Review of stereo vision algorithms and their suitability for resource-limited systems

Tippetts, Beau; Lee, Dah Jye; Lillywhite, Kirt; Archibald, James K.

doi:10.1007/s11554-012-0313-2

Cited by 233 publications

(131 citation statements)

References 135 publications

Supporting

Mentioning

126

Contrasting

Order By: Relevance

“…Pairs of images consisting of 320x240 pixels are used as test inputs; A cup is placed on a partition and bookshelves are ignored as background in the correlation process since it is beyond the range of consideration. We use SAD (sum of absolute differences) algorithm since it is simple and has linear data flow patterns to be processed all in parallel [4,5]. For the experiments we set the maximum disparity to 128 with the window size of 3x3.…”

Section: Methodsmentioning

confidence: 99%

A Block-based 3D Map: a Crude Sketch of Steric Environment

Kim

2014

IJMUE

View full text Add to dashboard Cite

show abstract

Section: Methodsmentioning

confidence: 99%

A Block-based 3D Map: a Crude Sketch of Steric Environment

Kim

2014

IJMUE

View full text Add to dashboard Cite

show abstract

“…A large body of research has been devoted to the scenario which assumes that images have been rectified so that the problem can be reduced to finding correspondences between a pair of scanlines, see reviews [3] [4]. Image rectification has been mainly focused on addressing global distortions associated with camera rotation and translation, and lens distortions.…”

Section: Related Workmentioning

confidence: 99%

Evolutionary Algorithm for Dense Pixel Matching in Presence of Distortions

dos-Santos-Paulino

Nebel

Flórez-Revuelta

2014

Applications of Evolutionary Computation

View full text Add to dashboard Cite

Abstract. Dense pixel matching is an essential step required by many computer vision applications. While a large body of work has addressed quite successfully the rectified scenario, accurate pixel correspondence between an image and a distorted version remains very challenging. Exploiting an analogy between sequences of genetic material and images, we propose a novel genetics inspired algorithm where image variability is treated as the product of a set of image mutations. As a consequence, correspondence for each scanline of the initial image is formulated as the optimisation of a path in the second image minimising a fitness function penalising mutations. This optimisation is performed by a evolutionary algorithm which, in addition to provide fast convergence, implicitly ensures consistency between successive scanlines. Performance evaluation on locally and globally distorted images validates our bio-inspired approach.

show abstract

“…and meet these constraints for producing a viable embedded stereo matching system. Thorough analysis of the existing literature shows that, despite having low-error rate in the disparity computation, state-of-the-art DSPs can not support global stereo matching algorithms due to intensive computational needs [2], [3]. A viable alternative to this could be GPU-based implementations but at the expense of high cost and power-consumption for real-time designs [4].…”

Section: Introductionmentioning

confidence: 99%

High-Speed Low-Complexity Guided Image Filtering-Based Disparity Estimation

Vala

Immadisetty

Acharyya

et al. 2018

IEEE Trans. Circuits Syst. I

View full text Add to dashboard Cite

Abstract-Stereo vision is a methodology to obtain depth in a scene based on the stereo image pair. In this paper we introduce a Discrete Wavelet Transform (DWT) based methodology for a state-of-the-art disparity estimation algorithm, that resulted in significant performance improvement in terms of speed and computational complexity. In the initial stage of the proposed algorithm, we apply DWT to the input images, reducing the number of samples to be processed in subsequent stages by 50%, thereby decreasing computational complexity and improving processing speed. Subsequently the architecture has been designed based on this proposed methodology and prototyped on a Xilinx Virtex-7 FPGA. The performance of the proposed methodology has been evaluated against four standard Middlebury Benchmark image pairs viz. Tsukuba, Venus, Teddy and Cones. The proposed methodology results in improvement of about 44.4% cycles per frame, 52% frames per second and 61.5% and 59.6% LUT and register utilization respectively, compared with state-of-the-art designs.

show abstract

Review of stereo vision algorithms and their suitability for resource-limited systems

Cited by 233 publications

References 135 publications

A Block-based 3D Map: a Crude Sketch of Steric Environment

A Block-based 3D Map: a Crude Sketch of Steric Environment

Evolutionary Algorithm for Dense Pixel Matching in Presence of Distortions

High-Speed Low-Complexity Guided Image Filtering-Based Disparity Estimation

Contact Info

Product

Resources

About