Sensors, Vol. 19, Pages 4451: 3D Object Recognition Based on Point Clouds in Underwater Environment with Global Descriptors: A Survey

Sensors, Vol. 19, Pages 4451: 3D Object Recognition Based on Point Clouds in Underwater Environment with Global Descriptors: A Survey Sensors doi: 10.3390/s19204451 Authors: Himri Ridao Gracias This paper addresses the problem of object recognition from colorless 3D point clouds inunderwater 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 assistAutonomous Underwater Vehicles (AUVs) in performing autonomous interventions in underwaterInspection, Maintenance and Repair (IMR) applications. A set of test objects were chosen as beingrepresentative of IMR applications whose shape is typically known a priori. As such, CAD modelswere used to create virtual views of the objects under realistic conditions of added noise and varyingresolution. Extensive experiments were conducted from both virtual scans and from real data collectedwith an AUV equipped with a fast laser sensor developed in our research centre. The underwatertesting was conducted from a moving platform, which can create deformations in the perceived shapeof 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 weconducted illustrated the importance of matching the resolution of the database scans and test scans,as this significantly impact...
Source: Sensors - Category: Biotechnology Authors: Tags: Article Source Type: research