Optical flow estimation on coarse-to-fine region-trees using discrete optimization
Abstract
In this paper, we propose a new region-based method for accurate motion estimation using discrete optimization. In particular, the input image is represented as a tree of over-segmented regions and the optical flow is estimated by optimizing an energy function defined on such a region-tree using dynamic programming. To accommodate the sampling-inefficiency problem intrinsic to discrete optimization compared to the continuous optimization based methods, both spatial and solution domain coarse-to-fine (C2F) strategies are used. That is, multiple region-trees are built using different over-segmentation granularities. Starting from a global displacement label discretization, optical flow estimation on the coarser level region-tree is used for defining region-wise finer displacement samplings for finer level region-trees. Furthermore, cross-checking based occlusion detection and correction and continuous optimization are also used to improve accuracy. Extensive experiments using the Middlebury benchmark datasets have shown that our proposed method can produce top-ranking results.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
DPOF's qualitative results on the Schefflera and Grove sequences show relatively good results around motion boundaries.
“The qualitative results obtained by DPOF on the Schefflera and Grove sequences in Fig. 8 show relatively good results around motion boundaries, supporting this conclusion.”
From A Database and Evaluation Methodology for Optical Flow (2011) · cites this paper as Lei and Yang 2009
The combination of segmentation and discrete optimization in DPOF is beneficial for avoiding outliers, but the continuous refinement is perhaps not as sophisticated as recent purely continuous algorithms.
“The variation of the results across the measures indicates that the combination of segmentation and discrete optimization is beneficial in terms of avoiding outliers, but that perhaps the continuous refinement is not as sophisticated as recent purely continuous algorithms.”
From A Database and Evaluation Methodology for Optical Flow (2011) · cites this paper as Lei and Yang 2009
DPOF (Lei and Yang 2009) is a segmentation-based discrete optimization algorithm followed by a continuous refinement.
“DPOF (Lei and Yang 2009) is a segmentation-based discrete optimization algorithm, followed by a continuous refinement (Sect. 2.4.2).”
From A Database and Evaluation Methodology for Optical Flow (2011) · cites this paper as Lei and Yang 2009
DPOF (Lei and Yang 2009) improves dramatically from R0.5 to R2.0.
“the performance of DPOF (Lei and Yang 2009) improves dramatically from R0.5 to R2.0”
From A Database and Evaluation Methodology for Optical Flow (2011) · cites this paper as Lei and Yang 2009
DPOF (Lei and Yang 2009) is a possible exception to the oversmoothing of motion discontinuities.
“A possible exception is DPOF (Lei and Yang 2009).”
From A Database and Evaluation Methodology for Optical Flow (2011) · cites this paper as Lei and Yang 2009
DPOF (Lei and Yang 2009) improves similarly from A50 to A95.
“and similarly from A50 to A95.”
From A Database and Evaluation Methodology for Optical Flow (2011) · cites this paper as Lei and Yang 2009
DPOF is good at avoiding gross outliers but relatively weak at obtaining high accuracy.
“This trend indicates that DPOF is good at avoiding gross outliers but is relatively weak at obtaining high accuracy.”
From A Database and Evaluation Methodology for Optical Flow (2011) · cites this paper as Lei and Yang 2009
DPOF (Lei and Yang 2009) involves segmentation.
“DPOF (Lei and Yang 2009), which involves segmentation”
From A Database and Evaluation Methodology for Optical Flow (2011) · cites this paper as Lei and Yang 2009
Algorithms such as CBF and DPOF, which are relatively robust but not so accurate, perform worse in terms of R2.5 than they do in terms of R5.0 and R10.0.
“Algorithms such as CBF (Trobin et al. 2008) and DPOF (Lei and Yang 2009), which are relatively robust but not so accurate (compare the performance of these algorithms for R0.5 and R2.0 in Fig. 9), therefore perform worse in terms of R2.5 than they do in terms of R5.0 and R10.0.”
From A Database and Evaluation Methodology for Optical Flow (2011) · cites this paper as Lei and Yang 2009
DPOF (Lei and Yang 2009) performs particularly poorly on Yosemite.
“does particular poorly on Yosemite”
From A Database and Evaluation Methodology for Optical Flow (2011) · cites this paper as Lei and Yang 2009
Only a few algorithms (e.g., DPOF, Fusion, and Dynamic MRF) perform well in this region.
“Only a few algorithms (e.g., DPOF-Lei and Yang 2009, Fusion-Lempitsky et al. 2008, and Dynamic MRF-Glocker et al. 2008) perform well in this region.”
From A Database and Evaluation Methodology for Optical Flow (2011) · cites this paper as Lei and Yang 2009
DPOF (Lei and Yang 2009) performs best on Grove.
“DPOF (Lei and Yang 2009), which involves segmentation and performs best on Grove”
From A Database and Evaluation Methodology for Optical Flow (2011) · cites this paper as Lei and Yang 2009
DPOF obtains the best flow results on the Teddy sequence with an average endpoint error of 0.5 pixels, whereas CBF is the 9th best with an average endpoint error of 0.76 pixels.
“DPOF obtains the best flow results with an average endpoint error of 0 . 5 pixels, whereas CBF is the 9th best with an average endpoint error of 0 . 76 pixels.”
From A Database and Evaluation Methodology for Optical Flow (2011) · cites this paper as Lei and Yang 2009
DPOF's poor performance on Yosemite is presumably because segmenting the grayscale Yosemite sequence is difficult.
“presumably because segmenting the grayscale Yosemite sequence is difficult.”
From A Database and Evaluation Methodology for Optical Flow (2011) · cites this paper as Lei and Yang 2009
CBF obtains the best interpolation error results on the Teddy sequence with an average interpolation error of 5.21 graylevels, whereas DPOF is 6th best with an average interpolation error of 5.58 graylevels.
“CBF obtains the best interpolation error results with an average interpolation error of 5 . 21 graylevels, whereas DPOF is 6th best with an average interpolation error of 5 . 58 graylevels.”
From A Database and Evaluation Methodology for Optical Flow (2011) · cites this paper as Lei and Yang 2009
Cites
Fast approximate energy minimization via graph cuts
Boykov, Y., Veksler, O., & Zabih, R. (2001) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.969114 · Cited by 6,988 · see citing works
FusionFlow: Discrete-continuous optimization for optical flow estimation
Lempitsky, V., Roth, S., & Rother, C. (2008) · 2008 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2008.4587751 · Cited by 145 · see citing works
Optical flow estimation with uncertainties through dynamic MRFs
Glocker, B., Paragios, N., Komodakis, N., Tziritas, G., & Navab, N. (2008) · 2008 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2008.4587562 · Cited by 69 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
A Database and Evaluation Methodology for Optical Flow
Baker, S., Scharstein, D., Lewis, J. P., Roth, S., Black, M. J., & Szeliski, R. (2011) · International Journal of Computer Vision · doi:10.1007/s11263-010-0390-2 · Cited by 2,205 · see citing works
“DPOF ( Lei and Yang 2009 ), which involves segmentation and performs best on Grove, does particular poorly on Yosemite presumably because segmenting the grayscale Yosemite sequence is difficult.”
BackgroundMethodInfluentialSecrets of optical flow estimation and their principles
Sun, D., Roth, S., & Black, M. J. (2010) · 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2010.5539939 · Cited by 1,656 · see citing works
Large Displacement Optical Flow: Descriptor Matching in Variational Motion Estimation
Brox, T., & Malik, J. (2011) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2010.143 · Cited by 1,295 · see citing works
Fast cost-volume filtering for visual correspondence and beyond
Hosni, A., Rhemann, C., Bleyer, M., Rother, C., & Gelautz, M. (2011) · Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2011.5995372 · Cited by 1,193 · see citing works
“Such a model has been shown to be robust to illumination changes and is commonly used in optical flow estimation [29], [43]:”
Sun, D., Roth, S., & Black, M. J. (2013) · International Journal of Computer Vision · doi:10.1007/s11263-013-0644-x · Cited by 698 · see citing works
“…(Nagel and Enkelmann 1986; Sun et al. 2008; Wedel et al. 2009; Zimmer et al. 2011, 2009), rigidity constraints (Wedel et al. 2008a, 2009), an over-parameterized smoothness term (Nir et al. 2008), or image segmentation (Black and Jepson 1996; Lei and Yang 2009; Xu et al. 2008; Zitnick et al. 2005).”
BackgroundMotion detail preserving optical flow estimation
Xu, L., Jia, J.-Y., & Matsushita, Y. (2010) · 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2010.5539820 · Cited by 193 · see citing works
“Segmentation information was incorporated to regularize flow estimates in [19], [24], [41].”
MethodLu, J.-B., Yang, H., Min, D., & Do, M. (2013) · 2013 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2013.242 · Cited by 175 · see citing works
Robust Monocular Epipolar Flow Estimation
Yamaguchi, K., McAllester, D. A., & Urtasun, R. (2013) · 2013 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2013.243 · Cited by 136 · see citing works
Dense, accurate optical flow estimation with piecewise parametric model
Yang, J., & Li, H. (2015) · Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2015.7298704 · Cited by 128 · see citing works
“Lei and Yang [27] represent the image with region-tree built from color segmentation; constant flow vector is computed for each region.”
BackgroundExploiting Semantic Information and Deep Matching for Optical Flow
Bai, M., Luo, W., Kundu, K., & Urtasun, R. (2016) · European Conference on Computer Vision · doi:10.1007/978-3-319-46466-4_10 · Cited by 127 · see citing works
Joint Recovery of Dense Correspondence and Cosegmentation in Two Images
Taniai, T., Sinha, S. N., & Sato, Y. (2016) · Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2016.460 · Cited by 125 · see citing works
“To exploit multi-scale image cues or to add flexible regularization, hierarchical conditional random fields (CRFs) have been proposed for single image segmentation [22], image matching [49], stereo correspondence [33], and much recently for optic flow [34, 27] and more general correspondence estimation [29, 23].”
MethodLearning Dense and Continuous Optical Flow From an Event Camera
Wan, Z., Dai, Y., & Mao, Y.-X. (2022) · IEEE Transactions on Image Processing · doi:10.1109/tip.2022.3220938 · Cited by 118 · see citing works
“Note that the discrete flow in our paper is defined in the temporal domain, and it is different from the discrete flow defined in the previous two-frame-based approaches [46], [47], which represents estimating optical flow by discrete optimization.”
BackgroundREal-time local stereo matching using guided image filtering
Hosni, A., Bleyer, M., Rhemann, C., Gelautz, M., & Rother, C. (2011) · IEEE International Conference on Multimedia and Expo · doi:10.1109/icme.2011.6012131 · Cited by 92
“It has been shown to be robust to illumination changes and is commonly used in optical flow estimation [16,17].”
BackgroundDeformable image registration by combining uncertainty estimates from supervoxel belief propagation
Heinrich, M., Simpson, I. J. A., Papież, B., Brady, M., & Schnabel, J. (2016) · Medical Image Anal. · doi:10.1016/j.media.2015.09.005 · Cited by 72 · see citing works
Bootstrap optical flow confidence and uncertainty measure
Kybic, J., & Nieuwenhuis, C. (2011) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2011.06.008 · Cited by 53 · see citing works
“On the other hand, our method would need to be modified for the third best algorithm [28] which represents the image as a tree of over-segmented regions.”
MethodConstrained Optical Flow Estimation as a Matching Problem
Mozerov, M. (2013) · IEEE Transactions on Image Processing · doi:10.1109/tip.2013.2244221 · Cited by 49 · see citing works
Learning Pixel Trajectories with Multiscale Contrastive Random Walks
Bian, Z., Jabri, A., Efros, A. A., & Owens, A. (2022) · Computer Vision and Pattern Recognition · doi:10.1109/cvpr52688.2022.00640 · Cited by 47 · see citing works
“Cycle consistency has long been used to detect occlusions [3,23,36,66,80], and is used to discount the loss of occluded pixels in unsupervised flow [25,28, 32,”
MethodSparsity model for robust optical flow estimation at motion discontinuities
Shen, X.-H., & Wu, Y. (2010) · 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2010.5539944 · Cited by 44
“[15] also proposed a new energy function based on discrete optimization.”
BackgroundSimultaneous Segmentation and Multiresolution Nonrigid Atlas Registration
Gass, T., Székely, G., & Goksel, O. (2014) · IEEE Transactions on Image Processing · doi:10.1109/tip.2014.2322447 · Cited by 43
PatchMatch Filter: Edge-Aware Filtering Meets Randomized Search for Visual Correspondence
Lu, J.-B., Li, Y., Yang, H., Min, D., Eng, W., & Do, M. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2616391 · Cited by 35 · see citing works
Sparse Camera Network for Visual Surveillance -- A Comprehensive Survey
Song, M.-L., Tao, D., & Maybank, S. (2013) · arXiv.org · doi:10.48550/arxiv.1302.0446 · Cited by 33 · see citing works
“To improve the accuracy and robustness of optical flow computation, Lei and Yang [58] presented a coarse-to-fine region tree-based model by treating the input image as a tree of over-segmented regions; the optical flow is estimated based on this region-tree using dynamic programming.”
BackgroundMethodOPTICAL FLOW FOR GLACIER MOTION ESTIMATION
Vogel, C., Bauder, A., & Schindler, K. (2012) · ISPRS annals of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprsannals-i-3-359-2012 · Cited by 28 · see citing works
“Notable exceptions are (Lei and Yang, 2009, Lempitsky et al., 2008).”
BackgroundA new multiview spacetime-consistent depth recovery framework for free viewpoint video rendering
Lei, C., Chen, X.-D., & Yang, H. (2009) · IEEE International Conference on Computer Vision · doi:10.1109/iccv.2009.5459357 · Cited by 28
Self-citationObservation Model Based on Scale Interactions for Optical Flow Estimation
Zille, P., Corpetti, T., Shao, L., & Chen, X. (2014) · IEEE Transactions on Image Processing · doi:10.1109/tip.2014.2328893 · Cited by 20
Hierarchical Scan-Line Dynamic Programming for Optical Flow Using Semi-Global Matching
Hermann, S., & Klette, R. (2012) · ACCV Workshops · doi:10.1007/978-3-642-37484-5_45 · Cited by 20 · see citing works
“Lei and Yang [12] also propose a coarse-to-fine concept for a discrete optimization technique.”
BackgroundSoft Cost Aggregation with Multi-resolution Fusion
Tan, X., Sun, C., Wang, D., Guo, Y., & Pham, T. (2014) · European Conference on Computer Vision · doi:10.1007/978-3-319-10602-1_2 · Cited by 19 · see citing works
“The balance between low resolution and high resolution is found by incorporating the multi-resolution or coarse-to-fine methods into an optimization framework [4,7,19].”
BackgroundTewari, N., Singh, P., Vohra, R., Langridge, B., Onida, S., Davies, A., Goodall, R., Lane, T., Shalhoub, J., Kwikiriza, G., et al. (2019) · International Conference on e-Business · doi:10.1002/bjs.11340 · Cited by 16
Quaternion based optical flow estimation for robust object tracking
Chen, E.-K., Xu, Y., Yang, X.-K., & Zhang, W.-J. (2013) · Digit. Signal Process. · doi:10.1016/j.dsp.2012.07.017 · Cited by 15
Self-Supervised Any-Point Tracking by Contrastive Random Walks
Shrivastava, A., & Owens, A. (2024) · European Conference on Computer Vision · doi:10.48550/arxiv.2409.16288 · Cited by 14
“Other methods have used cycle-consistency to detect occlusions [1,18,26,38], such as within unsupervised flow models [20,22,47,57].”
MethodOn the effectiveness of handcrafted features for deepfake video detection
Kaddar, B., Fezza, S. A., Hamidouche, W., Akhtar, Z., Hadid, A., Serra-Sagrista, J. S., Hernández-Cabronero, M., & Sanchez, V. (2023) · Journal of Electronic Imaging · doi:10.1117/1.jei.32.5.053033 · Cited by 15 · see citing works
“63,64 75 Let C nc be a facial image component and w ð n Þ ¼ ð h ð n Þ ; v ð n Þ Þ ∶ w ð n Þ → R 2 be the optical flow field computed over two successive facial image component, C n c and C n þ 1 c , where h ð n Þ v ð n Þ are the optical flow in the horizontal and vertical directions, respectively.”
Low complexity optical flow using neighbor-guided semi-global matching
Xiang, J., Li, Z., Blaauw, D., Kim, H.-S., & Chakrabarti, C. (2016) · International Conference on Information Photonics · doi:10.1109/icip.2016.7533208 · Cited by 12 · see citing works
Hierarchically-constrained optical flow
Kennedy, R., & Taylor, C. J. (2015) · Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2015.7298955 · Cited by 11 · see citing works
“Other related hierarchical methods for image matching include [33, 20, 17], although these methods are still approximate.”
Superpixel-based large displacement optical flow
Chang, H.-S., & Wang, Y. (2013) · 2013 IEEE International Conference on Image Processing · doi:10.1109/icip.2013.6738790 · Cited by 11 · see citing works
“Instead of relying on variational models, superpixel-based approaches have been recently proposed in [6, 7] for improved estimation.”
MethodXu, C., Xu, L., Zhang, H.-Y., Zhang, Y.-P., Du, X., & Li, S. (2018) · Computing · doi:10.1007/s00607-018-0675-9 · Cited by 10 · see citing works
“It using the pyramid-based coarse-to-fine scheme to achieve better performance [19].”
Yang, L., Liu, J.-Z., & Tang, X.-O. (2015) · IEEE Transactions on Image Processing · doi:10.1109/tip.2015.2397591 · Cited by 10
“We employ a commonly used cost function that has shown robust capacity for stereo and optical flow [17]–[19].”
MethodDetermining shape and motion from monocular camera: A direct approach using normal flows
Hui, T., & Chung, R. (2015) · Pattern Recognition · doi:10.1016/j.patcog.2014.08.012 · Cited by 8 · see citing works
Liang, M., Du, J.-P., & Liu, H.-G. (2013) · Mathematical Problems in Engineering · doi:10.1155/2013/745752 · Cited by 8 · see citing works
Multi-Exposure Motion Estimation Based on Deep Convolutional Networks
Xie, Z., Guo, Y.-C., Zhang, S.-H., Zhang, W.-J., & Ma, L.-Z. (2018) · Journal of Computational Science and Technology · doi:10.1007/s11390-018-1833-4 · Cited by 6 · see citing works
Li, Z., Xiang, J., Gong, L., Blaauw, D., Chakrabarti, C., & Kim, H.-S. (2019) · IEEE transactions on circuits and systems for video technology (Print) · doi:10.1109/tcsvt.2018.2854284 · Cited by 5 · see citing works
“Therefore, it is typical to employ a coarse-tofine approach [12], [13] for estimating large optical flow displacements.”
MethodDeep Semantic Matching for Optical Flow
Bai, M., Luo, W., Kundu, K., & Urtasun, R. (2016) · arXiv.org · doi:10.48550/arxiv.1604.01827 · Cited by 5
“Discrete flow methods: A number of discrete approaches to optical flow estimation have been proposed in recent years [10,11,12,13,14].”
BackgroundTransformation of Markov Random Fields for marginal distribution estimation
Saito, M., & Okatani, T. (2015) · Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2015.7298680 · Cited by 5 · see citing works
“They are targeted at specific problems such as stereo matching [6, 14, 27] and object segmentation [8].”
BackgroundAdaptive large window correlation for optical flow estimation with discrete optimization
Lee, K. J., Yun, I., & Lee, S.-U. (2013) · Image and Vision Computing · doi:10.1016/j.imavis.2013.06.009 · Cited by 5 · see citing works
PHYOT: Physics-Informed Object Tracking in Surveillance Cameras
Kamtue, K., Moura, J. M. F., Sangpetch, O., & Garcia, P. (2023) · IEEE International Conference on Acoustics, Speech, and Signal Processing · doi:10.1109/icassp48485.2024.10448150 · Cited by 4 · see citing works
“Our approach utilizes a second “sensor” that provides us with indirect observation of the tracked object velocities, independent of the tracking network: specifically, we use Optical Flow (OF [17]) to approximate the velocity of the tracked object.”
MethodStereo matching based on multi-scale fusion and multi-type support regions.
Li, H.-B., Gao, Y.-K., Huang, Z., & Zhang, Y. (2019) · Journal of The Optical Society of America A-optics Image Science and Vision · doi:10.1364/josaa.36.001523 · Cited by 4
Hierarchical architecture for motion and depth estimations based on color cues
Barranco, F., Tomasi, M., Vanegas, M., Díaz, J., Granados, S., & Ros, E. (2015) · Journal of Real-Time Image Processing · doi:10.1007/s11554-012-0294-1 · Cited by 4
“Lei and Yang [26] 640 9 480 0.”
Event classification for vehicle navigation system by regional optical flow analysis
Choi, M.-K., Park, J., & Lee, S.-C. (2014) · Machine Vision and Applications · doi:10.1007/s00138-011-0384-2 · Cited by 4
“presented a region based method using discrete optimization [25].”
Improving Motion Estimation Using Image-Driven Functions and Hybrid Scheme
Nguyen, D., & Jeon, J. (2011) · Pacific-Rim Symposium on Image and Video Technology · doi:10.1007/978-3-642-25367-6_7 · Cited by 3 · see citing works
“Our method yields better results than some of the current stateof-art methods [4,5,18,19,20,21,22,23,24] for Urban sequence.”
μ-UAV Based Dynamic Target Tracking for Surveillance and Exploration
Bhaskar, H., Dias, J., Seneviratne, L., & Al-Mualla, M. (2014) · International Symposium on Visual Computing · doi:10.1007/978-3-319-14249-4_42 · Cited by 2 · see citing works
“Mathematically, the estimation of optical flow as an energy minimisation problem is formulated as in [6,7].”
Romanenko, I., Edirisinghe, E., & Larkin, D. (2014) · Electronic imaging · doi:10.1117/12.2042489 · Cited by 2
Adaptive Support Weight-Based Stereo Matching with Iterative Disparity Refinement
Richter, A., Steinmann, T., Reichenbach, A., & Rupitsch, S. J. (2025) · Italian National Conference on Sensors · doi:10.3390/s25134124 · Cited by 1 · see citing works
Fine Dense Alignment of Image Bursts through Camera Pose and Depth Estimation
Lecouat, B., de Mont-Marin, Y., Bodrito, T., Mairal, J., & Ponce, J. (2023) · arXiv.org · doi:10.48550/arxiv.2312.05190 · Cited by 1
“From this initialization, we adopt a coarse-to-fine strategy as in [30, 39] for optimizing the plan map.”
Rapid handling of outliers in dense sampling descriptor correspondence fields
Dong, C., Wang, Z.-S., Xing, C.-D., & Xue, Y. (2018) · J. Electronic Imaging · doi:10.1117/1.jei.27.6.063025 · Cited by 1
Real-Time Stereo Matching System
Zhu, A., Cao, Z.-G., & Xiao, Y. (2018) · International Conference on Intelligent Robotics and Applications · doi:10.1007/978-3-319-97589-4_32 · Cited by 1 · see citing works
Occlusion detecting window matching scheme for optical flow estimation with discrete optimization
Lee, K. J., & Yun, I. (2017) · Pattern Recognition Letters · doi:10.1016/j.patrec.2017.02.009 · Cited by 1 · see citing works
Region Tree Based Sparse Model for Optical Flow Estimation
Luo, W., Zhang, F., Yang, J., & Yang, J.-Y. (2014) · International Conference on Pattern Recognition · doi:10.1109/icpr.2014.362 · Cited by 1
Hsu, C.-Y., Hsieh, Y.-Y., Lo, K.-H., & Chuang, J. (2014) · International Conference on Information Photonics · doi:10.1109/icip.2014.7025878 · Cited by 1
Enhancing accuracy and sharpness of motion field with adaptive scheme and occlusion-aware filter
Nguyen, D., & Jeon, J. (2013) · IET Image Processing · doi:10.1049/iet-ipr.2012.0563 · Cited by 1 · see citing works
“We also compared our method with some state-of-the-art methods, including [4, 5, 22 – 28].”
Control Embebido de Robots Móviles con Recursos Limitados Basado en Flujo Óptico
Sanahuja, G., Valera, Á., Sánchez, A. J., Ricolfe-Viala, C., Vallés, M., & Marín, L. (2011) · doi:10.1016/j.riai.2011.06.012 · Cited by 1
Human robot interaction in a crowded environment
Valibeik, S. (2010) · Spiral (Imperial College London) · doi:10.25560/5677 · Cited by 1 · see citing works
Zhang, K., Xing, J.-M., & Xiao, Q. (2026) · Journal of Imaging · doi:10.3390/jimaging12040156
“…and d v k,l denote the iteration variables at some step l. Finally, with Equation (21), the linear system of equations in d u k, l+1 , d v k, l+1 reads: = 0 The coarse-to-fine warping technique can be theoretically justified as a numerical approximation or a single minimization problem [17,46–48].”
Model-based Optical Flow: Layers, Learning, and Geometry
Wulff, J. (2017) · doi:10.15496/publikation-22990
“Lei and Yang [150] construct a hierarchical segmentation of the image, resulting in a tree.”
BackgroundStereo Matching Based on Edge-Aware T-MST
Zhou, D., & Zhao, J.-Y. (2016) · 2016 IEEE International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData) · doi:10.1109/ithings-greencom-cpscom-smartdata.2016.168
Contributions to accurate and efficient cost aggregation for stereo matching
Chen, D. (2015) · doi:10.70675/ea7d86eezc847z4a7cz948ez39c0ba74991e
“The TADCG cost function is also used in optical flow estimation [30] [31].”
MethodOptical flow based image analysis for investigating failure mechanism of a rock sample
Bhattacharjee, S., & Deb, D. (2013) · doi:10.1201/b14916-28
The analysis and development of computed 2D optical flow velocity based on phantom data
Cai, F., van Triest, H. J. W., & Kang, Y. (2012) · International Conference on Computerized Healthcare · doi:10.1109/icch.2012.6724469
“The ones which use oriented smoothness [9, 10, 11, 16], use rigidity constraints [15, 11] and use image segmentation [3, 7, 17, 14] deserve our notification and careful consideration.”
BackgroundOptical flow estimation with parameterized data term and warping
Xu, J., Feng, Z.-R., & Lu, N. (2012) · Proceedings of the 10th World Congress on Intelligent Control and Automation · doi:10.1109/wcica.2012.6359357
“Most of the current methods [16, 17, 18, 19, 20] resemble the variational model of Horn and Schunck [1], which consists of a data term and a smoothness term.”
MethodThe iterative graph cut optical flow estimation with space term disturbance
Lu, Z.-Y., Tang, T.-S., & Liu, W. (2010) · International Conference on Information Science and Engineering · doi:10.1109/icise.2010.5689955
“It could be classified into two types: the continuous optical flow estimation and the discrete optical flow estimation, according to the continuity of the optical flow value.”
BackgroundA REGION TREE BASED IMAGE DISCRETE LABELING FRAMEWORK
Lei, C., & Yang, H. (2009) · WORLD SCIENTIFIC eBooks · doi:10.1142/9789814273398_0007
Self-citationO PTICAL FLOW BASED ANALYSIS OF LEUKOCYTE DYNAMICS IN MICROCIRCULATION
Ismail, M. B. B., Bchir, O., & Artoli, A. (2015) · doi:10.5121/ijaia.2015.6303
“Other significant non-classical approaches adopt image segmentation [27, 28], oriented smoothness [24, 25] or rigidity constraints [25, 26].”
Background
- Authors
- Lei, C., & Yang, Y.-H.
- Affiliations
- University of Alberta (CA)
- Venue
- 2009 IEEE 12th International Conference on Computer Vision
- Publisher
- IEEE
- Published
- 2009-09
- Pages
- 1562-1569
- OpenAlex
- W2532567985
- Cited by
- 67
- References
- 0
- Citations by year
- 2025: 1 · 2024: 2 · 2023: 2 · 2022: 3 · 2019: 1 · 2018: 4 · 2017: 1 · 2016: 4 · 2015: 6 · 2014: 9 · 2013: 11 · 2012: 5
- FWCI
- 6.26
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE/CVF International Conference on Computer Vision (ICCV) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Vision and Imaging
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Video Surveillance and Tracking Methods
- Physical Sciences › Computer Science › Signal Processing › Video Coding and Compression Technologies
- Keywords
- optical flow, motion estimation, over-segmentation, coarse-to-fine refinement, dynamic programming, energy minimization, discrete optimization, occlusion detection
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
