Figure 18 - uploaded by Hyunwoo Song
Content may be subject to copyright.
Source publication
In recent years, the deterioration of infrastructure facilities such as bridges has become a problem. Precautionary measures such as visual inspection and repair by humans are in place as countermeasures for aging; however, there are issues with cost and safety in such inspections. If inspection by robots becomes possible, both these aspects will b...
Similar publications
The article considers three non-visual moments of perception during the process of making a drawing. The emphasis is on drawing as an experiential process rather than the making of artefacts, due to the author/artist’s use of audio-visual recording and writing as part of an expanded idea of drawing, the implication being that the reader of the arti...
Wide field-of-view (FOV) cameras, which capture a larger scene area than narrow FOV cameras, are used in many applications including 3D reconstruction, autonomous driving, and video surveillance. However, wide-angle images contain distortions that violate the assumptions underlying pinhole camera models, resulting in object distortion, difficulties...
![Figure 2-The basic elements of active perception [4]](profile/Mela-Francisco/publication/360687049/figure/fig2/AS:1157134377070593@1652893742288/The-basic-elements-of-active-perception-4_Q320.jpg)
![Figure 4-Le et al. Experimental setup for detecting staplers [1]](profile/Mela-Francisco/publication/360687049/figure/fig4/AS:1157134377058304@1652893742417/Le-et-al-Experimental-setup-for-detecting-staplers-1_Q320.jpg)
![Figure 5-Le et al. Experimental setup for detecting mugs [1]](profile/Mela-Francisco/publication/360687049/figure/fig5/AS:1157134377062410@1652893742429/Le-et-al-Experimental-setup-for-detecting-mugs-1_Q320.jpg)
Active perception is a methodology used to improve the acquisition of data by
autonomously planning the pose or settings of sensors in order to perceive the
environment. Traditional static camera vision systems are limited to only one
perspective of the scene and therefore they cannot deal with issues such as occlusions
in the field-of-view of...
The advent of autonomous driving and advanced driver assistance systems necessitates continuous developments in computer vision for 3D scene understanding. Self-supervised monocular depth estimation, a method for pixel-wise distance estimation of objects from a single camera without the use of ground truth labels, is an important task in 3D scene u...
Methods for 3D lane detection have been recently proposed to address the issue of inaccurate lane layouts in many autonomous driving scenarios (uphill/downhill, bump, etc.). Previous work struggled in complex cases due to their simple designs of the spatial transformation between front view and bird's eye view (BEV) and the lack of a realistic data...
Citations
... In addition, to improve the accuracy of the planar LiDAR, the position of the robot can be detected reliably using the image processing results obtained from the camera [17]. The image processing method combines the existing Harris corner detection and Hough transform based on the image captured by the camera and detects the edge located along the moving direction of the robot as a feature point. ...
Aiming at visual deformation monitoring for construction scaffold temporary structures, a 3D deformation measurement method based on multi-threaded LiDAR point cloud is proposed. The method consists of two parts, which are point cloud alignment and Scaffold tube axes modeling. Point cloud alignment is performed based on the spatial geometry of the normal vectors and intersection points of homologous feature planes in the scene. The scaffold tube point clouds are extracted using the random sampling consistent principle (RANSAC), and the scaffold tube axes model is further obtained by segmental noise reduction and least-squares fitting. Finally, the 3D deformation monitoring of the scaffold is realized by comparing the tube axes models at different times. The maximum relative error of scaffold deformation is 9.09%. The method provides a new technique for the daily monitoring of construction scaffold groups and can be extended to vehicle-mounted LiDAR applications.
