Efficient LiDAR-based In-water Obstacle Detection and Segmentation by Autonomous Surface Vehicles in Aquatic Environments

Jeong, Mingi; Li, Alberto Quattrini

doi:10.1109/iros51168.2021.9636028

Cited by 9 publications

(3 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It possesses inherent limitations, particularly in its applicability to environments beyond urban landscapes. One notable area where Cityscapes falls short is in the segmentation of aquatic environments [48]-a domain vastly different from urban settings in terms of visual features and segmentation challenges [49]. Recognizing this gap, researchers [20] started to develop a specialized model tailored for aquatic environments, leading to the creation of the WaSR model.…”

Section: Wasrmentioning

confidence: 99%

Urban Aquatic Scene Expansion for Semantic Segmentation in Cityscapes

Yue,

Lo,

et al. 2024

Urban Science

View full text Add to dashboard Cite

In urban environments, semantic segmentation using computer vision plays a pivotal role in understanding and interpreting the diverse elements within urban imagery. The Cityscapes dataset, widely used for semantic segmentation in urban scenes, predominantly features urban elements like buildings and vehicles but lacks aquatic elements. Recognizing this limitation, our study introduces a method to enhance the Cityscapes dataset by incorporating aquatic classes, crucial for a comprehensive understanding of coastal urban environments. To achieve this, we employ a dual-model approach using two advanced neural networks. The first network is trained on the standard Cityscapes dataset, while the second focuses on aquatic scenes. We adeptly integrate aquatic features from the marine-focused model into the Cityscapes imagery. This integration is carefully executed to ensure a seamless blend of urban and aquatic elements, thereby creating an enriched dataset that reflects the realities of coastal cities more accurately. Our method is evaluated by comparing the enhanced Cityscapes model with the original on a set of diverse urban images, including aquatic views. The results demonstrate that our approach effectively maintains the high segmentation accuracy of the original Cityscapes dataset for urban elements while successfully integrating marine features. Importantly, this is achieved without necessitating additional training, which is a significant advantage in terms of resource efficiency.

show abstract

Section: Wasrmentioning

confidence: 99%

Urban Aquatic Scene Expansion for Semantic Segmentation in Cityscapes

Yue,

Lo,

et al. 2024

Urban Science

View full text Add to dashboard Cite

show abstract

“…Conventional image‐processing methods (Jin et al, 2020; Park et al, 2015; Sinisterra et al, 2017; Zhang et al, 2017) or deep learning‐based detection methods (Chen et al, 2021; Hammedi et al, 2019; Lee et al, 2021; Liu et al, 2021; Moosbauer et al, 2019; Nita & Vandewal, 2020; Spraul et al, 2020) have been suggested, and some studies (Bovcon et al, 2021; Prasad et al, 2017; Shao et al, 2018) have provided data sets for training and validating the object‐detection algorithms. LiDAR (Jeong & Li, 2021; Lin et al, 2022; Thompson et al, 2019) and radar (Almeida et al, 2009; Ha et al, 2021; Im et al, 2021) have also been used to detect maritime obstacles. Unlike the camera which is technically a bearing‐only sensor, LiDAR and radar provide both range and bearing measurements.…”

Section: Related Workmentioning

confidence: 99%

Field experiment of autonomous ship navigation in canal and surrounding nearshore environments

Kim,

Lee,

Chung

et al. 2023

Journal of Field Robotics

View full text Add to dashboard Cite

In this paper, we present the development of autonomous navigation capabilities for small cruise boats, and their verification by field experiments in a canal and its surrounding waters. A cruise boat was converted to an autonomous surface vehicle (ASV) by installing various sensors and actuators to enable autonomous navigation. Navigation and perception sensors, such as global positioning system, attitude and heading reference system, radar, light detection and ranging (LiDAR), and cameras, were mounted on the ASV to estimate its motion and perceive the surrounding environment. Motors and potentiometers were installed for active control of the ASV. Software system components including navigation filters, object‐detection, path‐planning, and control algorithms were designed and implemented. In the narrow canal region, LiDARs were used to detect the side walls and boundaries of the canal. In open areas outside the canal, obstacles and object features were detected using various combinations of onboard sensors. A model‐based path‐planning algorithm was designed to avoid the detected obstacles, and the line‐of‐sight guidance was employed to control the vehicle. The performance of the developed system was verified through a field experiment in a real‐world maritime environment.

show abstract

“…Due to the use of infrared radiation, which has a much shorter wavelength than microwaves used by radar, they have higher resolution and lower range. Unlike the terrestrial environment, the use of LIDAR in the marine environment is characterized by a minimal return signal in calm water, which allows for quick recognition of potential obstacles floating on the surface [14]. The use of data from the LIDAR device allows medium-range data from the radar device to be supplemented with data about the ship's surroundings in its immediate vicinity.…”

Section: Autonomous Ship Navigationmentioning

confidence: 99%

Modeling of an Autonomous Electric Propulsion Barge for Future Inland Waterway Transport

Łebkowski,

Koznowski

2023

Energies

View full text Add to dashboard Cite

International trade is continuously rising, leading to an increase in the flow of goods passing through transportation hubs, including air and sea. In addition, the aging fleet of inland vessels necessitates renewal through the construction of new vessels, presenting opportunities for the adoption of modern transport technologies. Autonomous barges can transport bulk and containerized cargo between the central port of a specific region and smaller satellite ports, enabling the dispersal of goods over a wider area. Equipping autonomous barges with advanced sensors, such as LIDAR, computer vision systems that operate in visible light and thermal infrared, and incorporating advanced path finding and cooperation algorithms may enable them to operate autonomously, subject only to remote supervision. The purpose of this study is to explore the potential of autonomous electric propulsion barges in inland waterway transport. Given the increasing demand for efficient and sustainable transport solutions as a result of various new policies, which have set new ambitious goals in clean transportation, this study aims to develop a proposition of an electric propulsion hybrid drive inland waterway barge, and compare it to a conventional diesel-powered barge. The methodology involves the creation of a simulation model of an inland waterway class IV electric barge, equipped with advanced sensors and autonomous control systems. The barge’s navigation is managed through a multi-agent system, with evolutionary algorithms determining a safe passage route. This research also utilizes a proprietary networked ship traffic simulator, based on real inland vessel recorded routes, to conduct the autonomous navigation study. The energy consumption of the barge on a route resulting from the ship traffic simulation is then examined using the mathematical model using the OpenModelica package. As a result of the study, the proposed hybrid propulsion system achieved a 16% reduction in fuel consumption and CO2 emissions, while cutting engine operation time by more than 71%. The findings could provide valuable insights into the feasibility and efficiency of autonomous electric propulsion barges, potentially helping future developments in inland waterway transport.

show abstract

Efficient LiDAR-based In-water Obstacle Detection and Segmentation by Autonomous Surface Vehicles in Aquatic Environments

Cited by 9 publications

References 26 publications

Urban Aquatic Scene Expansion for Semantic Segmentation in Cityscapes

Urban Aquatic Scene Expansion for Semantic Segmentation in Cityscapes

Field experiment of autonomous ship navigation in canal and surrounding nearshore environments

Modeling of an Autonomous Electric Propulsion Barge for Future Inland Waterway Transport

Contact Info

Product

Resources

About