Depth image correction for intel realsense depth camera

Park, Hyun Jun; Kim, Kwang-Baek

doi:10.11591/ijeecs.v19.i2.pp1021-1027

Cited by 2 publications

(2 citation statements)

References 25 publications

(23 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To address these challenges, additional algorithms are often necessary to fix or fill the IR shadow regions that result from partial occlusions. For example, in [60], an object is assumed to have a similar color over the entire surface and a similar depth of adjacent pixels to fill the unmeasured areas. This approach can be effective in certain cases, but it may not always provide accurate results.…”

Section: Monocular Depth Acquisitionmentioning

confidence: 99%

(MARGOT) Monocular Camera-Based Robot Grasping Strategy for Metallic Objects

Veiga Almagro,

Muñoz Orrego,

García González

et al. 2023

Sensors

View full text Add to dashboard Cite

Robotic handling of objects is not always a trivial assignment, even in teleoperation where, in most cases, this might lead to stressful labor for operators. To reduce the task difficulty, supervised motions could be performed in safe scenarios to reduce the workload in these non-critical steps by using machine learning and computer vision techniques. This paper describes a novel grasping strategy based on a groundbreaking geometrical analysis which extracts diametrically opposite points taking into account surface smoothing (even those target objects that might conform highly complex shapes) to guarantee the uniformity of the grasping. It uses a monocular camera, as we are often facing space restrictions that generate the need to use laparoscopic cameras integrated in the tools, to recognize and isolate targets from the background, estimating their spatial coordinates and providing the best possible stable grasping points for both feature and featureless objects. It copes with reflections and shadows produced by light sources (which require extra effort to extract their geometrical properties) in unstructured facilities such as nuclear power plants or particle accelerators on scientific equipment. Based on the experimental results, utilizing a specialized dataset improved the detection of metallic objects in low-contrast environments, resulting in the successful application of the algorithm with error rates in the scale of millimeters in the majority of repeatability and accuracy tests.

show abstract

Section: Monocular Depth Acquisitionmentioning

confidence: 99%

(MARGOT) Monocular Camera-Based Robot Grasping Strategy for Metallic Objects

Veiga Almagro,

Muñoz Orrego,

García González

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…An automated test can be run repeatedly with comparably lower costs with faster speed [3], [4] and fit well with the requirement of an agile software and hardware development process. The recent technological advances in system on chip (SoC) [5], internet of things (IoT) [6], [7], computer vision (CV) [8], cloud computing [9], real-time technology [10], [11] and networked control systems (NCSs) [12] have made the full automation in validation and test industry become possible.…”

Section: Introductionmentioning

confidence: 99%

Advanced UI test automation (AUTA) for BIOS validation using OpenCV and OCR

Mohammed

Mustapa

Rahim

et al. 2021

IJEECS

View full text Add to dashboard Cite

<p>Basic input output system (BIOS) validation is performed on both graphical user interface (GUI) and command-line interface (CLI) by a test engineer. Keyboard and mouse are used to insert test cases commands into system under test (SUT). Test engineer monitors test cases progress on a monitor for validation. This method is time-consuming and relatively more expensive than automation. In this project we designed an independent automation system that able to mimic human interaction in BIOS validation. The approach can be divided into two main parts. The first part is the input device to enter commands into SUT and the second part is the advanced image recognizer. The keyboard and mouse emulator is used as an input device to reproduce test commands and send them to an SUT. The image analyzer algorithm is developed using OpenCV and optical character recognizer (OCR) tools to help automate some test challenges. Our result shows that advanced user interface (UI) test automation (AUTA) can perform a 125 test cases within 5 hours compared to 48 hours for a human to complete the job.</p>

show abstract

Depth image correction for intel realsense depth camera

Cited by 2 publications

References 25 publications

(MARGOT) Monocular Camera-Based Robot Grasping Strategy for Metallic Objects

(MARGOT) Monocular Camera-Based Robot Grasping Strategy for Metallic Objects

Advanced UI test automation (AUTA) for BIOS validation using OpenCV and OCR

Contact Info

Product

Resources

About