3D Object Recognition Based on Point Clouds in Underwater Environment with Global Descriptors: A Survey
This paper addresses the problem of object recognition from colorless 3D point clouds in underwater environments. It presents a performance comparison of state-of-the-art global descriptors, which are readily available as open source code. The studied methods are intended to assist Autonomous Underw...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-10-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/19/20/4451 |
| _version_ | 1818015549141024768 |
|---|---|
| author | Khadidja Himri Pere Ridao Nuno Gracias |
| author_facet | Khadidja Himri Pere Ridao Nuno Gracias |
| author_sort | Khadidja Himri |
| collection | DOAJ |
| description | This paper addresses the problem of object recognition from colorless 3D point clouds in underwater environments. It presents a performance comparison of state-of-the-art global descriptors, which are readily available as open source code. The studied methods are intended to assist Autonomous Underwater Vehicles (AUVs) in performing autonomous interventions in underwater Inspection, Maintenance and Repair (IMR) applications. A set of test objects were chosen as being representative of IMR applications whose shape is typically known a priori. As such, CAD models were used to create virtual views of the objects under realistic conditions of added noise and varying resolution. Extensive experiments were conducted from both virtual scans and from real data collected with an AUV equipped with a fast laser sensor developed in our research centre. The underwater testing was conducted from a moving platform, which can create deformations in the perceived shape of the objects. These effects are considerably more difficult to correct than in above-water counterparts, and therefore may affect the performance of the descriptor. Among other conclusions, the testing we conducted illustrated the importance of matching the resolution of the database scans and test scans, as this significantly impacted the performance of all descriptors except one. This paper contributes to the state-of-the-art as being the first work on the comparison and performance evaluation of methods for underwater object recognition. It is also the first effort using comparison of methods for data acquired with a free floating underwater platform. |
| first_indexed | 2024-04-14T06:59:39Z |
| format | Article |
| id | doaj.art-f1afd306f6a04853bb0036fc7c739130 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-14T06:59:39Z |
| publishDate | 2019-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-f1afd306f6a04853bb0036fc7c7391302022-12-22T02:06:48ZengMDPI AGSensors1424-82202019-10-011920445110.3390/s19204451s192044513D Object Recognition Based on Point Clouds in Underwater Environment with Global Descriptors: A SurveyKhadidja Himri0Pere Ridao1Nuno Gracias2Underwater Robotics Research Center (CIRS), Computer Vision and Robotics Institute (VICOROB), University of Girona, Parc Científic i Tecnològic UdG C/Pic de Peguera 13, 17003 Girona, SpainUnderwater Robotics Research Center (CIRS), Computer Vision and Robotics Institute (VICOROB), University of Girona, Parc Científic i Tecnològic UdG C/Pic de Peguera 13, 17003 Girona, SpainUnderwater Robotics Research Center (CIRS), Computer Vision and Robotics Institute (VICOROB), University of Girona, Parc Científic i Tecnològic UdG C/Pic de Peguera 13, 17003 Girona, SpainThis paper addresses the problem of object recognition from colorless 3D point clouds in underwater environments. It presents a performance comparison of state-of-the-art global descriptors, which are readily available as open source code. The studied methods are intended to assist Autonomous Underwater Vehicles (AUVs) in performing autonomous interventions in underwater Inspection, Maintenance and Repair (IMR) applications. A set of test objects were chosen as being representative of IMR applications whose shape is typically known a priori. As such, CAD models were used to create virtual views of the objects under realistic conditions of added noise and varying resolution. Extensive experiments were conducted from both virtual scans and from real data collected with an AUV equipped with a fast laser sensor developed in our research centre. The underwater testing was conducted from a moving platform, which can create deformations in the perceived shape of the objects. These effects are considerably more difficult to correct than in above-water counterparts, and therefore may affect the performance of the descriptor. Among other conclusions, the testing we conducted illustrated the importance of matching the resolution of the database scans and test scans, as this significantly impacted the performance of all descriptors except one. This paper contributes to the state-of-the-art as being the first work on the comparison and performance evaluation of methods for underwater object recognition. It is also the first effort using comparison of methods for data acquired with a free floating underwater platform.https://www.mdpi.com/1424-8220/19/20/44513d object recognitionpoint cloudsglobal descriptorslaser scannerunderwater environmentpipeline detectioninspectionmaintenance and repairauvautonomous manipulation |
| spellingShingle | Khadidja Himri Pere Ridao Nuno Gracias 3D Object Recognition Based on Point Clouds in Underwater Environment with Global Descriptors: A Survey Sensors 3d object recognition point clouds global descriptors laser scanner underwater environment pipeline detection inspection maintenance and repair auv autonomous manipulation |
| title | 3D Object Recognition Based on Point Clouds in Underwater Environment with Global Descriptors: A Survey |
| title_full | 3D Object Recognition Based on Point Clouds in Underwater Environment with Global Descriptors: A Survey |
| title_fullStr | 3D Object Recognition Based on Point Clouds in Underwater Environment with Global Descriptors: A Survey |
| title_full_unstemmed | 3D Object Recognition Based on Point Clouds in Underwater Environment with Global Descriptors: A Survey |
| title_short | 3D Object Recognition Based on Point Clouds in Underwater Environment with Global Descriptors: A Survey |
| title_sort | 3d object recognition based on point clouds in underwater environment with global descriptors a survey |
| topic | 3d object recognition point clouds global descriptors laser scanner underwater environment pipeline detection inspection maintenance and repair auv autonomous manipulation |
| url | https://www.mdpi.com/1424-8220/19/20/4451 |
| work_keys_str_mv | AT khadidjahimri 3dobjectrecognitionbasedonpointcloudsinunderwaterenvironmentwithglobaldescriptorsasurvey AT pereridao 3dobjectrecognitionbasedonpointcloudsinunderwaterenvironmentwithglobaldescriptorsasurvey AT nunogracias 3dobjectrecognitionbasedonpointcloudsinunderwaterenvironmentwithglobaldescriptorsasurvey |