Effective Combination of Vertical and Horizontal Stereo Vision

Kallwies, Jan; Wuensche, Hans-Joachim

doi:10.1109/wacv.2018.00220

Cited by 7 publications

(7 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The appropriate setup can be chosen correctly based on these characteristics, as seen in the real-world experiment where a vertical setup is used due to the nature of the area of interest. In addition to choosing only one setup, the further improvement would be to be able to fuse both vertical and horizontal stereos using the algorithm proposed in [ 16 ]. By increasing the number of mapping agents, in this case, the number of drones, multiple views including the combination of both horizontal and vertical setups can be used.…”

Section: Discussionmentioning

confidence: 99%

Variable Baseline and Flexible Configuration Stereo Vision Using Two Aerial Robots

Sumetheeprasit

Martinez

Paul

et al. 2023

Sensors

View full text Add to dashboard Cite

In this work, a new method for aerial robot remote sensing using stereo vision is proposed. A variable baseline and flexible configuration stereo setup is achieved by separating the left camera and right camera on two separate quadrotor aerial robots. Monocular cameras, one on each aerial robot, are used as a stereo pair, allowing independent adjustment of the pose of the stereo pair. In contrast to conventional stereo vision where two cameras are fixed, having a flexible configuration system allows a large degree of independence in changing the configuration in accordance with various kinds of applications. Larger baselines can be used for stereo vision of farther away targets while using a vertical stereo configuration in tasks where there would be a loss of horizontal overlap caused by a lack of suitable horizontal configuration. Additionally, a method for the practical use of variable baseline stereo vision is introduced, combining multiple point clouds from multiple stereo baselines. Issues from using an inappropriate baseline, such as estimation error induced by insufficient baseline, and occlusions from using too large a baseline can be avoided with this solution.

show abstract

Section: Discussionmentioning

confidence: 99%

Variable Baseline and Flexible Configuration Stereo Vision Using Two Aerial Robots

Sumetheeprasit

Martinez

Paul

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…However, the resulting image from the transformation has image damage at the bottom because the pixel position of the inner circle follows the position of the outer circle, so it is necessary to set the parameters and adjust the image size. In the study used by research [29], they showed differences in stereo cameras with vertical and horizontal configurations where stereo camera with vertical configurations had weaknesses in detecting vertical objects, while stereo camera with horizontal configurations had weaknesses in detecting horizontal objects. As a result of this research, they were able to combine vertical and horizontal disparity images from two camera settings (vertical and horizontal) that captured the same image object.…”

Section: Related Workmentioning

confidence: 99%

Omnidirectional Stereo Vision Study from Vertical and Horizontal Stereo Configuration

Pratama

Dewantara

Pramadihanto³

2022

EMITTER Int'l J. of Engin. Technol.

View full text Add to dashboard Cite

In stereo vision, an omnidirectional camera has high distortion compared to a standard camera, so the camera calibration is very decisive in its stereo matching. In this study, we will perform stereo matching for an omnidirectional camera with vertical and horizontal configuration so that the result of the image's depth has a 360-degree field of view by transforming the image using a calibration-based method. The result is that by using a vertical camera configuration, the image can be stereo matched directly, but by configuring a horizontal image, it is necessary to carry out a different stereo-matching process in each direction. Stereo matching with the semi-global matching method has better image results than block matching with more image objects detectable by the semi-global block matching method with a maximum disparity value of 32 pixels and with a window size of 21 pixels.

show abstract

“…In [26], the fusion was applied after computing the Sum of Squared Distances (SSD) of images. More recently, authors in [17,18] extended the standard two-view stereo to a three-view setup by adding a camera on top of the left one. This L-shape configuration creates a vertical and a horizontal baseline.…”

Section: Related Workmentioning

confidence: 99%

“…To the best of our knowledge, the proposed model is the first that processes the multi-baseline trinocular setting in an end-to-end deep learning-based manner. The previous multi-baseline stereo works [16][17][18] rely on traditional stereo approaches.…”

Section: Introductionmentioning

confidence: 99%

TriStereoNet: A Trinocular Framework for Multi-baseline Disparity Estimation

Shamsafar¹,

Zell²

2021

Preprint

View full text Add to dashboard Cite

Stereo vision is an effective technique for depth estimation with broad applicability in autonomous urban and highway driving. While various deep learning-based approaches have been developed for stereo, the input data from a binocular setup with a fixed baseline are limited. Addressing such a problem, we present an end-to-end network for processing the data from a trinocular setup, which is a combination of a narrow and a wide stereo pair. In this design, two pairs of binocular data with a common reference image are treated with shared weights of the network and a mid-level fusion. We also propose a Guided Addition method for merging the 4D data of the two baselines. Additionally, an iterative sequential selfsupervised and supervised learning on real and synthetic datasets is presented, making the training of the trinocular system practical with no need to ground-truth data of the real dataset. Experimental results demonstrate that the trinocular disparity network surpasses the scenario where individual pairs are fed into a similar architecture. Code and dataset: https://github.com/cogsystuebingen/tristereonet.

show abstract

Effective Combination of Vertical and Horizontal Stereo Vision

Cited by 7 publications

References 17 publications

Variable Baseline and Flexible Configuration Stereo Vision Using Two Aerial Robots

Variable Baseline and Flexible Configuration Stereo Vision Using Two Aerial Robots

Omnidirectional Stereo Vision Study from Vertical and Horizontal Stereo Configuration

TriStereoNet: A Trinocular Framework for Multi-baseline Disparity Estimation

Contact Info

Product

Resources

About