Título:	Bounding box-free instance segmentation using semi-supervised iterative learning for vehicle detection
Autor(es):	Carvalho, Osmar Luiz Ferreira de Carvalho Júnior, Osmar Abílio de Albuquerque, Anesmar Olino de Santana, Nickolas Castro Guimarães, Renato Fontes Gomes, Roberto Arnaldo Trancoso Borges, Díbio Leandro
ORCID:	https://orcid.org/ 0000-0002-5619-8525 https://orcid.org/ 0000-0002-0346-1684 https://orcid.org/ 0000-0003-1561-7583 https://orcid.org/ 0000-0001-6133-6753 https://orcid.org/ 0000-0003-4724-4064 https://orcid.org/ 0000-0002-9555-043X https://orcid.org/ 0000-0002-4868-0629
Assunto:	Imagens aéreas Veículos Aprendizagem profunda
Data de publicação:	21-Abr-2022
Editora:	IEEE
Referência:	CARVALHO, Osmar Luiz Ferreira de et al. Bounding box-free instance segmentation using semi-supervised iterative learning for vehicle detection. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, v. 15, p. 3403 - 3420, 2022. DOI: 10.1109/JSTARS.2022.3169128. Disponível em: https://ieeexplore.ieee.org/document/9761723. Acesso em: 07 jul. 2022.
Abstract:	Vehicle classification is a hot computer vision topic, with studies ranging from ground-view to top-view imagery. Top-view images allow understanding city patterns, traffic management, among others. However, there are some difficulties for pixel-wise classification: most vehicle classification studies use object detection methods, and most publicly available datasets are designed for this task, creating instance segmentation datasets is laborious, and traditional instance segmentation methods underperform on this task since the objects are small. Thus, the present research objectives are as follows: first, propose a novel semisupervised iterative learning approach using the geographic information system software, second, propose a box-free instance segmentation approach, and third, provide a city-scale vehicle dataset. The iterative learning procedure considered the following: first, labeling a few vehicles from the entire scene, second, choosing training samples near those areas, third, training the deep learning model (U-net with efficient-net-B7 backbone), fourth, classifying the whole scene, fifth, converting the predictions into shapefile, sixth, correcting areas with wrong predictions, seventh, including them in the training data, eighth repeating until results are satisfactory. We considered vehicle interior and borders to separate instances using a semantic segmentation model. When removing the borders, the vehicle interior becomes isolated, allowing for unique object identification. Our procedure is very efficient and accurate for generating data iteratively, which resulted in 122 567 mapped vehicles. Metrics-wise, our method presented higher intersection over union when compared to box-based methods (82% against 72%), and per-object metrics surpassed 90% for precision and recall.
Licença:	This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see https://creativecommons.org/licenses/by/4.0/
DOI:	10.1109/JSTARS.2022.3169128
Aparece nas coleções:	Artigos publicados em periódicos e afins

Os itens no repositório estão protegidos por copyright, com todos os direitos reservados, salvo quando é indicado o contrário.