Brain Strategy Algorithm for Multiple Object Tracking Based on Merging Semantic Attributes and Appearance Features

The human brain can effortlessly perform vision processes using the visual system, which helps solve multi-object tracking (MOT) problems. However, few algorithms simulate human strategies for solving MOT. Therefore, devising a method that simulates human activity in vision has become a good choice...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Mai S. Diab, Mostafa A. Elhosseini, Mohamed S. El-Sayed, Hesham A. Ali
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	multiple object tracking data association dataset deep learning semantic attribute Chemical technology TP1-1185
Acceso en línea:	https://doaj.org/article/f3be6e88b9564e13819d62308b79885c
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:f3be6e88b9564e13819d62308b79885c
record_format	dspace
spelling	oai:doaj.org-article:f3be6e88b9564e13819d62308b79885c2021-11-25T18:57:53ZBrain Strategy Algorithm for Multiple Object Tracking Based on Merging Semantic Attributes and Appearance Features10.3390/s212276041424-8220https://doaj.org/article/f3be6e88b9564e13819d62308b79885c2021-11-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/22/7604https://doaj.org/toc/1424-8220The human brain can effortlessly perform vision processes using the visual system, which helps solve multi-object tracking (MOT) problems. However, few algorithms simulate human strategies for solving MOT. Therefore, devising a method that simulates human activity in vision has become a good choice for improving MOT results, especially occlusion. Eight brain strategies have been studied from a cognitive perspective and imitated to build a novel algorithm. Two of these strategies gave our algorithm novel and outstanding results, rescuing saccades and stimulus attributes. First, rescue saccades were imitated by detecting the occlusion state in each frame, representing the critical situation that the human brain saccades toward. Then, stimulus attributes were mimicked by using semantic attributes to reidentify the person in these occlusion states. Our algorithm favourably performs on the MOT17 dataset compared to state-of-the-art trackers. In addition, we created a new dataset of 40,000 images, 190,000 annotations and 4 classes to train the detection model to detect occlusion and semantic attributes. The experimental results demonstrate that our new dataset achieves an outstanding performance on the scaled YOLOv4 detection model by achieving a 0.89 mAP 0.5.Mai S. DiabMostafa A. ElhosseiniMohamed S. El-SayedHesham A. AliMDPI AGarticlemultiple object trackingdata associationdatasetdeep learningsemantic attributeChemical technologyTP1-1185ENSensors, Vol 21, Iss 7604, p 7604 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	multiple object tracking data association dataset deep learning semantic attribute Chemical technology TP1-1185
spellingShingle	multiple object tracking data association dataset deep learning semantic attribute Chemical technology TP1-1185 Mai S. Diab Mostafa A. Elhosseini Mohamed S. El-Sayed Hesham A. Ali Brain Strategy Algorithm for Multiple Object Tracking Based on Merging Semantic Attributes and Appearance Features
description	The human brain can effortlessly perform vision processes using the visual system, which helps solve multi-object tracking (MOT) problems. However, few algorithms simulate human strategies for solving MOT. Therefore, devising a method that simulates human activity in vision has become a good choice for improving MOT results, especially occlusion. Eight brain strategies have been studied from a cognitive perspective and imitated to build a novel algorithm. Two of these strategies gave our algorithm novel and outstanding results, rescuing saccades and stimulus attributes. First, rescue saccades were imitated by detecting the occlusion state in each frame, representing the critical situation that the human brain saccades toward. Then, stimulus attributes were mimicked by using semantic attributes to reidentify the person in these occlusion states. Our algorithm favourably performs on the MOT17 dataset compared to state-of-the-art trackers. In addition, we created a new dataset of 40,000 images, 190,000 annotations and 4 classes to train the detection model to detect occlusion and semantic attributes. The experimental results demonstrate that our new dataset achieves an outstanding performance on the scaled YOLOv4 detection model by achieving a 0.89 mAP 0.5.
format	article
author	Mai S. Diab Mostafa A. Elhosseini Mohamed S. El-Sayed Hesham A. Ali
author_facet	Mai S. Diab Mostafa A. Elhosseini Mohamed S. El-Sayed Hesham A. Ali
author_sort	Mai S. Diab
title	Brain Strategy Algorithm for Multiple Object Tracking Based on Merging Semantic Attributes and Appearance Features
title_short	Brain Strategy Algorithm for Multiple Object Tracking Based on Merging Semantic Attributes and Appearance Features
title_full	Brain Strategy Algorithm for Multiple Object Tracking Based on Merging Semantic Attributes and Appearance Features
title_fullStr	Brain Strategy Algorithm for Multiple Object Tracking Based on Merging Semantic Attributes and Appearance Features
title_full_unstemmed	Brain Strategy Algorithm for Multiple Object Tracking Based on Merging Semantic Attributes and Appearance Features
title_sort	brain strategy algorithm for multiple object tracking based on merging semantic attributes and appearance features
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/f3be6e88b9564e13819d62308b79885c
work_keys_str_mv	AT maisdiab brainstrategyalgorithmformultipleobjecttrackingbasedonmergingsemanticattributesandappearancefeatures AT mostafaaelhosseini brainstrategyalgorithmformultipleobjecttrackingbasedonmergingsemanticattributesandappearancefeatures AT mohamedselsayed brainstrategyalgorithmformultipleobjecttrackingbasedonmergingsemanticattributesandappearancefeatures AT heshamaali brainstrategyalgorithmformultipleobjecttrackingbasedonmergingsemanticattributesandappearancefeatures
_version_	1718410501188222976

Brain Strategy Algorithm for Multiple Object Tracking Based on Merging Semantic Attributes and Appearance Features

Ejemplares similares