Deep learning for small object detection

  1. Bosquet Mera, Brais
Supervised by:
  1. Manuel Mucientes Molina Director
  2. Victor Manuel Brea Sánchez Director

Defence university: Universidade de Santiago de Compostela

Fecha de defensa: 18 December 2020

Committee:
  1. Francisco Herrera Triguero Chair
  2. Senén Barro Secretary
  3. Andrea Prati Committee member
Department:
  1. Department of Electronics and Computing

Type: Thesis

Abstract

Small object detection has become increasingly relevant due to the fact that the performance of common object detectors falls significantly as objects become smaller. Many computer vision applications require the analysis of the entire set of objects in the image, including extremely small objects. Moreover, the detection of small objects allows to perceive objects at a greater distance, thus giving more time to adapt to any situation or unforeseen event.