Abstract
The convolutional neural networks had enormous success in the classification of images, and networks such as “AlexNet”, “VGG”, “Inception” and “ResNet” were references for this purpose. This way, it is intended to verify which networks were more successful in the “Imagenet” dataset challenge. Then, it was verified their success when classifying videos through the “Kinetics400” and “UCF101” datasets and, finally, to conclude if the success in the classification of images can also evidence a possible success in the classification of videos. To this end, the margin of error of the networks mentioned above is compared. The two networks with the lowest margin of error are selected, and these networks are studied to classify videos. Thus, if these networks are successful, they can receive input videos from sensors and accurately identify the human activity present in the video. It should be noted that the networks “ResNet” and “Inception” had very satisfactory success rates, above 70%, showing success in the approach adopted.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Yamashita R, Nishio M, Do R, Togashi K (2018) Convolutional neural networks: an overview and application in radiology. Retrieved from https://insightsimaging.springeropen.com/articles/10.1007/s13244-018-0639-9
SAS (2019) Neural networks what they are & why they matter. Retrieved from https://www.sas.com/en_us/insights/analytics/neural-networks.html
Ebermam E, Krohling R (2018) Uma Introdução Compreensiva às Redes Neurais Convolucionais: Um Estudo de Caso para Reconhecimento de Caracteres Alfabéticos. Retrieved from http://www.fsma.edu.br/si/edicao21/FSMA_SI_2018_1_Principal_08.pdf
Balaji S (2020) Binary image classifier CNN using TensorFlow. https://medium.com/techiepedia/binary-image-classifier-cnn-using-tensorflow-a3f5d6746697
Florindo J (2018) Redes Neurais Convolucionais—deep learning. Retrieved from https://www.ime.unicamp.br/~jbflorindo/Teaching/2018/MT530/T10.pdf
Amor E (2020) Important CNN architectures. Retrieved April 16, 2021, from https://www.topbots.com/important-cnn-architectures/
Hacker D (2018). B CNN AlexNet. Retrieved from http://datahacker.rs/deep-learning-alexnet-architecture/
Team GL (2020) AlexNet: the first CNN to win image net. Retrieved from https://www.mygreatlearning.com/blog/alexnet-the-first-cnn-to-win-image-net/
Neurohive (2018) VGG16—convolutional network for classification and detection. Retrieved from https://neurohive.io/en/popular-networks/vgg16/
Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. Retrieved from https://arxiv.org/pdf/1409.1556.pdf
Sermanet P (Google I., Liu W (University of N. C., Reed S (University of M. (2014) Going deeper with convolutions. Retrieved from https://arxiv.org/pdf/1409.4842.pdf
Karim R (2019) 10 CNN Architectures. Towards data science. Retrieved from https://towardsdatascience.com/illustrated-10-cnn-architectures-95d78ace614d#6872
Feng V (2017) An overview of ResNet and its variants. Towards Data Science. https://towardsdatascience.com/an-overview-of-resnet-and-its-variants-5281e2f56035
He K, Zhang X, Ren S, Sun J (2015). Deep residual learning for image recognition. Retrieved from https://arxiv.org/pdf/1512.03385.pdf
Sharma P (2020) 7 popular image classification models in ImageNet challenge (ILSVRC) competition history. Retrieved from https://machinelearningknowledge.ai/popular-image-classification-models-in-imagenet-challenge-ilsvrc-competition-history/
Krizhevsky A, Sutskever I, Hinton G (2016) ImageNet classification with deep convolutional neural networks. Retrieved from https://www.cs.toronto.edu/~kriz/imagenet_classification_with_deep_convolutional.pdf
Google (2017) The kinetics human action video dataset. Retrieved from https://arxiv.org/pdf/1705.06950.pdf
Soomro K, Zamir A, Shah M (2012) UCF101: a dataset of 101 human actions classes from videos in the wild. Retrieved from https://arxiv.org/pdf/1212.0402.pdf
Rosebrock A (2019) Human activity recognition with OpenCV and deep learning. Retrieved from https://www.pyimagesearch.com/2019/11/25/human-activity-recognition-with-opencv-and-deep-learning/
Acknowledgements
This work has been supported by FCT—Fundação para a Ciência e Tecnologia within the R&D Units Project Scope: UIDB/00319/2020 and supervised by IOTECH.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Azevedo, J., Portela, F. (2022). Convolutional Neural Network—A Practical Case Study. In: Ullah, A., Anwar, S., Rocha, Á., Gill, S. (eds) Proceedings of International Conference on Information Technology and Applications. Lecture Notes in Networks and Systems, vol 350. Springer, Singapore. https://doi.org/10.1007/978-981-16-7618-5_27
Download citation
DOI: https://doi.org/10.1007/978-981-16-7618-5_27
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-7617-8
Online ISBN: 978-981-16-7618-5
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)