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...
Guardado en:
Autores principales: | , , , |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
MDPI AG
2021
|
Materias: | |
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 |