Real-Time Subpixel Fast Bilateral Stereo

  title={Real-Time Subpixel Fast Bilateral Stereo},
  author={Rui Fan and Yanan Liu and Mohammud Junaid Bocus and Ming Liu},
  journal={2018 IEEE International Conference on Information and Automation (ICIA)},
  • Rui FanYanan Liu Ming Liu
  • Published 5 July 2018
  • Computer Science
  • 2018 IEEE International Conference on Information and Automation (ICIA)
Stereo vision technique has been widely used in robotic systems to acquire 3-D information. In recent years, many researchers have applied bilateral filtering in stereo vision to adaptively aggregate the matching costs. This has greatly improved the accuracy of the estimated disparity maps. However, the process of filtering the whole cost volume is very time consuming and therefore the researchers have to resort to some powerful hardware for the real-time purpose. This paper presents the… 

Figures from this paper

Real-Time Stereo Vision for Road Surface 3-D Reconstruction

This paper presents a real-time stereo vision system used for road surface 3- D reconstruction developed from the previously published 3-D reconstruction algorithm where the perspective view of the target image is first transformed into the reference view, which increases the disparity accuracy but also improves the processing speed.

Real-Time Binocular Vision Implementation on an SoC TMS320C6678 DSP

An efficient binocular vision system implemented on an SoC TMS320C6678 DSP for real-time depth information extrapolation, where the search range propagates from the bottom of an image to its top, to improve the stereo matching efficiency.

Computer Stereo Vision for Autonomous Driving

This chapter introduces both the hardware and software aspects of computer stereo vision for autonomous car systems and discusses four autonomous car perception tasks, including 1) visual feature detection, description and matching, 2) 3D information acquisition, 3) object detection/recognition and 4) semantic image segmentation.

A Novel Disparity Transformation Algorithm for Road Segmentation

Multiple Lane Detection Algorithm Based on Optimised Dense Disparity Map Estimation

  • Han MaYixin Ma Rui Fan
  • Computer Science, Business
    2018 IEEE International Conference on Imaging Systems and Techniques (IST)
  • 2018
A multiple lane detection algorithm developed based on optimised dense disparity map estimation, where the disparity information obtained at time t_{n} is utilised to optimise the process of disparity estimation at time $t_{n+1}(n \ge 0)$.

Rethinking Road Surface 3-D Reconstruction and Pothole Detection: From Perspective Transformation to Disparity Map Segmentation

An efficient pothole detection algorithm based on road disparity map estimation and segmentation that achieves state-of-the-art accuracy and efficiency is presented.

A Robust Roll Angle Estimation Algorithm Based on Gradient Descent

To achieve greater computational efficiency, the presented roll angle estimation method takes fewer iterations to achieve the same precision as the previous method, and utilizes gradient descent to optimize the aforementioned global energy.

Robust Lane Marking Detection Algorithm Using Drivable Area Segmentation and Extended SLT

In this paper, a robust lane detection algorithm is proposed, where the vertical road profile of the road is estimated using dynamic programming from the v-disparity map and, based on the estimated

Computer-Aided Road Inspection: Systems and Algorithms

The most common road damage types are compared and 2-D/3-D road imaging systems are discussed and state-of-the-art machine vision and intelligence-based road damage detection algorithms are introduced.

Road crack detection using deep convolutional neural network

Quantitative evaluation conducted on a data set of 500 images of size 3264 χ 2448, collected by a low-cost smart phone, demonstrates that the learned deep features with the proposed deep learning framework provide superior crack detection performance when compared with features extracted with existing hand-craft methods.



Real-time implementation of stereo vision based on optimised normalised cross-correlation and propagated search range on a GPU

  • Rui FanN. Dahnoun
  • Computer Science
    2017 IEEE International Conference on Imaging Systems and Techniques (IST)
  • 2017
An efficient stereo matching algorithm is implemented on a state-of-the-art GPU to achieve highly accurate disparity maps in real time for various autonomous vehicle applications.

On building an accurate stereo matching system on graphics hardware

This paper presents a GPU-based stereo matching system with good performance in both accuracy and speed, and is the top performer in the Middlebury benchmark, and the results are achieved on GPU within 0.1 seconds.

High-accuracy stereo depth maps using structured light

  • Daniel ScharsteinR. Szeliski
  • Computer Science
    2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings.
  • 2003
A method for acquiring high-complexity stereo image pairs with pixel-accurate correspondence information using structured light that does not require the calibration of the light sources and yields registered disparity maps between all pairs of cameras and illumination projectors.

Real-Time Stereo Vision for Resource Limited Systems

Overall, this work aims to organize existing efforts and encourage new ones in the development of stereo vision algorithms for resource limited systems through a review of the status quo as well as providing both software and hardware designs of new stereo Vision algorithms that offer an efficient tradeoff between speed and accuracy.

Efficient Sampling of Disparity Space for Fast And Accurate Matching

  • Jan CechR. Sára
  • Computer Science
    2007 IEEE Conference on Computer Vision and Pattern Recognition
  • 2007
A simple stereo matching algorithm is proposed that visits only a small fraction of disparity space in order to find a semi-dense disparity map by growing from a small set of correspondence seeds, which is very unlike the existing growing algorithms which are fast but erroneous.

Fast cost-volume filtering for visual correspondence and beyond

This paper proposes a generic and simple framework comprising three steps: constructing a cost volume, fast cost volume filtering and winner-take-all label selection, and achieves state-of-the-art results that achieve disparity maps in real-time, and optical flow fields with very fine structures as well as large displacements.

Road Surface 3D Reconstruction Based on Dense Subpixel Disparity Map Estimation

A novel dense subpixel disparity estimation algorithm with high computational efficiency and robustness is proposed by first transforming the perspective view of the target frame into the reference view, which not only increases the accuracy of the block matching for the road surface but also improves the processing speed.

Stereo Matching with Color-Weighted Correlation, Hierarchical Belief Propagation, and Occlusion Handling

A stereo matching algorithm with careful handling of disparity, discontinuity, and occlusion based on an energy-minimization framework that is evaluated on the Middlebury data sets, showing that the algorithm is the top performer among all the algorithms listed there.

Robust correspondence recognition for computer vision

This paper introduces constraint satisfaction framework suitable for the task of finding correspondences in computer vision based on a robust modification of graph-theoretic notion known as digraph kernel.

Real-time stereo vision-based lane detection system

A proposed lane detection system is developed from the previous work where the estimation of the dense vanishing point is further improved using the disparity information, and a novel lane position validation approach which computes the energy of each possible solution and selects all satisfying lane positions for visualisation is proposed.