Local stereo matching algorithm with efficient matching cost and adaptive guided image filter

Zhu, Shiping; Yan, Liang

doi:10.1007/s00371-016-1264-6

Cited by 31 publications

(25 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Figure 7 shows the left image of the aloe data under three different illuminations (no exposure variation) and with three different exposure settings (no illumination change). In this paper, three widely used cost computation methods were considered for comparison, including a function combining the sum of absolute difference (SAD) and gradient [6], a function combining absolute difference (AD) with census transform [14] and a combination of absolute difference, gradient, and Census transform [15]. To highlight the preference of cost computation function, all disparity maps were computed with the same cost aggregation algorithm proposed in Section 2.2 and no further refinement was applied.…”

Section: Evaluation Of the Robustness To The Illumination And Exposurmentioning

confidence: 99%

“…Mei et al [14] combined the absolute differences and Census transform to achieve an impressive performance. In [15][16][17], a combination of absolute difference, gradient and census transform or the variant versions were used for initial cost computation. The combination of multiple matching costs provides an alternative way to improve the performance of stereo matching algorithms.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Improved Cost Computation and Adaptive Shape Guided Filter for Local Stereo Matching of Low Texture Stereo Images

et al. 2020

View full text Add to dashboard Cite

Dense stereo matching has been widely used in photogrammetry and computer vision applications. Even though it has a long research history, dense stereo matching is still challenging for occluded, textureless and discontinuous regions. This paper proposed an efficient and effective matching cost measurement and an adaptive shape guided filter-based matching cost aggregation method to improve the stereo matching performance for large textureless regions. At first, an efficient matching cost function combining enhanced image gradient-based matching cost and improved census transform-based matching cost is introduced. This proposed matching cost function is robust against radiometric variations and textureless regions. Following this, an adaptive shape cross-based window is constructed for each pixel and a modified guided filter based on this adaptive shape window is implemented for cost aggregation. The final disparity map is obtained after disparity selection and multiple steps disparity refinement. Experiments were conducted on the Middlebury benchmark dataset to evaluate the effectiveness of the proposed cost measurement and cost aggregation strategy. The experimental results demonstrated that the average matching error rate on Middlebury standard image pairs is 9.40%. Compared with the traditional guided filter-based stereo matching method, the proposed method achieved a better matching result in textureless regions.

show abstract

Section: Evaluation Of the Robustness To The Illumination And Exposurmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Improved Cost Computation and Adaptive Shape Guided Filter for Local Stereo Matching of Low Texture Stereo Images

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Step 3: Select the neighboring intraframe modes [24][25][26] by step 1 according to the modes in list L4 to constitute list L5={11, 13,15,17,19}. Calculate the SATD of each mode in list L5 in like manner, and select five modes with the smallest SATD from list L4 and list L5 to constitute list L6.…”

Section: Optimization Algorithm Based On Three-step Searchmentioning

confidence: 99%

The Study on Decision Tree Classification and Three-Step Search Algorithm Based Compression Technology for High Efficiency Video Coding

Liu¹

2018

Proceedings of the 2018 8th International Conference on Management, Education and Information (MEICI 2018)

View full text Add to dashboard Cite

The new generation video coding algorithm HEVC reduces the bitrate by half compared to the previous standard H.264 with the same video quality, but this also brings the increasing of encoding time. In this paper, we mainly improve the intra frame prediction to solve this question: Combined with the decision tree method in machine learning, the reference pixel smoothing characteristics of the prediction unit of each partition mode are quickly determined, and some intra modes with the same prediction result are adaptively skipped, which greatly saves coding time. Experimental results show that the proposed decision tree and three-step search based intra prediction algorithm achieves better performance compared with the HM15.0 encoder. The BD-Rate is increased by 1.19%, the BD-PSNR is decreased by 0.058dB, and the encoding time is reduced by 37.87% on average.

show abstract

“…Generally, stereo matching algorithms can be divided into two categories: conventional algorithms and deep learningbased algorithms. Specifically, conventional stereo matching algorithms can be subdivided into global stereo matching [4], local stereo matching [5][6][7], and semi-global stereo matching [8]. The effect of global stereo matching depends on accuracy of matching cost, and the calculation process is very slow as the disparity is solved by global energy function.…”

Section: Introductionmentioning

confidence: 99%

A simplified ICA-based local similarity stereo matching

2020

View full text Add to dashboard Cite

Since the existing stereo matching methods may fail in the regions of non-textures, boundaries and tiny details, a simplified independent component correlation algorithm (ICA)-based local similarity stereo matching algorithm is proposed. In order to improve the DispNetC, the proposed algorithm first offers the simplified independent component correlation algorithm (SICA) cost aggregation. Then, the algorithm introduces the matching cost volume pyramid, which simplifies the preprocessing process for the ICA. Also, the SICA loss function is defined. Next, the region-wise loss function combined with the pixel-wise loss function is defined as a local similarity loss function to improve the spatial structure of the disparity map. Finally, the SICA loss function is combined with the local similarity loss function, which is defined to estimate the disparity map and to compensate the edge information of the disparity map. Experimental results on KITTI dataset show that the average absolute error of the proposed algorithm is about 37% lower than that of the DispNetC, and its runtime consuming is about 0.6 s lower than that of GC-Net.

show abstract

Local stereo matching algorithm with efficient matching cost and adaptive guided image filter

Cited by 31 publications

References 33 publications

Improved Cost Computation and Adaptive Shape Guided Filter for Local Stereo Matching of Low Texture Stereo Images

Improved Cost Computation and Adaptive Shape Guided Filter for Local Stereo Matching of Low Texture Stereo Images

The Study on Decision Tree Classification and Three-Step Search Algorithm Based Compression Technology for High Efficiency Video Coding

A simplified ICA-based local similarity stereo matching

Contact Info

Product

Resources

About