Dezembro 2021 vol. 8 num. 4 - VII Simpósio Internacional de Inovação e Tecnologia

Literature Review - Open Access.

Idioma principal | Segundo idioma

DETECÇÃO DE OBJETOS EM IMAGENS 2D AUXILIADA POR REDES ADVERSÁRIAS GENERATIVAS: UMA REVISÃO DE LITERATURA

2D IMAGE OBJECT DETECTION AIDED BY GENERATIVE ADVERSARIAL NETWORKS A LITERATURE REVIEW

Bertolini, Caio Vinicius ; Monteiro, Roberto ;

Literature Review:

Detecção de objetos (DO) é uma das tarefas mais importantes dentro do processamento de imagens em 2D. Para isso muitos modelos foram propostos sendo os mais comuns, baseados em redes profundas convolucionais como: R-CNN, SSD e YOLO. As redes generativas adversárias (RGA’s) vêm ganhando grande destaque na academia, com aplicações diversas e resultados interessantes. O objetivo deste trabalho é avaliar a aplicação de RGA’s em tarefas de DO como potencial área de estudo. A metodologia para isso foi uma revisão de literatura sistêmica de 14 trabalhos. Concluimos que apesar de serem temas bastante populares, não existem grandes desenvolvimentos na intersecção de RGA’s e OD. Portanto, um excelente campo a ser explorado em trabalhos futuros e com grades potenciais.

Literature Review:

Object Detection (OD) is one of the most important tasks in 2D image processing. Multiple math models have been proposed and frameworks based in Deep Convolutional Networks such as R-CNN, SSD and YOLO are most common. Generative Adversarial Nets (GAN’s) represent a prominent field of study in machine learning and it has been applied to many tasks with exciting results. The objective of this work is to assess the potential of GAN’s applied to OD tasks and the proposed frameworks as field of study. The methodology used was a systemically review of 14 papers. The conclusion shows that even though OD and GAN’s are popular themes, there are not many developments done in the intersection of both subjects. Therefore, OD with GAN applied tasks are an excellent field to explore in future works.

Download (PDF)

Palavras-chave: Redes Generativas Adversárias; Detecção de Objetos; Aprendizado Profundo de Máquinas,

Palavras-chave: Generative Adversarial Nets; Object Detection; Deep Learning,

DOI: 10.5151/siintec2021-205943

Referências bibliográficas
  • [1] "1 ZOU, Zhengxia et al. Object detection in 20 years: A survey. arXiv preprint arXiv:1905.05055, 2019.
  • [2] 2 GIRSHICK, Ross et al. Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2014. p. 580-587.
  • [3] 3 GIRSHICK, Ross. Fast r-cnn. In: Proceedings of the IEEE international conference on computer vision. 2015. p. 1440-1448.
  • [4] 4 HE, Kaiming et al. Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE transactions on pattern analysis and machine intelligence, v. 37, n. 9, p. 1904-1916, 2015.
  • [5] 5 REN, Shaoqing et al. Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems, v. 28, p. 91-99, 201
  • [6] 6 REDMON, Joseph et al. You only look once: Unified, real-time object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 201 p. 779-78
  • [7] 7 LIU, Wei et al. Ssd: Single shot multibox detector. In: European conference on computer vision. Springer, Cham, 2016. p. 21-3
  • [8] 8 GOODFELLOW, Ian et al. Generative adversarial nets. Advances in neural information processing systems, v. 27, 2014.
  • [9] 9 NAVIDAN, Hojjat et al. Generative Adversarial Networks (GANs) in networking: A comprehensive survey & evaluation. Computer Networks, p. 108149, 2021.
  • [10] 10 GOOGLE SCHOLAR. Initial Page. Available at: . Access in: Jul 25th, 2021
  • [11] 11 SCIENCE DIRECT. Initial Page. Available at: < https://www.sciencedirect.com/>. Access in: Jul 25th, 2021
  • [12] 12 IEEE Xplore. Initial Page. Available at: . Access in: Jul 25th, 2021
  • [13] 13 arXiv.og. Initial Page. Available at: < https://arxiv.org/>. Access in: Jul 25th, 2021
  • [14] 14 WANG, Wanwei et al. Gan-knowledge distillation for one-stage object detection. IEEE Access, v. 8, p. 60719-60727, 2020.
  • [15] 15 PRAKASH, Charan D.; KARAM, Lina J. It GAN DO better: GAN-based detection of objects on images with varying quality. arXiv preprint arXiv:1912.01707, 2019.
  • [16] 16 HUANG, Shiyu; RAMANAN, Deva. Expecting the unexpected: Training detectors for unusual pedestrians with adversarial imposters. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2017. p. 2243-2252.
  • [17] 17 DINAKARAN, Ranjith K. et al. Deep learning based pedestrian detection at distance in smart cities. In: Proceedings of SAI Intelligent Systems Conference. Springer, Cham, 2019. p. 588-593.
  • [18] 18 DINAKARAN, Ranjith et al. Distant Pedestrian Detection in the Wild using Single Shot Detector with Deep Convolutional Generative Adversarial Networks. In: 2019 International Joint Conference on Neural Networks (IJCNN). IEEE, 2019. p. 1-7.
  • [19] 19 DINAKARAN, Ranjith; ZHANG, Li; JIANG, Richard. In-vehicle object detection in the wild for driverless vehicles. In: Developments of Artificial Intelligence Technologies in Computation and Robotics: Proceedings of the 14th International FLINS Conference (FLINS 2020). 2020. p. 1139-1147.
  • [20] 20 HUANG, Wenqing; HUANG, Mingzhu; ZHANG, Yuting. Detection of traffic signs based on combination of GAN and faster-RCNN. In: Journal of Physics: Conference Series. IOP Publishing, 2018. p. 012159.
  • [21] 21 RABBI, Jakaria et al. Small-object detection in remote sensing images with end-to-end edge-enhanced GAN and object detector network. Remote Sensing, v. 12, n. 9, p. 1432, 2020.
  • [22] 22 LI, Jianan et al. Perceptual generative adversarial networks for small object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2017. p. 1222-1230.
  • [23] 23 HALICI, Eren; ALATAN, A. Aydin. Object Localization Without Bounding Box Information Using Generative Adversarial Reinforcement Learning. In: 2018 25th IEEE International Conference on Image Processing (ICIP). IEEE, 2018. p. 3728-3732.
  • [24] 24 JANG, Heeoh et al. Generative object detection: Erasing the boundary via adversarial learning with mask. In: 2019 IEEE 2nd International Conference on Information Communication and Signal Processing (ICICSP). IEEE, 2019. p. 495-499. 25 DIBA, Ali et al. Weakly supervised object discovery by generative adversarial & ranking networks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. 2019. p. 0-0."
Como citar:

Bertolini, Caio Vinicius; Monteiro, Roberto; "DETECÇÃO DE OBJETOS EM IMAGENS 2D AUXILIADA POR REDES ADVERSÁRIAS GENERATIVAS: UMA REVISÃO DE LITERATURA", p. 353-360 . In: VII International Symposium on Innovation and Technology. São Paulo: Blucher, 2021.
ISSN 2357-7592, DOI 10.5151/siintec2021-205943

últimos 30 dias | último ano | desde a publicação


downloads


visualizações


indexações