Circle Marker Based Distance Measurement Using a Single Camera

Cao, Yu-Tao; Wang, Jianming; Sun, Yukuan; Duan, Xiaojie

doi:10.7763/lnse.2013.v1.80

Cited by 20 publications

(9 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The number of cameras used in some of these studies varies. One study uses a single camera called the triangle similarity for object [18]/marker to distance camera method [19][20][21][22]. Other studies have shown the use of more than one camera, known as a stereo camera [23,24].…”

Section: Research Methods 31 Distance Measurement Systemmentioning

confidence: 99%

Single camera depth control in micro class ROV

2020

View full text Add to dashboard Cite

Navigation is one of the main challenges in an underwater vehicle. To measure and sustain the depth in the micro class remotely operated vehicle (ROV) robot is one of the main demands in the underwater robot competition. There are many sensors that can be used to measure the depth; one of the sensors is using a single camera sensor. In this works, camera-based depth control is developed and evaluated for micro class ROV, namely as fitoplankton SAS ROV. Fitoplankton SAS ROV is a micro ROV prototype with six thrusters. To maintain the depth position, a PID control system with a camera-based depth sensor as the input of the setpoint is used. Moreover, the method for the camera to measure the distance is using the triangle similarity method. In this paper, the experimental scenario is using the rectangular marker to measure the distance, and the value of the depth is processing in the ground control station (GCS). The GCS will send the thruster value to control the depth, which depends on the PID control system. The experiment results show an average of depth accuracy of 95.74% to the depth setpoint.

show abstract

Section: Research Methods 31 Distance Measurement Systemmentioning

confidence: 99%

Single camera depth control in micro class ROV

2020

View full text Add to dashboard Cite

show abstract

“…The approach in [4] uses the principle of similar triangles to calculate the distance between the object and the camera. As simultaneously estimating depth information, our algorithm can directly obtain the distance from the depth of marked points.…”

Section: Distance Estimationmentioning

confidence: 99%

Camera focal length from distances in a single image

Lin

et al. 2021

Vis Comput

View full text Add to dashboard Cite

Camera focal length estimation from a single image is of great importance for many computer vision tasks. Unfortunately, previous methods cannot achieve satisfactory accuracy yet. This paper proposes a focal length estimation approach based on distances among four points in the scene of a single image. The issue is cast into a nonlinear optimization by adapting a standard pinhole camera model under the constraints of distance information. Multiple algorithms are employed to solve the optimization, and the best solution is then regarded as the final solution. Experimental results show that our method is able to obtain a more accurate focal length than some state of the art in a single image setting. In addition, we provide some simple application examples and show the intuitive effects of focal length estimation errors. We also demonstrate experimentally that distance information has an improved meaning for the solution of the focal length.

show abstract

“…Besides the aforementioned approaches, some other works attempted to address this challenging problem by making use of some auxiliary information. Some markerbased methods [2,26] first segmented markers in the image then estimated distance using the marker area and camera parameters. Instead of utilizing markers, Feng et al [8] proposed a model to predict physical distance based on a rectangular pattern, where four image points of a rectangular were needed to compute the camera calibration.…”

Section: Related Workmentioning

confidence: 99%

Learning Object-Specific Distance From a Monocular Image

Zhu

Fang

2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

Environment perception, including object detection and distance estimation, is one of the most crucial tasks for autonomous driving. Many attentions have been paid on the object detection task, but distance estimation only arouse few interests in the computer vision community. Observing that the traditional inverse perspective mapping algorithm performs poorly for objects far away from the camera or on the curved road, in this paper, we address the challenging distance estimation problem by developing the first end-toend learning-based model to directly predict distances for given objects in the images. Besides the introduction of a learning-based base model, we further design an enhanced model with a keypoint regressor, where a projection loss is defined to enforce a better distance estimation, especially for objects close to the camera. To facilitate the research on this task, we construct the extented KITTI and nuScenes (mini) object detection datasets with a distance for each object. Our experiments demonstrate that our proposed methods outperform alternative approaches (e.g., the traditional IPM, SVR) on object-specific distance estimation, particularly for the challenging cases that objects are on a curved road. Moreover, the performance margin implies the effectiveness of our enhanced method.

show abstract

Circle Marker Based Distance Measurement Using a Single Camera

Cited by 20 publications

References 4 publications

Single camera depth control in micro class ROV

Single camera depth control in micro class ROV

Camera focal length from distances in a single image

Learning Object-Specific Distance From a Monocular Image

Contact Info

Product

Resources

About