Repositório Digital

A- A A+

Faster than the fastest : using calibrated cameras to improve the fastest pedestrian detector in the west

.

Faster than the fastest : using calibrated cameras to improve the fastest pedestrian detector in the west

Mostrar registro completo

Estatísticas

Título Faster than the fastest : using calibrated cameras to improve the fastest pedestrian detector in the west
Autor Arnoud, Charles Daniel Ribeiro
Orientador Jung, Claudio Rosito
Data 2015
Nível Graduação
Instituição Universidade Federal do Rio Grande do Sul. Instituto de Informática. Curso de Ciência da Computação: Ênfase em Ciência da Computação: Bacharelado.
Assunto Computação gráfica
Visualização
[en] Computer vision
[en] Pedestrian detection
Abstract In this thesis, we translated a state-of-the-art object detector (the Dóllar method) to the C++ programming language and explored ways to use camera calibration to improve its performance by reducing the amount of calculations necessary and to improve the results by taking away false positives. We developed these techniques in the context of pedestrian detection. On data sets more aligned with video surveillance applications (the camera is high in relation to the ground and far from the area where objects are expected to be), we had great results across the board: the amount of scales in the feature pyramid is reduced by about half, the amount of times the classifier is applied is greatly reduced together with the number of false detections, all while keeping the loss in detection coverage manageable. We also tested our detector in one data set that closely resembles the use of detection in robotics or self-driving systems for automobiles (camera closer to the ground plane and parallel to it). The results suggest the method needs adjustments to be applied to this type of setting. Although there was no loss in detection quality and both the number of scales in the feature pyramid and the number of false positives were reduced, the amount of classifier applications seems excessive. To avoid this problem, we need to adjust the Dense Detection phase of our method (subsection 3.2.2) to account for the fact that images created by these camera settings have a bigger range of possible pedestrian heights and more portions of the image are plausible to provide detections.
Tipo Trabalho de conclusão de graduação
URI http://hdl.handle.net/10183/126065
Arquivos Descrição Formato
000972318.pdf (7.113Mb) Texto completo Adobe PDF Visualizar/abrir

Este item está licenciado na Creative Commons License

Este item aparece na(s) seguinte(s) coleção(ões)


Mostrar registro completo

Percorrer



  • O autor é titular dos direitos autorais dos documentos disponíveis neste repositório e é vedada, nos termos da lei, a comercialização de qualquer espécie sem sua autorização prévia.
    Projeto gráfico elaborado pelo Caixola - Clube de Criação Fabico/UFRGS Powered by DSpace software, Version 1.8.1.