the-art techniques using four datasets. Additionally, the ROT framework as a processing platform is compared with other event-based vision processing platforms in terms of memory usage and is found to be one of the most memory efficient platforms available.

AB - This paper presents a novel Reducing-Over-Time (ROT) binary tree structure for event-based vision data and sub- types of the tree structure. A framework is presented using ROT, that takes advantage of the self-balancing and self-pruning nature of the tree structure to extract spatial-temporal information. The ROT framework is paired with an established motion classification technique and performance is evaluated against other state-of-the-art techniques using four datasets. Additionally, the ROT framework as a processing platform is compared with other event-based vision processing platforms in terms of memory usage and is found to be one of the most memory efficient platforms available.

KW - Bio-inspired

KW - Neuromorphic

KW - Computer Vision

KW - Feature Extraction

KW - Corner Detection

KW - Edge Detection

KW - Motion Recognition

M3 - Conference contribution

BT - The 25th IEEE International Conference on Pattern Recognition

T2 - The 25th IEEE International Conference on Pattern Recognition

Y2 - 10 January 2021 through 15 January 2021

ER -

Reducing-Over-Time Tree for Event-based Data

Abstract

Conference

UN SDGs

Keywords

Access to Document

Fingerprint

Student theses

Neuromorphic vision processing

Cite this