Automated Dimensional Extraction Of Different Regions Using Single Monocular Camera In Pseudo-Stereo Configuration

Lee, Denzel; Liu, Jingmin; Lee, Shawndy Michael; Foong, Shaohui

doi:10.1109/aim43001.2020.9158842

Cited by 3 publications

(5 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As seen in the figure, rotating the camera results in an warped and unusable point cloud. The point cloud generated with the cascaded linear actuator is closer to a semi-circle curvature in its top orthographic view than the standard rack-and-pinion linear actuator used in our previous work [3], where the point cloud's curvature is not as extensive.…”

Section: Custom Pseudo-stereo Camera Systemmentioning

confidence: 65%

“…Within a confined and limited operating space such as our proposed application, there are a few situations where the camera assembly's useful FOV might be insufficient to cover the entire inspection target's length, rendering any measurement algorithm useless. These situations include the UAV landing too near or towards the cavity's sides, which were major pitfalls in our previous work [3]. Due to the tight space within the cavity, it is challenging to precisely maneuver or hold a stable hover inside.…”

Section: Custom Pseudo-stereo Camera Systemmentioning

confidence: 98%

“…Our proposed set-up emulates the parallel stereo camera by capturing image pairs from various positions on the actuator based on a baseline distance, b base . Broadly, the overall camera assembly operation and our parallel pseudo-stereo camera setup calibration process remain the same as our previous work [3]. However, the translation from a standard single-tiered rack-and-pinion to an n − th tiered cascaded set-up changes the baseline calculation.…”

Section: B Pseudo-stereo Camera Configurationmentioning

confidence: 99%

“…The max average RMSE of the ten execution along all positions is 0.822mm, which is still much within the current standards of ±3mm. 3) Cascaded Versus Traditional Linear Actuator's Impact on Measurement Accuracy: The third part compares displacement measurement obtained from the cascaded linear actuator, traditional single-tiered linear actuator, and the 2D measurement algorithm from our previous work [3] when the camera is directly parallel to the orthographic frontal view. The third experiment consists of ten execution of the algorithm, each for the cascaded and traditional linear actuator and the 2D measurement algorithm from our previous work.…”

Section: ) Full Conduct Inspection Operationmentioning

confidence: 99%

“…Thanks to the exponential growth in robotics, computer science, and many other related fields, drone or Unmanned Aerial Vehicle (UAV) has served as an optimal solution when coupled with computer vision methods [1], [2]. This paper is an extension of our previous work [3], where the application in focus is the inspection of the rail viaduct bearing (see Fig. 1).…”

Section: Introductionmentioning

confidence: 97%

See 4 more Smart Citations

Geometrical-Based Displacement Measurement With Pseudostereo Monocular Camera on Bidirectional Cascaded Linear Actuator

Lee

Liu

Lim

et al. 2021

IEEE/ASME Trans. Mechatron.

Self Cite

View full text Add to dashboard Cite

This paper details the development of a geometrical-based displacement extraction framework capable of automatically extracting critical infrastructure measurements in one sequence. The framework is a novel rail viaduct bearing inspection pipeline implemented on BINOv2: Bearing Inspector for Narrow-space Observation Version 2. BINOv2 is a tethered custom Unmanned Aerial Vehicle (UAV) system utilized to supplant labor-intensive pipelines and enhance inspection accuracy of infrastructure conditions in confined remote locations. The algorithm accepts stereoscopic images taken from a single monocular camera on a bi-directional cascaded linear actuator system in a rack-and-pinion configuration. A point cloud model generated from the image sets then runs through a hierarchical neural network for 3D segmentation to extract targeted regions of interest. Our training pipeline generates and forms the full model's training data set using only a small sample of real point clouds. The point cloud generated is inadequate to form the full bearing geometry profile. Therefore, the proposed framework projects best-fit circles based on the point cloud curvature to form the full bearing geometry profile so that the required displacement measurement is available for extraction. Several experiments were conducted on a mock-up and actual operational site to validate the proposed framework's accuracy, its robustness and comparison with other state-of-the-art alternatives.

show abstract

Section: Custom Pseudo-stereo Camera Systemmentioning

confidence: 65%

Section: Custom Pseudo-stereo Camera Systemmentioning

confidence: 98%

Section: B Pseudo-stereo Camera Configurationmentioning

confidence: 99%

Section: ) Full Conduct Inspection Operationmentioning

confidence: 99%