International Journal of Image, Graphics and Signal Processing (IJIGSP)
IJIGSP Vol. 15, No. 1, 8 Feb. 2023
Cover page and Table of Contents: PDF (size: 1003KB)
Real-Time Video based Human Suspicious Activity Recognition with Transfer Learning for Deep Learning
Full Text (PDF, 1003KB), PP.47-62
Views: 0 Downloads: 0
Author(s)
Index Terms
Convolutional neural network, human suspicious activity recognition, pre-trained models, transfer learning, real-time human activity recognition, VGG16 and ResNet50.
Abstract
Nowadays, the primary concern of any society is providing safety to an individual. It is very hard to recognize the human behaviour and identify whether it is suspicious or normal. Deep learning approaches paved the way for the development of various machine learning and artificial intelligence. The proposed system detects real-time human activity using a convolutional neural network. The objective of the study is to develop a real-time application for Activity recognition using with and without transfer learning methods. The proposed system considers criminal, suspicious and normal categories of activities. Differentiate suspicious behaviour videos are collected from different peoples(men/women). This proposed system is used to detect suspicious activities of a person. The novel 2D-CNN, pre-trained VGG-16 and ResNet50 is trained on video frames of human activities such as normal and suspicious behaviour. Similarly, the transfer learning in VGG16 and ResNet50 is trained using human suspicious activity datasets. The results show that the novel 2D-CNN, VGG16, and ResNet50 without transfer learning achieve accuracy of 98.96%, 97.84%, and 99.03%, respectively. In Kaggle/real-time video, the proposed system employing 2D-CNN outperforms the pre-trained model VGG16. The trained model is used to classify the activity in the real-time captured video. The performance obtained on ResNet50 with transfer learning accuracy of 99.18% is higher than VGG16 transfer learning accuracy of 98.36%.
Cite This Paper
Indhumathi .J, Balasubramanian .M, Balasaigayathri .B, "Real-Time Video based Human Suspicious Activity Recognition with Transfer Learning for Deep Learning", International Journal of Image, Graphics and Signal Processing(IJIGSP), Vol.15, No.1, pp. 47-62, 2023. DOI:10.5815/ijigsp.2023.01.05
Reference
[1] Allah Bux Sargano et..al., 2017 International Joint Conference on Neural Networks (IJCNN),“Human Action Recognition using Transfer Learning with Deep Representations”, IEEE,2017.
[2] Amrutha, C.V; Jyotsna, C. Amudha, J. (2020). [IEEE 2020 2nd International Conference on Innovative Mechanisms for Industry Applications (ICIMIA) - Bangalore, India] 2020 2nd International Conference on Innovative Mechanisms for Industry Applications (ICIMIA) - Deep Learning Approach for Suspicious Activity Detection from Surveillance Video, 335–339.
[3] Al Amin Biswas;Md. Mahbubur Rahman;Aditya Rajbongshi;Anup Majumder; (2021). Recognition of Local Birds using Different CNN Architectures with Transfer Learning. International Conference on Computer Communication and Informatics (ICCCI), 2021.
[4] Mutegeki, Ronald; Han, Dong Seog (2019). IEEE International Conference on Information and Communication Technology Convergence (ICTC) Feature-Representation Transfer Learning for Human Activity Recognition, 18–20,2019.
[5] Yousry Abdulazeem;Hossam Magdy Balaha;Waleed M. Bahgat;Mahmoud Badawy, IEEE Access, Human Action Recognition Based on Transfer Learning Approach,2021.
[6] Phan, Ha Tran Hong; Kumar, Ashnil; Kim, Jinman; Feng, Dagan. IEEE 2016 13th International Symposium on Biomedical Imaging (ISBI 2016) - Prague, Czech Republic” Transfer learning of a convolutional neural network for HEp-2 cell image classification, 1208–1211.
[7] Islam, Md Shafiqul; Okita, Tsuyoshi; Inoue, Sozo, 2019 IEEE Intl Conf on Dependable, Autonomic and Secure Computing, Intl Conf on Pervasive Intelligence and Computing, Intl Conf on Cloud and Big Data Computing, Intl Conf on Cyber Science and Technology Congress (DASC/PiCom/CBDCom/CyberSciTech) - Fukuoka, Japan- Evaluation of Transfer Learning for Human Activity Recognition Among Different Datasets.854–859,2019.
[8] Yang Liu, Peng Sun, Max R. Highsmith, Nickolas M. Wergeles, Joel Sartwell, Andy Raedeke, et.al.,“Third International Conference on Data Science in Cyberspace”, IEEE, Performance Comparison of Deep Learning Techniques for Recognizing Birds in Aerial Images,2018.
[9] Nour Abuared;Alavikunhu Panthakkan, Mina Al-Saad, Saad Ali Amin, Wathiq Mansoor. Skin Cancer Classification Model Based on VGG 19 and Transfer Learning. 2020 3rd International Conference on Signal Processing and Information Security (ICSPIS), 2020.
[10] Nutter, Mark; Crawford, Catherine H.; Ortiz, Jorge, “IEEE 2018 International Joint Conference on Neural Networks (IJCNN) - Rio de Janeiro”, Brazil Design of Novel Deep Learning Models for Real- time Human Activity Recognition with Mobile Phones,1–8,2018.
[11] Miss. Sayali V,Mr.R.G.Mevekar,i "International Research Journal of Engineering and Technology (IRJET)",Developments of Deep Learning for Animal Classification: A Review, 2021,e-ISSN: 2395-0056.
[12] Priya Gupta, Nidhi Saxena, Meetika Sharma, Jagriti Tripathi, “Deep Neural Network for Human Face Recognition”, International Journal of Engineering and Manufacturing,Vol.8, No.1, PP.63-71, 2018.
[13] Ahmad Ilham Gustisyaf, Ardiles Sinaga, “Implementation of Convolutional Neural Network to Classification Gender based on Fingerprint”, International Journal of Modern Education and Computer Science, Vol.13, No.4, PP.55-67, 2021.
[14] Iorga, C., & Neagoe, V.-E.,”11th International Conference on Electronics, Computers and Artificial Intelligence (ECAI)” A Deep CNN Approach with Transfer Learning for Image Recognition, 2019.
[15] Kamal Kant Verma ET.AL., “International Journal of Interactive Multimedia and Artificial Intelligence”, Two-Stage Human Activity Recognition Using 2D-ConvNet, Vol. 6,2.
[16] Yang Xing, Chen Lv, Member, Huaji Wang, Dongpu Cao, “Transaction of Vechicular Technology,” Driver Activity Recognition for Intelligent Vehicles: A Deep Learning Approach, IEEE 2019, Vol.68, Issue 6.
[17] Yang Liu, Peng Sun, Max R. Highsmith, Nickolas M. Wergeles, Joel Sartwell, Andy Raedeke, et.al.,“Third International Conference on Data Science in Cyberspace”, IEEE, Performance Comparison of Deep Learning Techniques for Recognizing Birds in Aerial Images,2018.
[18] Afshar Shamsi, Brij Mohan Singh, H. L. Mandoria, Prachi Chauhan, “IEEE Transactions on Neural Networks and Learning System”, An Uncertainty-Aware Transfer Learning-Based Framework for COVID-19 Diagnosis, Vol.32, NO. 4, April 2021.
[19] S.M. Mohidul Islam, Farhana Tazmim Pinki,“I. J. Engineering and Manufacturing”,Colour, Texture, and Shape Features based Object Recognition Using Distance Measures,PP.42-50,August 2021.
[20] Tu, Xinyuan; Lai, Kenneth; Yanushkevich, Svetlana (2018). "[IEEE 2018 9th International Conference on Software Engineering and Service Science (ICSESS) - Beijing ", China - Transfer Learning on Convolutional Neural Networks for Dog Identification, 357–360,2018.
[21] Md. Rayhan Ahmed, Towhidul Islam Robin, Ashfaq Ali Shafin, “Automatic Environmental Sound Recognition (AESR) Using Convolutional Neural Network”, I.J. Modern Education and Computer Science, 5, 41-54, 2020.
[22] Kamal Kant Verma1 et.al., “International Journal of Interactive Multimedia and Artificial Intelligence”, Two-Stage Human Activity Recognition Using 2D-ConvNet,24 April 2020, 10.9781/ijimai.2020.04.002.
[23] Apri Junaidi et.al., IEEE International Conference on Communication, Networks and Satellite COMNETSAT)", Image Classification for Egg Inclubator using Transfer Learning of VGG16 and VGG19, IEEE, 17-18 July 2021.