Nowadays, semantic segmentation is used increasingly often in exploration by underwater robots. For example, it is used in autonomous navigation so that the robot can recognise the elements of its environment during the mission to avoid collisions. Other applications include the search for archaeological artefacts, the inspection of underwater structures or in species monitoring. Therefore, it is necessary to improve the performance in these tasks as much as possible. To this end, we compare some methods for image quality improvement and data augmentation and test whether higher performance metrics can be achieved with both strategies. The experiments are performed with the SegNet implementation and the SUIM dataset with eight common underwater classes to compare the obtained results with the already known ones. The results obtained with both strategies show that they are beneficial and lead to better performance results by achieving a mean IoU of 56% and an increased overall accuracy of 81.8%. The result for the individual classes shows that there are five classes with an IoU value close to 60% and only one class with an IoU value less than 30%, which is a more reliable result and is easier to use in real contexts.

Nowadays, ocean exploration is far from complete and the development of suitable recognition systems are crucial, to allow that the robots perform inspection and monitoring tasks in diverse conditions. The online available datasets are incomplete for these kinds of scenarios and, so it is important to build datasets that covered real condition in a simulated environment. Thus, it was developed a dataset with some man-made objects presents in the underwater environment. Moreover, it is also presented the developed method (Convolutional Neural Network) and its evaluation in diverse conditions is performed. It is also presented a comparative analysis and a discussion between the proposed algorithm and the ResNet architecture. The obtained results showed that the developed method is appropriate to classify 7 critical different objects with good performance.

Nowadays, semantic segmentation is increasingly used in exploration by underwater robots, for example in autonomous navigation, so that the robot can recognise the nature and elements of its environment during the mission and act according to this classification to avoid collisions. Other applications can be found in the search for archaeological artefacts, in the inspection of underwater structures or in species monitoring. Therefore, it is necessary to try to improve the performance in these tasks as much as possible. To this end, we compare some methods for improving image quality and for data augmentation and test whether higher performance metrics can be achieved with both strategies. The experiments are performed with the SegNet implementations and the SUIM dataset with 8 common underwater classes to compare the obtained results with the already known ones. The results obtained with both strategies show that they are beneficial and lead to better performance results by achieving a mean IoU of 56% and an increased overall accuracy of 81.8%. The single result shows that there are 5 classes with an IoU value above 60% and only one class with an IoU value below 30%, which is a more reliable result and easier to use in real contexts.

This paper aims to present a mosaicking method for underwater robotic applications, whose result can be provided to other perceptual systems for scene understanding such as real-time object recognition. This method is called robust and large-scale mosaicking (ROLAMOS) and presents an efficient frame-to-frame motion estimation with outlier removal and consistency checking that maps large visual areas in high resolution. The visual mosaic of the sea-floor is created on-the-fly by a robust registration procedure that composes monocular observations and manages the computational resources. Moreover, the registration process of ROLAMOS aligns the observation to the existing mosaic. A comprehensive set of experiments compares the performance of ROLAMOS to other similar approaches, using both data sets (publicly available) and live data obtained by a ROV operating in real scenes. The results demonstrate that ROLAMOS is adequate for mapping of sea-floor scenarios as it provides accurate information from the seabed, which is of extreme importance for autonomous robots surveying the environment that does not rely on specialized computers. The ROLAMOS is suitable for robotic applications that require an online, robust and effective technique to reconstruct the underwater environment from only visual information.