Compression of sensor data in robotic systems
Autor(a) principal: | |
---|---|
Data de Publicação: | 2018 |
Tipo de documento: | Dissertação |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/10773/25969 |
Resumo: | One of the main problems in the development and debugging of robotic systems is the amount of data stored in files containing sensor data (ex. ROS proprietary log files - BAGS). If we consider a robot with several cameras and other sensors that collect information from the environment several times per second, we quickly obtain very large files. Besides the concerns regarding storage and, in some cases, transmission, it becomes extremely hard to find important information in these files. In this thesis, we tried to solve both problems studying and implementing data compression solutions to reduce the referred files. The main focus was image and video compression, by far the most storage consuming data. Moreover, we conducted a detailed study about the effect of lossy compression methods in the performance of some state of the art image analysis algorithms. Another contribution was the development of an intelligent video player to help roboticists in their work while they evaluate the recorded data after experiments. Parts of the video that do not contain relevant information are skipped during the play. Based on the results, we concluded that ROS native compression is not sufficient. Furthermore, solutions based on ROS, or virtually any robotic system that has to deal with image/video data, would benefit with the use of a H.265 codec, as it provides the smallest number of bits per pixel without a significant penalty on the performance of image analysis algorithms. |
id |
RCAP_7683a466ea841d668f4fbbd8db28bd3a |
---|---|
oai_identifier_str |
oai:ria.ua.pt:10773/25969 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Compression of sensor data in robotic systemsROSRoboticsComputer VisionData CompressionOne of the main problems in the development and debugging of robotic systems is the amount of data stored in files containing sensor data (ex. ROS proprietary log files - BAGS). If we consider a robot with several cameras and other sensors that collect information from the environment several times per second, we quickly obtain very large files. Besides the concerns regarding storage and, in some cases, transmission, it becomes extremely hard to find important information in these files. In this thesis, we tried to solve both problems studying and implementing data compression solutions to reduce the referred files. The main focus was image and video compression, by far the most storage consuming data. Moreover, we conducted a detailed study about the effect of lossy compression methods in the performance of some state of the art image analysis algorithms. Another contribution was the development of an intelligent video player to help roboticists in their work while they evaluate the recorded data after experiments. Parts of the video that do not contain relevant information are skipped during the play. Based on the results, we concluded that ROS native compression is not sufficient. Furthermore, solutions based on ROS, or virtually any robotic system that has to deal with image/video data, would benefit with the use of a H.265 codec, as it provides the smallest number of bits per pixel without a significant penalty on the performance of image analysis algorithms.Um dos principais problemas no desenvolvimento e depuração de sistemas robóticos é a quantidade de dados armazenados em ficheiros contendo dados sensoriais (ex. ficheiros de log proprietários de ROS - Bags). Se considerarmos um robô com várias câmaras e outros sensores, que recolhem informação do ambiente diversas vezes por segundo, obtemos rapidamente ficheiros muito grandes. Além das preocupações com o armazenamento e, em alguns casos, a transmissão, torna-se extremamente difícil encontrar informações importantes nesses ficheiros. Nesta dissertação, procuramos a melhor solução para os dois problemas estudando e implementando soluções de compressão de dados para reduzir os ficheiros referidos. O foco principal foi compressão de imagem/video, de longe, os dados que consomem mais armazenamento. Além disso, realizamos um estudo detalhado sobre o efeito de compressão com perdas no desempenho de alguns algoritmos de análise de imagem estado da arte. Outra contribuição foi o desenvolvimento de um leitor de vídeo inteligente para ajudar os roboticistas no seu trabalho enquanto avaliam os dados gravados. Partes do vídeo que não contêm informações relevantes são aceleradas durante a leitura. Com base nos resultados, concluímos que a compressão nativa de ROS não é suficiente. Além disso, soluções baseadas em ROS, ou de um modo geral qualquer sistema robótico que precise de lidar com dados de imagem/vídeo, beneficiaria com o uso de um codec H.265, uma vez que fornece o menor número de bits por pixel sem penalização significativa da eficiência dos algoritmos de análise de imagem.2019-05-08T13:53:43Z2018-01-01T00:00:00Z2018info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfhttp://hdl.handle.net/10773/25969TID:202233871engMartins, Álvaro Rodrigues de Castro Mendesinfo:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2024-02-22T11:50:20Zoai:ria.ua.pt:10773/25969Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-20T02:59:06.137622Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse |
dc.title.none.fl_str_mv |
Compression of sensor data in robotic systems |
title |
Compression of sensor data in robotic systems |
spellingShingle |
Compression of sensor data in robotic systems Martins, Álvaro Rodrigues de Castro Mendes ROS Robotics Computer Vision Data Compression |
title_short |
Compression of sensor data in robotic systems |
title_full |
Compression of sensor data in robotic systems |
title_fullStr |
Compression of sensor data in robotic systems |
title_full_unstemmed |
Compression of sensor data in robotic systems |
title_sort |
Compression of sensor data in robotic systems |
author |
Martins, Álvaro Rodrigues de Castro Mendes |
author_facet |
Martins, Álvaro Rodrigues de Castro Mendes |
author_role |
author |
dc.contributor.author.fl_str_mv |
Martins, Álvaro Rodrigues de Castro Mendes |
dc.subject.por.fl_str_mv |
ROS Robotics Computer Vision Data Compression |
topic |
ROS Robotics Computer Vision Data Compression |
description |
One of the main problems in the development and debugging of robotic systems is the amount of data stored in files containing sensor data (ex. ROS proprietary log files - BAGS). If we consider a robot with several cameras and other sensors that collect information from the environment several times per second, we quickly obtain very large files. Besides the concerns regarding storage and, in some cases, transmission, it becomes extremely hard to find important information in these files. In this thesis, we tried to solve both problems studying and implementing data compression solutions to reduce the referred files. The main focus was image and video compression, by far the most storage consuming data. Moreover, we conducted a detailed study about the effect of lossy compression methods in the performance of some state of the art image analysis algorithms. Another contribution was the development of an intelligent video player to help roboticists in their work while they evaluate the recorded data after experiments. Parts of the video that do not contain relevant information are skipped during the play. Based on the results, we concluded that ROS native compression is not sufficient. Furthermore, solutions based on ROS, or virtually any robotic system that has to deal with image/video data, would benefit with the use of a H.265 codec, as it provides the smallest number of bits per pixel without a significant penalty on the performance of image analysis algorithms. |
publishDate |
2018 |
dc.date.none.fl_str_mv |
2018-01-01T00:00:00Z 2018 2019-05-08T13:53:43Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/masterThesis |
format |
masterThesis |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://hdl.handle.net/10773/25969 TID:202233871 |
url |
http://hdl.handle.net/10773/25969 |
identifier_str_mv |
TID:202233871 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.source.none.fl_str_mv |
reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação instacron:RCAAP |
instname_str |
Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
instacron_str |
RCAAP |
institution |
RCAAP |
reponame_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
collection |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository.name.fl_str_mv |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
repository.mail.fl_str_mv |
|
_version_ |
1799137644789104640 |