Object detection and tracking under Complex environment using deep learning-based LPM

Object detection and tracking under complex environment are challenging because of the disturbances induced by background clutter, illumination changes, occlusions and other factors. The bulk of traditional algorithms basically rely on hand-crafted features, which are not sufficiently robust to a co...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IET computer vision Jg. 13; H. 2; S. 157 - 164
Hauptverfasser: Li, Yundong, Zhang, Xueyan, Li, Hongguang, Zhou, Qichen, Cao, Xianbin, Xiao, Zhifeng
Format: Journal Article
Sprache:Englisch
Veröffentlicht: The Institution of Engineering and Technology 01.03.2019
Wiley
Schlagworte:
colour histograms
deep learning-based LPM
feature extraction
hand-crafted features
histograms of oriented gradients
image colour analysis
learning (artificial intelligence)
local probability model
local probability model-based mean shift algorithm
LPM-based mean shift algorithm
MS tracking algorithm
neural nets
object detection
object tracking
probability
Special Issue: Visual Domain Adaptation and Generalisation
stacked denoising autoencoders
stacked denoising autoencoders
local probability model-based mean shift algorithm
probability
deep learning-based LPM
colour histograms
object detection
MS tracking algorithm
LPM-based mean shift algorithm
local probability model
feature extraction
histograms of oriented gradients
hand-crafted features
object tracking
image colour analysis
learning (artificial intelligence)
neural nets
ISSN:1751-9632, 1751-9640, 1751-9640
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Object detection and tracking under complex environment are challenging because of the disturbances induced by background clutter, illumination changes, occlusions and other factors. The bulk of traditional algorithms basically rely on hand-crafted features, which are not sufficiently robust to a complex environment. Moreover, the processes of detection and tracking are separated, which leads to the overall efficiency not high. In this study, a novel local probability model (LPM)-based mean shift (MS) algorithm is proposed to integrate object detection and tracking. The main contributions include: (i) a new framework based on the combination of LPM and MS is established for the integration of object tracking and detection. (ii) For object detection, the training and prediction of LPM are built by stacked denoising autoencoders based deep learning. (iii) For object tracking, an MS tracking algorithm leveraging LPM is modified to improve the tracking efficiency under a complex environment. Experimental results demonstrate that the proposed method is superior to the colour histograms based MS and histograms of oriented gradients based MS in terms of robustness and tracking accuracy.
ISSN:1751-9632
1751-9640
1751-9640
DOI:10.1049/iet-cvi.2018.5129