ODSAC: An Innovative Approach for Detection of Suspicious Human Activity and Crime Prediction
Keywords:
Machine Learning, Suspicious Activity, Classifier, Object Detection, Neural NetworkAbstract
The escalating crime rate has spurred a surge of research into real-time object detection for video surveillance. An automatic video detection system is required since it is challenging to continuously watch camera footage taken in public areas in order to identify any unusual activity. Real-time systems find it challenging to identify suspicious or small moving objects against a blurry background. In order to identify suspicious human activity in real-time video, this research introduces a novel algorithm dubbed ODSAC (Object Detection And Suspicious Activity Classification). Darknet53 is used by the system as an object-detecting tool. We have designed a custom classifier that accurately distinguishes whether activity is suspicious or not. The classifier is trained on a self-created dataset to ensure robust performance across various environmental conditions and scenarios. Extensive experimentation on the self-created dataset validates the effectiveness of the proposed approach. The evaluation metrics, including precision, recall, and F1 score, showcase the system's high accuracy in detecting individuals with weapons. The achieved detection accuracy of 99.31% underscores the reliability and efficiency of the architecture with the custom classifier. We have also done a comparative analysis with some existing Methods studied during the literature study. This research paper will be useful for applications such as Criminal Justice to identify suspicious criminal behaviors, Healthcare, Law Enforcement, etc. Integrating this technology with the current monitoring infrastructure might have a significant impact, especially in important locations like airports, schools, and public areas.
Downloads
References
F. Enrique, L.M. Soria, J.A. Álvarez-García, et al., Vision and crowdsensing technology for an optimal response in physical-security, Int. Conf. on Computational Science, Springer, 2019, pp. 15–26.
T. Ainsworth, Buyer beware, Security Oz 19 (2002) 18–26.
S.A. Velastin, et al., A motion-based image processing system for detecting potentially dangerous situations in underground railway stations, Transp. Res. Part C: Emerging Tech. 14 (2) (2006) 96–113.
Everytown for Gun Safety, Gunfire on School Grounds in the United States, 2020.
R.A. Tessler, S.J. Mooney, C.E. Witt, et al., Use of firearms in terrorist attacks: differences between the USA, Canada, Europe, Australia, and New Zealand, JAMA Intern. Med. 177 (12) (2017) 1865–1868.
G. Flitton, T.P. Breckon, N. Megherbi, A comparison of 3D interest point descriptors with application to airport baggage object detection in complex CT imagery, Pattern Recognition, 46 (9) (2013) 2420–2436.
R.K. Tiwari, G.K. Verma, A computer vision based framework for visual gun detection using Harris interest point detector, Procedia Computer. Sci. 54 (2015) 703–712.
F. Gelana, A. Yadav, Firearm Detection from Surveillance Cameras Using Image Processing and Machine Learning Techniques, in: Smart Innovations in Communication & Computation. Sci., Springer, 2019, pp. 25–34.
Joseph Redmon, Ali Farhadi, ‘YOLOv3: An Incremental Improvement University of Washington’, Computer Vision and Pattern Recognition, Published in arXiv.org 8 April 2018.
S. Ren, K. He, R. Girshick, J. Sun, Faster R-CNN: towards real-time object detection with region proposal networks, Adv. Neural. Inf. Process System. 28 (2015).R. Olmos, S. Tabik, F. Herrera, Automatic handgun detection alarm in videos using deep learning, Neurocomputing 275 (2018) 66–72.J. Redmon, A. Farhadi, Yolov3: an incremental improvement, Available online: arXiv preprint arXiv:1804.02767 (2018).
T.-Y. Lin, P. Goyal, R. Girshick, et al., Focal loss for dense object detection, in: Proc. of the IEEE Int. CVPR, 2017, pp. 2980–2988.
W. Liu, D. Anguelov, D. Erhan, et al., SSD: Single shot multibox detector, in: ECCV, Springer, 2016, pp. 21–37.
Warsi, M. Abdullah, M.N. Husen, et al., Gun detection system using yolov3, in: 2019 ICSIMA, IEEE, 2019, pp. 1–4.
R.F. de Azevedo Kanehisa, A. de Almeida, Firearm detection using Convolutional neural networks, in: ICAART (2), 2019, pp. 707–714.
J.L. Salazar Gonzalez, other, Real-time gun detection in CCTV: an open problem, Neural Networks 132 (2020) 297–308.
Adwait A. Borwankar, Ajay S. Ladkat, Manisha R. Mhetre. Thermal Transducers Analysis. National Conference on, Modeling, Optimization and Control, 4th – 6th March 2015, NCMOC – 2015.
Ajay S. Ladkat, Sunil L. Bangare, Vishal Jagota, Sumaya Sanober, Shehab Mohamed Beram, Kantilal Rane, Bhupesh Kumar Singh, "Deep Neural Network-Based Novel Mathematical Model for 3D Brain Tumor Segmentation", Computational Intelligence and Neuroscience, vol. 2022, Article ID 4271711, 8 pages, 2022.
M. Shobana, V. R. Balasraswathi, R. Radhika, Ahmed Kareem Oleiwi, Sushovan Chaudhury, et al, "Classification and Detection of Mesothelioma Cancer Using Feature Selection-Enabled Machine Learning Technique'', BioMed Research International, vol. 2022, Article ID 9900668, 6 pages, 2022.
J. Salido, V. Lomas, J. Ruiz-Santaquiteria, O. Deniz, Automatic handgun detection with deep learning in video surveillance images, Appl. Sci. 11 (13), 2021.
A. Velasco-Mata, J. Ruiz-Santaquiteria, N. Vallez, O. Deniz, Using human pose information for handgun detection, Neural Comput. Appl. 33 (2021) 17273–17286.
J. Ruiz-Santaquiteria, et al., Handgun detection using combined human pose and weapon appearance, IEEE Access 9 (2021) 123815–123826.
A. S. Ladkat, S. S. Patankar, and J. V. Kulkarni, "Modified matched filter kernel for classification of hard exudate," 2016 International Conference on Inventive Computation Technologies (ICICT), Coimbatore, India, 2016, pp. 1-6, Doi: 10.1109/INVENTIVE.2016.7830123.
Gao Huang, Zhuang Liu, Laurens van der Maaten, ‘Densely Connected Convolutional Networks’, Computer Vision and Pattern Recognition, IEEE, 2017.
Ms. Ashwini M. Bhugul, Dr. Vijay S. Gulhane, “Real Time Video Activity Detection Techniques in Machine Learning”, IOSR Journal of Computer Engineering (IOSR-JCE) e-ISSN: 2278-0661, p-ISSN: 2278-8727, Volume 23, Issue 6, Ser. I, PP 40-44, December 2021.
Ms. A. M. Bhugul, Dr. V. S. Gulhane, "Novel Deep Neural Network for Suspicious Activity Detection and Classification”, IEEE International Students' Conference on Electrical, Electronics and Computer Science (SCEECS), February 2023.
Ms. A. M. Bhugul, Dr. V. S. Gulhane, “Detection of Suspicious Human Activities and Prediction of Crime Using Machine Learning Approach”, International Research Journal of Science Engineering And Technology, Vol - 10, Issue- 4, Page(s): 83 - 88 (2020).
Yudhvir Rana, Title of subordinate document. In: Armed robbers loot Rs 22 lakh from Punjab National Bank bran, 2023)
Sounak Mukhopadhyay, Title of subordinate document. In: “Mass shooting: 6 people shot dead in Mississippi, the US state with the weakest gun laws”, Feb 2023.
The Takeaways, Title of subordinate document. In: “Gun Violence in 2023: Nearly 40 Mass Shootings in 26 Days”, 2023.
Amrutha C. and Jyotsna, Amudha J, ‘Deep Learning Approach for Suspicious Activity Detection from Surveillance Video’, Proceedings of the Second International Conference on Innovative Mechanisms for Industry Applications (ICIMIA 2020), IEEE Xplore Part Number: CFP20K58-ART; ISBN: 978-1- 7281-4167-1.
Neelam Dwivedi, Dushyant Kumar, Dharmender Singh Kushwaha, “Weapon Classification using Deep Convolutional Neural Network “, IEEE Conference on Information and Communication Technology (CICT) , IEEE , 2019,
Harsh Jain; Aditya Vikram; Mohana; Ankit Kashyap; Ayush Jain, “Weapon Detection Using AI and Deep Learning for security Applications”, IEEE Xplore, International conference on electronics and sustainable communication system, 2020, https://doi.org/10.1109/ICESC48915.2020.9155832
Nuha H. Abdulghafoor, Hadeel N. Abdullah,’ A novel real-time multiple objects detection and tracking framework for different challenges’, Alexandria Engineering Journal, Volume 61, Issue 12, Pages 9637-9647, 2022.
Sarita Chaudhary, Mohd Aamir Khan, Charul Bhatnagar, “Multiple Anomalous Activity Detection in Videos “, 6th International Conference on Smart Computing and Communications, ICSCC 2017, Procedia Computer Science 125 (2018) 336–345,2018.
M. Baranitharan, R. Nagarajan, G. ChandraPraba ,’Automatic Human Detection in Surveillance Camera to Avoid Theft Activities in ATM Centre using Artificial Intelligence’, International Journal of Engineering Research & Technology (IJERT) ISSN: 2278-0181.
Rajesh Kumar Tripathi1, Anand Singh Jalal1, Subhash Chand Agrawal, ‘Suspicious human activity recognition: a review’, February 2017, Artificial Intelligence Review 50(3), DOI: 10.1007/s10462-017-9545.
Hitesh Kumar Reddy, Toppi Reddya , Bhavna Sainia, Ginika Mahajan, 'Crime Prediction & Monitoring Framework Based on Spatial Analysis', Elsevier, Procedia Computer Science, Volume 132, 2018, Pages 696-705.
Heba M. Ismail, Saad Harous, Boumediene Belkhouche, ‘A Comparative Analysis of Machine Learning Classifiers for Twitter Sentiment Analysis’, IConference: 17th International Conference on Intelligent Text Processing and Computational Linguistics - CICLing, 2016.
Laxmi Shanker Maurya, Md Shadab Hussain & Sarita Singh, ‘Developing Classifiers through Machine Learning Algorithms for Student Placement Prediction Based on Academic Performance’, Applied Artificial Intelligence, Taylor and francis, Pages 403-420 , Mar 2021.
Sanjeev Tannirkulam Chandrasekaran; Akshay Jayaraj; Vinay Elkoori Ghantala Karnam; Imon Banerjee; Arindam Sanyal, ‘Fully Integrated Analog Machine Learning Classifier Using Custom Activation Function for Low Resolution Image Classification’, IEEE Transactions on Circuits and Systems I: Regular Papers , Volume: 68, Issue: 3, March 2021.
Savitha Acharya, Vaishnavi M. , Sujith Kumar , Shahid Raza, Halesh R, ‘Smart Surveillance Robot for Weapon Detection’, International Journal for Research in Applied Science & Engineering Technology (IJRASET), ISSN: 2321-9653, IC Value: 45.98; Impact Factor: 7.177, Volume 7 Issue V, May 2019.
Gaurav Raturi, Priya Rani, Sanjay Madan, Sonia Dosanjh , ‘ADoCW: An Automated method for Detection of Concealed Weapon’, 2019 Fifth International Conference on Image Information Processing (ICIIP), Shimla, India, Accession Number: 19342607, IEEE, 2019.
Ramzan, M., Abid, A., Khan, H. U., Awan, S. M., Ismail, A., Ahmed, M., Mahmood, A. ‘A Review on state-of-the-art Violence Detection Techniques’, IEEE Access, 1–1, doi:10.1109/access.2019.2932114, 2019.
Baser M, Mittal M, Samiya D. ‘Real Time Foreground Segmentation for Video Sequences with Dynamic Background’, IEEE 17th India Council International Conference (INDICON), 2020.
Khawaja MoyeezUllah Ghori, Muhammad Imran, Asad Nawaz, Rabeeh Ayaz Abbasi, Ata Ullah & Laszlo Szathmary, ‘Performance analysis of machine learning classifiers for non-technical loss detection’, Journal of Ambient Intelligence and Humanized Computing, Springer Link, DOI: 10.1109/CSNT.2017.8418550 , 2020.
Nandini. G, Dr. B. Mathivanan, Nantha Bala. R. S, Poornima. P, ‘Suspicious human activity detection’, International Journal of Advance Research and Development, 2018, Volume 3, Issue 4.
R. Mahajan and D. Padha, ‘Detection of concealed weapons using image processing techniques: A review’, First International Conference on Secure Cyber Computing and Communication (ICSCCC), Dec 2018, pp. 375–378.
Bhagya Divya, S. Shalini, R .Deepa, Baddeli Sravya Reddy, ‘Inspection of Suspicious Human Activity In The Crowdsourced Areas Captured In Surveillance Cameras’, International Research Journal of Engineering and Technology(IRJET), e-ISSN: 2395-0056, Volume: 04, Issue: 12 , Dec-2017.]
S. Gupta, 'Introducing Custom Classifier — Build Your Own Text Classification Model without Any Training Data'.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
