COMPARISON OF COMPUTER VISION ARCHITECTURES PERFORMANCE TO IMPROVE THE HEALTH PROTOCOL VIOLATIONS DETECTION

Stephen Royanmart Patrick, Robertus Setiawan Aji Nugroho

Abstract


The COVID-19 pandemic is a big problem for the world. Many things have been done to solve the problem of Covid-19, one of which is the prevention of transmission. Prevention of the transmission of COVID-19 has been carried out by many methods, one of which is the creation of a detection system based on computer vision technology.

To improve the performance of the system, researchers conducted special research that compared the performance between 3 architectures, Faster-RNN ResNet50 V1, SSD ResNet50 V1 FPN & SSD MobileNet V2 architectures. SSD ResNet50 V1 FPN was found as the best model in this test. That is because in two experiments the researcher got that model has consistency in performance. In the first experiment, mean average precision, mean average precision of medium images, mean average precision of small images, average recall, average recall for large images, average recall of medium images, and an average recall of small images SSD ResNet50 V1 FPN has the better results than others. In the second experiment, mean average precision, mean average precision of large images, mean average precision of medium images, mean average precision of small images, average recall, average recall of medium images, and an average recall of small images.


Keywords


Computer Vision; Health Violations Detection; Pandemic; Artificial Intelligence

Full Text:

PDF

References


Z. Zou, Z. Shi, Y. Guo, and J. Ye, “Object Detection in 20 Years: A Survey,” ArXiv190505055 Cs, May 2019, Accessed: Oct. 22, 2021. [Online]. Available: http://arxiv.org/abs/1905.05055

Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, no. 7553, pp. 436–444, May 2015, doi: 10.1038/nature14539.

“Google Trends,” Google Trends. https://trends.google.co.id/trends/explore?geo=ID&q=tensorflow,pytorch (accessed Oct. 22, 2021).

“TensorFlow.” https://www.tensorflow.org/ (accessed Oct. 22, 2021).

G. J. Chowdary, N. S. Punn, S. K. Sonbhadra, and S. Agarwal, “Face Mask Detection using Transfer Learning of InceptionV3,” ArXiv200908369 Cs Eess, Oct. 2020, Accessed: Oct. 09, 2021. [Online]. Available: http://arxiv.org/abs/2009.08369

S. Bianco, R. Cadene, L. Celona, and P. Napoletano, “Benchmark Analysis of Representative Deep Neural Network Architectures,” IEEE Access, vol. 6, pp. 64270–64277, 2018, doi: 10.1109/ACCESS.2018.2877890.

O. Alsing, “Mobile Object Detection using TensorFlow Lite and Transfer Learning,” Independent thesis Advanced level, KTH ROYAL INSTITUTE OF TECHNOLOGY, SCHOOL OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCE, 2018. [Online]. Available: http://kth.diva-portal.org/smash/record.jsf?pid=diva2%3A1242627

A. Campoverde and G. Barros, “Detection and Classification of Urban Actors Through TensorFlow with an Android Device,” in Information and Communication Technologies of Ecuador (TIC.EC), Cham, 2020, pp. 167–181. doi: 10.1007/978-3-030-35740-5_12.

D. Choe, E. Choi, and D. K. Kim, “The Real-Time Mobile Application for Classifying of Endangered Parrot Species Using the CNN Models Based on Transfer Learning,” Mob. Inf. Syst., vol. 2020, p. e1475164, Mar. 2020, doi: 10.1155/2020/1475164.

R. Deepa, E. Tamilselvan, E. S. Abrar, and S. Sampath, “Comparison of Yolo, SSD, Faster RCNN for Real Time Tennis Ball Tracking for Action Decision Networks,” in 2019 International Conference on Advances in Computing and Communication Engineering (ICACCE), Apr. 2019, pp. 1–4. doi: 10.1109/ICACCE46606.2019.9079965.

G. Fan, F. Chen, D. Chen, Y. Li, and Y. Dong, “A Deep Learning Model for Quick and Accurate Rock Recognition with Smartphones,” Mob. Inf. Syst., vol. 2020, p. e7462524, May 2020, doi: 10.1155/2020/7462524.

S. Ghoury, C. Sungur, and A. Durdu, “Real-Time Diseases Detection of Grape and Grape Leaves using Faster R-CNN and SSD MobileNet Architectures,” Apr. 2019. [Online]. Available: https://www.researchgate.net/publication/334987612_Real-Time_Diseases_Detection_of_Grape_and_Grape_Leaves_using_Faster_R-CNN_and_SSD_MobileNet_Architectures

P. D. Hung and N. N. Kien, “SSD-Mobilenet Implementation for Classifying Fish Species,” in Intelligent Computing and Optimization, Cham, 2020, pp. 399–408. doi: 10.1007/978-3-030-33585-4_40.

W. Wang, Y. Li, T. Zou, X. Wang, J. You, and Y. Luo, “A Novel Image Classification Approach via Dense-MobileNet Models,” Mob. Inf. Syst., vol. 2020, p. e7602384, Jan. 2020, doi: 10.1155/2020/7602384.

Y. Zhang, C. Song, and D. Zhang, “Deep Learning-Based Object Detection Improvement for Tomato Disease,” IEEE Access, vol. 8, pp. 56607–56614, 2020, doi: 10.1109/ACCESS.2020.2982456.

W. Liu et al., “SSD: Single Shot MultiBox Detector,” in Computer Vision – ECCV 2016, Cham, 2016, pp. 21–37. doi: 10.1007/978-3-319-46448-0_2.

“TFRecord and tf.train.Example | TensorFlow Core,” TensorFlow. https://www.tensorflow.org/tutorials/load_data/tfrecord (accessed Oct. 20, 2021).




DOI: https://doi.org/10.24167/proxies.v5i1.12444

Copyright (c) 2024 Proxies : Jurnal Informatika



View My Stats