The Experts below are selected from a list of 30 Experts worldwide ranked by ideXlab platform
Yanning Zhang - One of the best experts on this subject based on the ideXlab platform.
-
a monocular visual odometry method based on virtual real hybrid map in low Texture outdoor Environment
Sensors, 2021Co-Authors: Xiuchuan Xie, Tao Yang, Yajia Ning, Fangbing Zhang, Yanning ZhangAbstract:With the extensive application of robots, such as unmanned aerial vehicle (UAV) in exploring unknown Environments, visual odometry (VO) algorithms have played an increasingly important role. The Environments are diverse, not always Textured, or low-Textured with insufficient features, making them challenging for mainstream VO. However, for low-Texture Environment, due to the structural characteristics of man-made scene, the lines are usually abundant. In this paper, we propose a virtual-real hybrid map based monocular visual odometry algorithm. The core idea is that we reprocess line segment features to generate the virtual intersection matching points, which can be used to build the virtual map. Introducing virtual map can improve the stability of the visual odometry algorithm in low-Texture Environment. Specifically, we first combine unparallel matched line segments to generate virtual intersection matching points, then, based on the virtual intersection matching points, we triangulate to get a virtual map, combined with the real map built upon the ordinary point features to form a virtual-real hybrid 3D map. Finally, using the hybrid map, the continuous camera pose estimation can be solved. Extensive experimental results have demonstrated the robustness and effectiveness of the proposed method in various low-Texture scenes.
C Wilson - One of the best experts on this subject based on the ideXlab platform.
-
sediment infilling and geomorphological change of a mud capped raccoon island dredge pit near ship shoal of louisiana shelf
Estuarine Coastal and Shelf Science, 2020Co-Authors: Haoran Liu, C WilsonAbstract:Abstract To restore degraded barrier shorelines of the Mississippi River Delta of coastal Louisiana, sand is dredged from high-quality borrow areas on the adjacent continental shelf. This dredging process generally creates a topographic low that facilitates the rapid capture of sediments. Our understanding of sedimentary processes and influences on seabed morphologic evolution is still limited. In this study, Raccoon Island dredge pit in a paleo-river channel on the Louisiana shelf was studied via multiple bathymetric surveys. Physical parameters include pit geometry and topographic change from post-dredging, and infilling sediment sources were analyzed. Raccoon Island pit was 100% filled up less than six years after dredging. The average infilling rate in the Raccoon Island pit was 1.10 m/year from 2013 to 2018. During the surveying period, the pit wall slope decreased by 6.8° within two years. The sediment infilling process in the Raccoon Island pit was likely under the combined influence of topography, wind-driven currents, storm waves, and the dynamic Atchafalaya River dispersal system. The Atchafalaya River reached high discharge in 2016, which likely contributed to a surprisingly high sediment infilling rate at Raccoon Island pit between 2015 and 2018. Raccoon Island pit is in a mixed Texture Environment in which the sandy pit was fully filled with mud. Mud is useful for marsh restoration but is not considered a quality resource for barrier island or beach restoration. Thus, the Raccoon Island pit is not regarded as a renewable resource for future barrier island restoration.
Xiuchuan Xie - One of the best experts on this subject based on the ideXlab platform.
-
a monocular visual odometry method based on virtual real hybrid map in low Texture outdoor Environment
Sensors, 2021Co-Authors: Xiuchuan Xie, Tao Yang, Yajia Ning, Fangbing Zhang, Yanning ZhangAbstract:With the extensive application of robots, such as unmanned aerial vehicle (UAV) in exploring unknown Environments, visual odometry (VO) algorithms have played an increasingly important role. The Environments are diverse, not always Textured, or low-Textured with insufficient features, making them challenging for mainstream VO. However, for low-Texture Environment, due to the structural characteristics of man-made scene, the lines are usually abundant. In this paper, we propose a virtual-real hybrid map based monocular visual odometry algorithm. The core idea is that we reprocess line segment features to generate the virtual intersection matching points, which can be used to build the virtual map. Introducing virtual map can improve the stability of the visual odometry algorithm in low-Texture Environment. Specifically, we first combine unparallel matched line segments to generate virtual intersection matching points, then, based on the virtual intersection matching points, we triangulate to get a virtual map, combined with the real map built upon the ordinary point features to form a virtual-real hybrid 3D map. Finally, using the hybrid map, the continuous camera pose estimation can be solved. Extensive experimental results have demonstrated the robustness and effectiveness of the proposed method in various low-Texture scenes.
Haoran Liu - One of the best experts on this subject based on the ideXlab platform.
-
sediment infilling and geomorphological change of a mud capped raccoon island dredge pit near ship shoal of louisiana shelf
Estuarine Coastal and Shelf Science, 2020Co-Authors: Haoran Liu, C WilsonAbstract:Abstract To restore degraded barrier shorelines of the Mississippi River Delta of coastal Louisiana, sand is dredged from high-quality borrow areas on the adjacent continental shelf. This dredging process generally creates a topographic low that facilitates the rapid capture of sediments. Our understanding of sedimentary processes and influences on seabed morphologic evolution is still limited. In this study, Raccoon Island dredge pit in a paleo-river channel on the Louisiana shelf was studied via multiple bathymetric surveys. Physical parameters include pit geometry and topographic change from post-dredging, and infilling sediment sources were analyzed. Raccoon Island pit was 100% filled up less than six years after dredging. The average infilling rate in the Raccoon Island pit was 1.10 m/year from 2013 to 2018. During the surveying period, the pit wall slope decreased by 6.8° within two years. The sediment infilling process in the Raccoon Island pit was likely under the combined influence of topography, wind-driven currents, storm waves, and the dynamic Atchafalaya River dispersal system. The Atchafalaya River reached high discharge in 2016, which likely contributed to a surprisingly high sediment infilling rate at Raccoon Island pit between 2015 and 2018. Raccoon Island pit is in a mixed Texture Environment in which the sandy pit was fully filled with mud. Mud is useful for marsh restoration but is not considered a quality resource for barrier island or beach restoration. Thus, the Raccoon Island pit is not regarded as a renewable resource for future barrier island restoration.
Fangbing Zhang - One of the best experts on this subject based on the ideXlab platform.
-
a monocular visual odometry method based on virtual real hybrid map in low Texture outdoor Environment
Sensors, 2021Co-Authors: Xiuchuan Xie, Tao Yang, Yajia Ning, Fangbing Zhang, Yanning ZhangAbstract:With the extensive application of robots, such as unmanned aerial vehicle (UAV) in exploring unknown Environments, visual odometry (VO) algorithms have played an increasingly important role. The Environments are diverse, not always Textured, or low-Textured with insufficient features, making them challenging for mainstream VO. However, for low-Texture Environment, due to the structural characteristics of man-made scene, the lines are usually abundant. In this paper, we propose a virtual-real hybrid map based monocular visual odometry algorithm. The core idea is that we reprocess line segment features to generate the virtual intersection matching points, which can be used to build the virtual map. Introducing virtual map can improve the stability of the visual odometry algorithm in low-Texture Environment. Specifically, we first combine unparallel matched line segments to generate virtual intersection matching points, then, based on the virtual intersection matching points, we triangulate to get a virtual map, combined with the real map built upon the ordinary point features to form a virtual-real hybrid 3D map. Finally, using the hybrid map, the continuous camera pose estimation can be solved. Extensive experimental results have demonstrated the robustness and effectiveness of the proposed method in various low-Texture scenes.