Criado em 2005 com aprovação do primeiro projeto de pesquisa do grupo apoiado pelo CNPq na área de visualização de informação. O grupo tem como características principais trabalhar com tecnologias inovadoras, que possibilitem no avanço e divulgação do conhecimento cietífico e desenvolver produtos aplicados em benefício da sociedade. As Linhas de Pesquisa do grupo são Visualização da Informação, Realidade Virtual e Aumentada, Interação Humano-Computador, Aprendizado de Máquina, Processamento de Imagens, Visão Computacional, Síntese e Reconhecimento de Voz e Tecnologias Assistivas.

Rua Augusto Corrêa, 1 - Guamá, Belém
Universidade Federal do Pará - Campus Guamá
Instituto de Ciências Exatas e Naturais
Setor Básico
E-mail: ufpalabvis@gmail.com

Publicações:

Visual Abstract!

One of the main challenges to creating rich, seamless, and adaptive Augmented Reality (AR) browsers is the accurate registration of the virtual contents in the real world. Usually, the AR browsers offer augmented navigation functionality by GPS and sensors, such as magnetometer and accelerometer. However, the position of virtual markers suffers some errors when the user is near to the desired location, due to many factors such as sensors failures and bad internet connections, among others. Additionally, to identify the correct marker, when there are many, is a challenging task to users. Therefore, to mitigate these problems, this paper proposes a hybrid approach of location and vision based tracking for AR applications, since the image recognition can be very helpful to identify near locations, avoiding misplaced markers and at the same time giving emphasis to that marker. Furthermore, to avoid bottlenecks in the AR browser applications the combination of the quality of vision-based tracking and the speed of the sensors is proposed. The designed system gets the information about the Points Of Interests (POIs), recommend places to explore around the user via GPS and sensors (as already done by current AR browsers) and run the recognition process only for the nearest POI to improve its registration. Aiming to choose the best recognition algorithm for this scenario, precision and time tests are performed using three algorithms (ORB, BRISK, and AKAZE) to detect keypoints and compute theirs features, and two algorithms (RANSAC and LMEDS) to estimate camera pose. The test pointed that the combination of AKAZE and RANSAC has the best accuracy, but an impractical time to use in real time application. Hence, the usage of vision techniques in an interval of time (skipping some frames) and the usage of inertial sensors movements to update the skipped frames are proposed, in order to use this solution on a mobile platform. Finally, the system solution was implemented in a tourism mobile AR application and some results are presented.

Lorem Ipsum

Lorem ipsum dolor sit amet, consectetur adipiscing elit. Nam finibus felis at posuere ullamcorper. Class aptent taciti sociosqu ad litora torquent per conubia nostra, per inceptos himenaeos. Interdum et malesuada fames ac ante ipsum primis in faucibus. Quisque ac malesuada purus, et lobortis arcu. Ut dapibus facilisis augue. Sed gravida nisi et metus congue aliquet. Fusce et turpis quam. Sed consectetur semper aliquet. Pellentesque habitant morbi tristique senectus et netus et malesuada fames ac turpis egestas. Cras non metus vitae felis molestie aliquet porttitor sit amet arcu. Suspendisse dui diam, condimentum in nunc quis, tincidunt elementum lectus. Donec eu elementum mi, quis accumsan est. Aenean commodo eros arcu, porta iaculis risus efficitur eget. Duis vulputate non lorem quis pulvinar. Nunc eu bibendum neque. Pellentesque et euismod risus, vel gravida elit.

Aliquam id neque eget quam consectetur finibus. Vivamus scelerisque justo mauris, id blandit tortor pharetra et. In hac habitasse platea dictumst. Aenean id metus ut magna dictum tincidunt eu a enim. Curabitur a felis justo. Ut placerat elit sit amet tortor molestie aliquet. Donec efficitur eros id odio semper, ut fermentum ipsum semper. Proin luctus sapien leo, quis bibendum leo molestie sit amet. Donec eu augue cursus, sagittis tellus sed, auctor magna. Aenean id magna eu sem rutrum maximus. In feugiat facilisis luctus. Morbi nec nibh vel dui imperdiet commodo a nec lectus. Donec imperdiet turpis dui, nec dapibus risus scelerisque at. Mauris vel ante dolor. Cras laoreet pellentesque lorem ut ullamcorper. Donec massa libero, ultricies id ipsum at, lacinia tincidunt neque.

Nunc sed scelerisque metus, non viverra nisi. Pellentesque habitant morbi tristique senectus et netus et malesuada fames ac turpis egestas. Nunc lacinia augue id nisi pellentesque, vitae efficitur magna sollicitudin. Morbi congue commodo lorem, quis sodales tortor ullamcorper interdum. Vivamus pretium dui ligula, non consectetur purus egestas ac. Nunc tincidunt velit tempus nunc elementum imperdiet. Etiam sit amet justo aliquam, tempus mauris eu, scelerisque tellus. Proin facilisis, risus et ultricies feugiat, dolor nulla efficitur tellus, eu scelerisque ligula quam a nunc. Morbi gravida odio id leo egestas tempor. Phasellus bibendum, mi in mattis faucibus, mauris nisi ullamcorper neque, et eleifend ligula purus eu urna. Ut a mattis neque, ac viverra sem. Nam ut lacus id ligula maximus lacinia. Fusce luctus semper rhoncus. Vivamus non metus aliquet, faucibus leo ullamcorper, rhoncus neque. Donec congue pharetra magna at tincidunt. Maecenas lobortis imperdiet est id malesuada.

Donec fringilla erat quam, eu placerat diam mollis in. Etiam pretium enim urna, vitae vulputate lectus fermentum sed. Sed rhoncus convallis risus quis faucibus. Sed iaculis est eget erat faucibus, in tincidunt mauris luctus. Integer quis ultricies lacus. Pellentesque semper lectus a condimentum lacinia. Donec a nunc odio. Donec sed tincidunt orci, vitae tempus lectus. Pellentesque eget condimentum erat.

Nunc laoreet augue ipsum, ac scelerisque arcu finibus vel. Donec eu nulla laoreet, imperdiet ex vel, interdum elit. Duis iaculis faucibus orci, id elementum augue gravida sit amet. Phasellus ornare erat vitae pharetra cursus. Phasellus nec finibus tortor. Quisque pretium mattis pellentesque. Donec mattis, neque sed tempus egestas, erat lectus faucibus libero, id facilisis ligula nisi eu turpis. Mauris accumsan sapien at tortor sodales congue. Curabitur auctor orci eu varius tincidunt. Integer porttitor sit amet est non vulputate. Integer dignissim ipsum sit amet eros bibendum, ac sollicitudin lorem gravida. Nunc ut fringilla tortor. Pellentesque eros enim, dignissim at mauris quis, sodales pharetra dolor.

One of the main challenges to creating rich, seamless, and adaptive Augmented Reality (AR) browsers is the accurate registration of the virtual contents in the real world. Usually, the AR browsers offer augmented navigation functionality by GPS and sensors, such as magnetometer and accelerometer. However, the position of virtual markers suffers some errors when the user is near to the desired location, due to many factors such as sensors failures and bad internet connections, among others. Additionally, to identify the correct marker, when there are many, is a challenging task to users. Therefore, to mitigate these problems, this paper proposes a hybrid approach of location and vision based tracking for AR applications, since the image recognition can be very helpful to identify near locations, avoiding misplaced markers and at the same time giving emphasis to that marker. Furthermore, to avoid bottlenecks in the AR browser applications the combination of the quality of vision-based tracking and the speed of the sensors is proposed. The designed system gets the information about the Points Of Interests (POIs), recommend places to explore around the user via GPS and sensors (as already done by current AR browsers) and run the recognition process only for the nearest POI to improve its registration. Aiming to choose the best recognition algorithm for this scenario, precision and time tests are performed using three algorithms (ORB, BRISK, and AKAZE) to detect keypoints and compute theirs features, and two algorithms (RANSAC and LMEDS) to estimate camera pose. The test pointed that the combination of AKAZE and RANSAC has the best accuracy, but an impractical time to use in real time application. Hence, the usage of vision techniques in an interval of time (skipping some frames) and the usage of inertial sensors movements to update the skipped frames are proposed, in order to use this solution on a mobile platform. Finally, the system solution was implemented in a tourism mobile AR application and some results are presented.

Visual Abstract!

One of the main challenges to creating rich, seamless, and adaptive Augmented Reality (AR) browsers is the accurate registration of the virtual contents in the real world. Usually, the AR browsers offer augmented navigation functionality by GPS and sensors, such as magnetometer and accelerometer. However, the position of virtual markers suffers some errors when the user is near to the desired location, due to many factors such as sensors failures and bad internet connections, among others. Additionally, to identify the correct marker, when there are many, is a challenging task to users. Therefore, to mitigate these problems, this paper proposes a hybrid approach of location and vision based tracking for AR applications, since the image recognition can be very helpful to identify near locations, avoiding misplaced markers and at the same time giving emphasis to that marker. Furthermore, to avoid bottlenecks in the AR browser applications the combination of the quality of vision-based tracking and the speed of the sensors is proposed. The designed system gets the information about the Points Of Interests (POIs), recommend places to explore around the user via GPS and sensors (as already done by current AR browsers) and run the recognition process only for the nearest POI to improve its registration. Aiming to choose the best recognition algorithm for this scenario, precision and time tests are performed using three algorithms (ORB, BRISK, and AKAZE) to detect keypoints and compute theirs features, and two algorithms (RANSAC and LMEDS) to estimate camera pose. The test pointed that the combination of AKAZE and RANSAC has the best accuracy, but an impractical time to use in real time application. Hence, the usage of vision techniques in an interval of time (skipping some frames) and the usage of inertial sensors movements to update the skipped frames are proposed, in order to use this solution on a mobile platform. Finally, the system solution was implemented in a tourism mobile AR application and some results are presented.