• Shivam Jangid
• Aditya Jagtap
• Mayank Digamber Amte
• Piyusha Kamthe

This System strives for the detection of real-world anomalies such as burglaries and assaults in surveillance videos. Although anomalies are generally local, as they happen in a limited portion of the frame, none of the previous works on the subject has ever studied the contribution of locality. Identification is the act of identifying a person. It means determination of individuality of a person. Concerning about different city, the department of Police is the major organization of preventing crimes. Police stations utilize paper-based information storing systems and they don’t employ computer based applications up to a great extent. Due to this utilization of paper-based systems police officers have to spend a lot of time as well as man power to analyse existing criminal crime information and to identify suspects for crime incidents. So the requirement of an efficient way for criminal identification as well as crime investigation has arisen. Image processing with the help of machine learning practices is one aspect of criminal identification. In this work, we explore the impact of considering spatio-temporal tubes instead of whole-frame video segments. For this purpose, we enrich existing surveillance videos with spatial and temporal annotations: it is thefirst dataset for criminal identification and crime scene detection with bounding box supervision in both its train and test set. Our experiments show that a network trained with spatio-temporal tubes performs better than its analogous model trained with whole-frame videos. In addition, we discover that the locality is robust to different kinds of errors in the extraction phase at test time. Finally, we demonstrate that our network can provide spatio-temporal proposals for unseen surveillance videos leveraging only video-level labels. By doing, we enlarge our spatio-temporal crime scene dataset without the need for further human labelling.

K-Nearest Neighbor Support, Vector Machine Autoregressive moving average, recurrent neural network, Recursive Feature Elimination, National Crime Records Bureau

"Crime prediction using Machine Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 5, page no.c831-c840, May-2022, Available :http://www.jetir.org/papers/JETIR2205409.pdf

"Crime prediction using Machine Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 5, page no. ppc831-c840, May-2022, Available at : http://www.jetir.org/papers/JETIR2205409.pdf