The detector of variable motion objects in the task of identifying forensically relevant information

In the modern world, digital evidence is taking an increasing role in crime investigations, video recordings from CCTV being one of the most common types of such evidence. For investigative authorities, the information contained in video recordings is of significant, and in some cases of key importance. This paper focuses on describing the development of a detector of moving and motionless objects on video recordings of CCTV systems. An analysis of a wide range of video materials from the subject area is performed based on the overview of scientific publications on object detection in video data, with the main constraints and assumptions formulated with the use of a mathematical model. The existing solutions are compared, given the set constraints and assumptions. A model of object detection is proposed on the basis of the results of the study, with the most preferable solution for the problem of detection with the required accuracy and performance. Use of the detector as one of the stages helps solve the problem of identifying criminally significant information in video data of surveillance systems. The detector can also be used in other computer vision systems for detecting both moving and inactive objects on video recordings.

1. The situation of Crime in the Russian Federation. (In Russ) Available at: https://мвд.рф/reports (accessed: 12.02.2021)

2. Zou Z., Shi Z., Guo Y, Ye J. Object detection in 20 years: A survey. arXiv, 2019.

3. Zivkovic Z. Improved adaptive Gaussian mixture model for background subtraction. Proceedings of the 17th International Conference on Pattern Recognition. 2004;2:28-31.

4. Ko T., Stefano S., Deborah E. Background subtraction on distributions. European Conference on Computer Vision. 2008:276-289.

5. Yu X., Chen X., Jiang M. Motion detection in moving background using a novel algorithm based on image features guiding self-adaptive Sequential Similarity Detection Algorithm. Optik. 2012;123(22):2031-2037.

6. Alandkar L., Gengaje S.R. Dealing Background Issues in Object Detection using GMM: A Survey. International Journal of Computer Applications. 2016;150(5):50-55.

7. Gonzalez R., Woods R. Digital Image Processing. Tekhnosfera; 2012.

8. Forsyth D., Pons J. Computer Vision: A Modern Approach. Vil'yams; 2004.

9. Luk'yanitsa A.A., Shishkin A.G. Digital video processing. ISS Press; 2009. (In Russ)

10. Jahne B. Digital Image Processing. Tekhnosfera; 2007.

11. Patel M.P., Parmar S.K. Moving object detection with moving background using optic flow. International Conference on Recent Advances and Innovations in Engineering. 2014:1-6.

12. Cheurin Ya.E., Mashkin S.V. Comparison of background subtraction methods based on a mixture of Gaussians (mog) and resistant to camera trembling. Physics for the Perm Region. 2019:168-173. (In Russ)

13. Vid.stab – Transcode video stabilization plugin. Available at: http://public. hronopik.de/vid.stab (accessed: 12.02.2021)

14. Krasnyashchikh A.V. Optical image processing. ITMO University; 2012. (In Russ)

15. Sreedhar K., Panlal B. Enhancement of Images Using Morphological Transformations. International Journal of Computer Science and Information Technology. 2012;4(1):33-50.

16. Pritch Y., Rav-Acha A., Peleg S. Nonchronological Video Synopsis and Indexing. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2008;30(11):1971-1984.