Limits...
Complete scene recovery and terrain classification in textured terrain meshes.

Song W, Cho K, Um K, Won CS, Sim S - Sensors (Basel) (2012)

Bottom Line: Terrain classification allows a mobile robot to create an annotated map of its local environment from the three-dimensional (3D) and two-dimensional (2D) datasets collected by its array of sensors, including a GPS receiver, gyroscope, video camera, and range sensor.However, parts of objects that are outside the measurement range of the range sensor will not be detected.Here, the Gibbs-Markov random field is used to segment the ground from 2D videos and 3D point clouds.

View Article: PubMed Central - PubMed

Affiliation: Department of Multimedia Engineering, Dongguk University-Seoul, 26 Pildosng 3 Ga, Jung-gu, Seoul 100-715, Korea. songwei@dongguk.edu

ABSTRACT
Terrain classification allows a mobile robot to create an annotated map of its local environment from the three-dimensional (3D) and two-dimensional (2D) datasets collected by its array of sensors, including a GPS receiver, gyroscope, video camera, and range sensor. However, parts of objects that are outside the measurement range of the range sensor will not be detected. To overcome this problem, this paper describes an edge estimation method for complete scene recovery and complete terrain reconstruction. Here, the Gibbs-Markov random field is used to segment the ground from 2D videos and 3D point clouds. Further, a masking method is proposed to classify buildings and trees in a terrain mesh.

No MeSH data available.


Height estimation result.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC3472881&req=5

f14-sensors-12-11221: Height estimation result.

Mentions: We then detect the edge of objects by using the non-ground classification result. We investigate the performance of the proposed height estimation method by comparing the obtained values with the actual heights (2.90 m on average). Since the range sensor scans objects only up to a height of 1.8 m, the upper parts of buildings cannot be sensed. However, as shown in Figure 14, we recover the missing parts from the incomplete terrain mesh, and the average estimated height value is 2.92 ± 0.11 m. In Figure 14, the x-axis represents the distance between the estimated vertices with the first estimated vertex.


Complete scene recovery and terrain classification in textured terrain meshes.

Song W, Cho K, Um K, Won CS, Sim S - Sensors (Basel) (2012)

Height estimation result.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC3472881&req=5

f14-sensors-12-11221: Height estimation result.
Mentions: We then detect the edge of objects by using the non-ground classification result. We investigate the performance of the proposed height estimation method by comparing the obtained values with the actual heights (2.90 m on average). Since the range sensor scans objects only up to a height of 1.8 m, the upper parts of buildings cannot be sensed. However, as shown in Figure 14, we recover the missing parts from the incomplete terrain mesh, and the average estimated height value is 2.92 ± 0.11 m. In Figure 14, the x-axis represents the distance between the estimated vertices with the first estimated vertex.

Bottom Line: Terrain classification allows a mobile robot to create an annotated map of its local environment from the three-dimensional (3D) and two-dimensional (2D) datasets collected by its array of sensors, including a GPS receiver, gyroscope, video camera, and range sensor.However, parts of objects that are outside the measurement range of the range sensor will not be detected.Here, the Gibbs-Markov random field is used to segment the ground from 2D videos and 3D point clouds.

View Article: PubMed Central - PubMed

Affiliation: Department of Multimedia Engineering, Dongguk University-Seoul, 26 Pildosng 3 Ga, Jung-gu, Seoul 100-715, Korea. songwei@dongguk.edu

ABSTRACT
Terrain classification allows a mobile robot to create an annotated map of its local environment from the three-dimensional (3D) and two-dimensional (2D) datasets collected by its array of sensors, including a GPS receiver, gyroscope, video camera, and range sensor. However, parts of objects that are outside the measurement range of the range sensor will not be detected. To overcome this problem, this paper describes an edge estimation method for complete scene recovery and complete terrain reconstruction. Here, the Gibbs-Markov random field is used to segment the ground from 2D videos and 3D point clouds. Further, a masking method is proposed to classify buildings and trees in a terrain mesh.

No MeSH data available.