Review of Stereo Matching Algorithms Based on Deep Learning

Zhou, Kun; Meng, Xiangxi; Cheng, Bo

doi:10.1155/2020/8562323

Cited by 67 publications

(45 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These data enhancement operations help to develop a model that is more robust to light and noise. Similar to PSMNet [ 14 ], the maximum disparity of this paper is set to 192. Specifically, for the Scene Flow data set, training occurred for 10 epochs with a fixed learning rate of 0.001.…”

Section: Resultsmentioning

confidence: 99%

“…The stereo matching algorithm based on the convolution neural network can be divided into two categories [ 14 ]: deep learning methods combined with traditional methods and end-to-end deep learning stereo matching algorithms. The combination of deep learning and a conventional algorithm applies a deep learning algorithm to the steps of a conventional matching algorithm to learn the matching costs, cost aggregation, etc., and reduce the error caused by human design.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A stereo matching algorithm based on the improved PSMNet

Huang

et al. 2021

PLoS ONE

View full text Add to dashboard Cite

Deep learning based on a convolutional neural network (CNN) has been successfully applied to stereo matching. Compared with the traditional method, the speed and accuracy of this method have been greatly improved. However, the existing stereo matching framework based on a CNN often encounters two problems. First, the existing stereo matching network has many parameters, which leads to the matching running time being too long. Second, the disparity estimation is inadequate in some regions where reflections, repeated textures, and fine structures may lead to ill-posed problems. Through the lightweight improvement of the PSMNet (Pyramid Stereo Matching Network) model, the common matching effect of ill-conditioned areas such as repeated texture areas and weak texture areas is solved. In the feature extraction part, ResNeXt is introduced to learn unitary feature extraction, and the ASPP (Atrous Spatial Pyramid Pooling) module is trained to extract multiscale spatial feature information. The feature fusion module is designed to effectively fuse the feature information of different scales to construct the matching cost volume. The improved 3D CNN uses the stacked encoding and decoding structure to further regularize the matching cost volume and obtain the corresponding relationship between feature points under different parallax conditions. Finally, the disparity map is obtained by a regression. We evaluate our method on the Scene Flow, KITTI 2012, and KITTI 2015 stereo datasets. The experiments show that the proposed stereo matching network achieves a comparable prediction accuracy and much faster running speed compared with PSMNet.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A stereo matching algorithm based on the improved PSMNet

Huang

et al. 2021

PLoS ONE

View full text Add to dashboard Cite

show abstract

“…In particular, Deep Learning models now represent the state-ofthe-art for many classical Computer Vision problems. In addition, dense stereo has been formulated as a data-driven learning problem, with approaches that can often exceed the accuracy of legacy algorithm based solutions [33]. In our case, however, most of the time is spent to fit a uniform surface grid to the point cloud, a problem that still needs to also be addressed for deep-learning based dense stereo techniques.…”

Section: Related Workmentioning

confidence: 99%

A Physics-Driven CNN Model for Real-Time Sea Waves 3D Reconstruction

et al. 2021

View full text Add to dashboard Cite

One of the most promising techniques for the analysis of Spatio-Temporal ocean wave fields is stereo vision. Indeed, the reconstruction accuracy and resolution typically outperform other approaches like radars, satellites, etc. However, it is computationally expensive so its application is typically restricted to the analysis of short pre-recorded sequences. What prevents such methodology from being truly real-time is the final 3D surface estimation from a scattered, non-equispaced point cloud. Recently, we studied a novel approach exploiting the temporal dependence of subsequent frames to iteratively update the wave spectrum over time. Albeit substantially faster, the unpredictable convergence time of the optimization involved still prevents its usage as a continuously running remote sensing infrastructure. In this work, we build upon the same idea, but investigating the feasibility of a fully data-driven Machine Learning (ML) approach. We designed a novel Convolutional Neural Network that learns how to produce an accurate surface from the scattered elevation data of three subsequent frames. The key idea is to embed the linear dispersion relation into the model itself to physically relate the sparse points observed at different times. Assuming that the scattered data are uniformly distributed in the spatial domain, this has the same effect of increasing the sample density of each single frame. Experiments demonstrate how the proposed technique, even if trained with purely synthetic data, can produce accurate and physically consistent surfaces at five frames per second on a modern PC.

show abstract

“…We convert the node index into the coordinate of PGM, where grids are considered as boundary points of freespace in wcs. In addition, the boundary points in wcs are back projected into ics through Equation (6). As shown in Figure 7, the red line in the probability grad map is the optimal path and the yellow line is the freespace boundary in ics.…”

Section: Wireless Communications and Mobile Computingmentioning

confidence: 99%

“…In recent years, light detection and ranging (LiDAR) [5], cameras [6], and multisensor fusion technique are adopted to perceive the road environment. In literatures, LiDAR and cameras are devoted to the odometry method, in which the relative motion is estimated by matched points in continuous frames.…”

Section: Introductionmentioning

confidence: 99%

A Road Environment Prediction System for Intelligent Vehicle

Sun

Pei

et al. 2021

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

The road environment prediction is an essential task for intelligent vehicle. In this study, we provide a flexible system that focuses on freespace detection and road environment prediction to host vehicle. The hardware of this system includes two parts: a binocular camera and a low-power mobile platform, which is flexible and portable for a variety of intelligent vehicle. We put forward a multiscale stereo matching algorithm to reduce the computing cost of the hardware unit. Based on disparity space and points cloud, we propose a weighted probability grid map to detect freespace region and a state model to describe the road environment. The experiments show that the proposed system is accurate and robust, which indicates that this technique is fully competent for road environment prediction for intelligent vehicle.

show abstract

Review of Stereo Matching Algorithms Based on Deep Learning

Cited by 67 publications

References 57 publications

A stereo matching algorithm based on the improved PSMNet

A stereo matching algorithm based on the improved PSMNet

A Physics-Driven CNN Model for Real-Time Sea Waves 3D Reconstruction

A Road Environment Prediction System for Intelligent Vehicle

Contact Info

Product

Resources

About