Abstract
Crime scene investigation is an important and challenging work for detecting suspects from the incident. Investigations begin from collecting various objects, markings, location, and scalability of the incident. Evaluation of artificial intelligence helped a lot in creating automated investigation models. To detect the crime scene objects, markings impact a lot in making decisions. Investigation scenario is highly sensitive; hence, detection of crime scene objects as early as possible is important. The proposed approach considers crime scene videos collected from CCTV cameras as prime input. Video-to-image conversion is implemented initially. Visual HOG histogram of orientation gradient feature (VHOG) is extracted from the image. Based on the feature, the background subtraction is done. The semantic object is extracted from the image through morphology factor as well as HOG feature matching. The correlated semantic object shades are compared with the training images. Deep resilient net (DRN) is created to make training and testing processes. Various images of the objects are separately trained using the neural network. Using the hidden layers of neural perceptrons, the similar blob of the object is continuously compared with all the salient objects in the database images. Based on the correlated score, the confusion matrix is formulated. The calculation of true positive, true negative, false positive, and false negative rate is evaluated. The novel structure is validated with repeated iterations of comparisons and further the achieved the accuracy of 91%. Reduction of false similarity issues is considered here to avoid occluded images, and rejection of false image is adopted steps here.
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
Farhood H, Saberi M, Najafi M (2021) Improving object recognition in crime scenes via local interpretable model-agnostic explanations. In: 2021 IEEE 25th international enterprise distributed object computing workshop (EDOCW), 2021, pp 90–94. https://doi.org/10.1109/EDOCW52865.2021.00037
Proceedings of the 2019 Federated conference on computer science and information systems, Ganzha M, Maciaszek L, Paprzycki M (eds). ACSIS, vol 18, pp 391–396 (2019)
Sun H, Meng Z, Tao PY, Ang MH (2018) Scene recognition and object detection in a unified convolutional neural network on a mobile manipulator. In: 2018 IEEE International conference on robotics and automation (ICRA), 2018, pp 5875–5881. https://doi.org/10.1109/ICRA.2018.8460535
Saikia S, Fidalgo E, Alegre E, Fernández-Robles L (2017) Object detection for crime scene evidence analysis using deep learning. Image Anal Process—ICIAP 2017:14–24
Espinace P, Kollar T, Soto A, Roy N (2010) Indoor scene recognition through object detection. In: 2010 IEEE international conference on robotics and automation, 2010, pp 1406–1413. https://doi.org/10.1109/ROBOT.2010.5509682
Masuda S, Kaeri Y, Manabe Y, Kenji S (2018) Scene recognition method by bag of objects based on object detector. In: 2018 Joint 10th international conference on soft computing and intelligent systems (SCIS) and 19th international symposium on advanced intelligent systems (ISIS), 2018, pp 321–324. https://doi.org/10.1109/SCIS-ISIS.2018.00062
Tankard C (2011) Advanced persistent threats and how to monitor and deter them. Netw Secur 2011(8):16–19
Baber C, Smith P, Cross J, Zasikowski D, Hunter J (2005) Wearable technology for Crime Scene Investigation. Proceedings – International Symposium on Wearable Computers (ISWC), 2005, pp 138–141. https://doi.org/10.1109/ISWC.2005.58
Araújo P, Fontinele J, Oliveira L (2020) Multi-perspective object detection for remote criminal analysis using drones. IEEE Geosci Remote Sens Lett 17(7):1283–1286. https://doi.org/10.1109/LGRS.2019.2940546
Nakib M, Khan RT, Hasan MS, Uddin J (2018) Crime scene prediction by detecting threatening objects using convolutional neural network. In: 2018 International conference on computer, communication, chemical, material and electronic engineering (IC4ME2), 2018, pp 1–4. https://doi.org/10.1109/IC4ME2.2018.8465583
Gur A, Erim M, Karakose M (2020) Image processing based approach for crime scene investigation using drone. pp 1–6. https://doi.org/10.1109/ICDABI51230.2020.9325606
Sani S (2022) Object detection for crime scene evidence analysis. 2022 J Softw Eng Simul 8(7):44–53, ISSN(Online):2321-3795 ISSN(Print):2321-3809
Aarthi S, Chitrakala S (2017) Scene understanding—a survey. In: 2017 International conference on computer, communication and signal processing (ICCCSP), 2017, pp 1–4. https://doi.org/10.1109/ICCCSP.2017.7944094
Liu W, Wu CY (2019) Crime scene investigation image retrieval using a hierarchical approach and rank fusion. In 2019 14th IEEE Conference on Industrial Electronics and Applications (ICIEA), pp. 1974–1978. IEEE
Tasci T, Kim K (2015) Imagenet classification with deep convolutional neural networks
Liu Y, Hu D, Fan J, Wang F, Zhang D (2017) Multi-feature fusion for crime scene investigation image retrieval. In 2017 International Conference on Digital Image Computing: Techniques and Applications (DICTA), pp. 1–7). IEEE
Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. In: International conference on learning representations, 2014
Chen Y-R et al (2021) Forensic science education by crime scene investigation in virtual reality. In: 2021 IEEE international conference on artificial intelligence and virtual reality (AIVR), 2021, pp 205–206. https://doi.org/10.1109/AIVR52153.2021.00046
Mahesha P, Royina KJ, Lal S, Anoop Krishna Y, Thrupthi MP (2021) Crime scene analysis using deep learning. In: 2021 6th International conference on signal processing, computing and control (ISPCC), 2021, pp 760–764. https://doi.org/10.1109/ISPCC53510.2021.9609350
Petty M, Teng SW, Murshed M (2019) Improved image analysis methodology for detecting changes in evidence positioning at crime scenes. In: 2019 Digital image computing: techniques and applications (DICTA), 2019, pp 1–8. https://doi.org/10.1109/DICTA47822.2019.8945934
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Nandhini, T.J., Thinakaran, K. (2023). Visual HOG-Enabled Deep ResiNet for Crime Scene Object Detection. In: Yadav, A., Nanda, S.J., Lim, MH. (eds) Proceedings of International Conference on Paradigms of Communication, Computing and Data Analytics. PCCDA 2023. Algorithms for Intelligent Systems. Springer, Singapore. https://doi.org/10.1007/978-981-99-4626-6_19
Download citation
DOI: https://doi.org/10.1007/978-981-99-4626-6_19
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-4625-9
Online ISBN: 978-981-99-4626-6
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)