Different Color Spaces in Deep Learning-Based Water Segmentation for Autonomous Marine Operations
| Autor: | Nikolaos Passalis, Jenni Raitoharju, Jussi Taipalmaa |
|---|---|
| Přispěvatelé: | Tampere University, Computing Sciences |
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
Channel (digital image)
business.industry Computer science Deep learning 02 engineering and technology HSL and HSV Image segmentation 010501 environmental sciences Color space 113 Computer and information sciences 01 natural sciences Drone 0202 electrical engineering electronic engineering information engineering RGB color model 020201 artificial intelligence & image processing Segmentation Computer vision Artificial intelligence business 0105 earth and related environmental sciences |
| Zdroj: | ICIP |
| Popis: | For autonomous unmanned surface vehicles (USV) operations, it is important to be able to observe the surroundings using visual information. Water segmentation is a task where the water surface is recognized and separated from everything else. The algorithm performing the segmentation must be robust, because safety is the most important feature of autonomous USVs. This is especially challenging in many USV applications, where the rapidly changing weather and lighting conditions can cause significant distribution shifts. In this study, we analyze the robustness of different color spaces (e.g., RGB and HSV) for water segmentation and consider how to use different color channels in training and testing to maximize the robustness. We evaluate the segmentation performance on a challenging completely unseen test dataset, recorded in vastly different conditions and with different equipment. acceptedVersion |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|