TY - GEN
T1 - Detecting Violent Robberies in CCTV Videos Using Deep Learning
AU - Morales, Giorgio
AU - Salazar-Reque, Itamar
AU - Telles, Joel
AU - Díaz, Daniel
N1 - Publisher Copyright:
© 2019, IFIP International Federation for Information Processing.
PY - 2019
Y1 - 2019
N2 - 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%.
AB - 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%.
KW - Action recognition
KW - Robbery detection
KW - convLSTM
UR - http://www.scopus.com/inward/record.url?scp=85065913796&partnerID=8YFLogxK
U2 - 10.1007/978-3-030-19823-7_23
DO - 10.1007/978-3-030-19823-7_23
M3 - Conference contribution
AN - SCOPUS:85065913796
SN - 9783030198220
T3 - IFIP Advances in Information and Communication Technology
SP - 282
EP - 291
BT - Artificial Intelligence Applications and Innovations - 15th IFIP WG 12.5 International Conference, AIAI 2019, Proceedings
A2 - Pimenidis, Elias
A2 - Maglogiannis, Ilias
A2 - Iliadis, Lazaros
A2 - MacIntyre, John
PB - Springer New York LLC
T2 - 15th IFIP WG 12.5 International Conference on Artificial Intelligence Applications and Innovations, AIAI 2019
Y2 - 24 May 2019 through 26 May 2019
ER -
