Por favor, use este identificador para citar o enlazar este ítem: http://repositorio.udec.cl/jspui/handle/11594/10226
T√≠tulo : Dual reconstructive autoencoder for crowd localization and estimation in density and FIDT maps.
Autor : Godoy Medel, Sebasti√°n, supervisor de grado
Lamas Silva, Felipe Ignacio
Palabras clave : Teor√≠a de la Estimaci√≥n;Aprendizaje de M√°quina;Computadores Neurales;Redes Sensoriales Inal√°mbricas
Fecha de publicaci√≥n : 2022
Editorial : Universidad de Concepci√≥n, Facultad de Ingenier√≠a, Departamento de Ingenier√≠a El√©ctrica.
Resumen : This research proposes a novel crowd estimation technology to help authorities to make the right decisions in times of crisis. Specifically, deep learning models have faced these challenges, achieving excellent results. In particular, the trend of using single-column Fully Convolutional Networks (FCNs) has increased in recent years. A typical architecture that meets these charac teristics is the autoencoder. However, this model presents an intrinsic difficulty: the search for the optimal dimensionality of the latent space. In order to alleviate such difficulty, we propose a dual architecture consisting of two cascaded autoencoders. The first autoencoder is responsible for carrying out the masked reconstruction of the original images, whereas the second obtains crowd maps from the outputs of the first one. Our architecture improves the location of people and crowds on Focal Inverse Distance Transform (FIDT) maps, resulting in more accurate count estimates than estimates obtained through a single autoencoder architecture. Specifically, to evaluate the model in the location task we used two decision thresholds (ūĚúé = 4 and ūĚúé = 8), obtaining, respectively, that our model increased the Precision by 36 (from 27.11% to 63.11%) and 46.8 (from 37.26% to 84.06%) percentage points, the Recall metric by 3.05 (from 54.56% to 57.61%) and 1.75 (from 74.98% to 76.73%) percentage points, and F1-Score by 24.02 (from 36.22% to 60.24%) and 30.45 (from 49.78% to 80.23%) percentage points. For the counting task, the Dual Reconstructive Autoencoder (DRA) model decreased MAE and RMSE by 88.5% and 75.18%, respectively, compared to the metrics obtained for the Single Autoencoder (SA) model (SA model MAE: 121.73, DRA model MAE: 13.92, SA model RMSE: 127.61, DRA model RMSE: 31.67).
Descripci√≥n : Thesis to qualify for the degree of Master of Science in Electrical Engineering.
URI : http://repositorio.udec.cl/jspui/handle/11594/10226
Aparece en las colecciones: Ingeniería Eléctrica - Tesis Magister

Ficheros en este ítem:
Fichero Descripci√≥n Tama√Īo Formato  
Tesis Felipe Lamas.pdf1,7 MBAdobe PDFVista previa

Este ítem está sujeto a una licencia Creative Commons Licencia Creative Commons Creative Commons