RT Journal Article
T1 Small-Scale Urban Object Anomaly Detection Using Convolutional Neural Networks with Probability Estimation.
A1 García Aguilar, Iván
A1 Luque-Baena, Rafael Marcos
A1 Domínguez-Merino, Enrique
A1 López-Rubio, Ezequiel
K1 Redes neuronales (Informática)
AB Anomaly detection in sequences is a complex problem in security and surveillance. With theexponential growth of surveillance cameras in urban roads, automating them to analyze the data andautomatically identify anomalous events efficiently is essential. This paper presents a methodologyto detect anomalous events in urban sequences using pre-trained convolutional neural networks(CNN) and super-resolution (SR) models. The proposal is composed of two parts. In the offline stage,the pre-trained CNN model evaluated a large dataset of urban sequences to detect and establish thecommon locations of the elements of interest. Analyzing the offline sequences, a density matrix iscalculated to learn the spatial patterns and identify the most frequent locations of these elements.Based on probabilities previously calculated from the offline analysis, the pre-trained CNN, nowin an online stage, assesses the probability of anomalies appearing in the real-time sequence usingthe density matrix. Experimental results demonstrate the effectiveness of the presented approachin detecting several anomalies, such as unusual pedestrian routes. This research contributes tourban surveillance by providing a practical and reliable method to improve public safety in urbanenvironments. The proposed methodology can assist city management authorities in proactivelydetecting anomalies, thus enabling timely reaction and improving urban safety.
PB MDPI
YR 2023
FD 2023-08-15
LK https://hdl.handle.net/10630/31387
UL https://hdl.handle.net/10630/31387
LA eng
NO García-Aguilar, I., Luque-Baena, R. M., Domínguez, E., & López-Rubio, E. (2023). Small-Scale Urban Object Anomaly Detection Using Convolutional Neural Networks with Probability Estimation. Sensors, 23(16), 7185. https://doi.org/10.3390/s23167185
NO Partial funding for open access charge: Universidad de Málaga.
DS RIUMA. Repositorio Institucional de la Universidad de Málaga
RD 19 ene 2026