Skip to Main content Skip to Navigation
Conference papers

Detecting Violent Robberies in CCTV Videos Using Deep Learning

Abstract : Video surveillance through security cameras has become difficult due to the fact that many systems require manual human inspection for identifying violent or suspicious scenarios, which is practically inefficient. Therefore, the contribution of this paper is twofold: the presentation of a video dataset called UNI-Crime, and the proposal of a violent robbery detection method in CCTV videos using a deep-learning sequence model. Each of the 30 frames of our videos passes through a pre-trained VGG-16 feature extractor; then, all the sequence of features is processed by two convolutional long-short term memory (convLSTM) layers; finally, the last hidden state passes through a series of fully-connected layers in order to obtain a single classification result. The method is able to detect a variety of violent robberies (i.e., armed robberies involving firearms or knives, or robberies showing different level of aggressiveness) with an accuracy of 96.69%.
Document type :
Conference papers
Complete list of metadata

Cited literature [34 references]  Display  Hide  Download

https://hal.inria.fr/hal-02331311
Contributor : Hal Ifip <>
Submitted on : Thursday, October 24, 2019 - 12:50:38 PM
Last modification on : Thursday, October 24, 2019 - 12:54:42 PM
Long-term archiving on: : Saturday, January 25, 2020 - 2:51:20 PM

File

 Restricted access
To satisfy the distribution rights of the publisher, the document is embargoed until : 2022-01-01

Please log in to resquest access to the document

Licence


Distributed under a Creative Commons Attribution 4.0 International License

Identifiers

Citation

Giorgio Morales, Itamar Salazar-Reque, Joel Telles, Daniel Díaz. Detecting Violent Robberies in CCTV Videos Using Deep Learning. 15th IFIP International Conference on Artificial Intelligence Applications and Innovations (AIAI), May 2019, Hersonissos, Greece. pp.282-291, ⟨10.1007/978-3-030-19823-7_23⟩. ⟨hal-02331311⟩

Share

Metrics

Record views

502