The focus of motion analysis has been on estimating a flow vector for every pixel by matching intensities. In my thesis, I will explore motion representations beyond the pixel level and new applications to which these representations lead.
I first focus on analyzing motion from video sequences. Traditional motion analysis suffers from the inappropriate modeling of the grouping relationship of pixels and from a lack of ground-truth data. Using layers as the interface for humans to interact with videos, we build a human-assisted motion annotation system to obtain ground-truth motion, missing in the literature, for natural video sequences. Furthermore, we show that with the layer representation, we can detect and magnify small motions to make them visible to human eyes. Then we move to a contour presentation to analyze the motion for textureless objects under occlusion. We demonstrate that simultaneous boundary grouping and motion analysis can solve challenging data, where the traditional pixel-wise motion analysis fails.
In the second part of my thesis, I will show the benefits of matching local image structures instead of intensity values. We propose SIFT flow that establishes dense, semantically meaningful correspondence between two images across scenes by matching pixel-wise SIFT features. Using SIFT flow, we develop a new framework for image parsing by transferring the metadata information, such as annotation, motion and depth, from the images in a large database to an unknown query image. We demonstrate this framework using new applications such as predicting motion from a single image and motion synthesis via object transfer. Based on SIFT flow, we introduce a nonparametric scene parsing system using label transfer, with very promising experimental results suggesting that our system outperforms state-of-the-art techniques based on training classifiers. (Copies available exclusively from MIT Libraries, Rm. 14-0551, Cambridge, MA 02139-4307. Ph. 617-253-5668; Fax 617-253-1690.)
Cited By
- Zhu S, Wan M, Manne S, Hatamimajoumerd E, Hayes M, Zimmerman E and Ostadabbas S (2024). Subtle signals, Computer Vision and Image Understanding, 247:C, Online publication date: 1-Oct-2024.
- Pan Z, Geng D and Owens A Self-supervised motion magnification by backpropagating through optical flow Proceedings of the 37th International Conference on Neural Information Processing Systems, (253-273)
- Liu Z, Li Z, Chen W, Wu X and Liu Z (2023). Unsupervised Optical Flow Estimation for Differently Exposed Images in LDR Domain, IEEE Transactions on Circuits and Systems for Video Technology, 33:10, (5332-5344), Online publication date: 1-Oct-2023.
- Sultana M, Mahmood A and Jung S (2022). Unsupervised moving object segmentation using background subtraction and optimal adversarial noise sample search, Pattern Recognition, 129:C, Online publication date: 1-Sep-2022.
- Saleem N, Gao J, Irfan M, Verdu E and Fuente J (2022). E2E-V2SResNet, Image and Vision Computing, 119:C, Online publication date: 1-Mar-2022.
- Martin P, Benois-Pineau J, Péteri R and Morlier J Three-Stream 3D/1D CNN for Fine-Grained Action Classification and Segmentation in Table Tennis Proceedings of the 4th International Workshop on Multimedia Content Analysis in Sports, (35-41)
- Chaudhary S, Dudhane A, Patil P, Murala S and Talbar S (2021). Motion estimation in hazy videos, Pattern Recognition Letters, 150:C, (130-138), Online publication date: 1-Oct-2021.
- Wang H, Liu W and Xing W (2021). Video object segmentation via random walks on two-frame graphs comprising superpixels, Journal of Visual Communication and Image Representation, 80:C, Online publication date: 1-Oct-2021.
- Saoji S, Krishna D, Sanap V, Nagar R and Shah S Learning-based Approach for Estimation of Axis of Rotation for Markerless Visual Servoing to Tumbling Object Proceedings of the 2021 5th International Conference on Advances in Robotics, (1-7)
- Liba O, Murthy K, Tsai Y, Brooks T, Xue T, Karnad N, He Q, Barron J, Sharlet D, Geiss R, Hasinoff S, Pritch Y and Levoy M (2019). Handheld mobile photography in very low light, ACM Transactions on Graphics, 38:6, (1-16), Online publication date: 31-Dec-2020.
- Lu R, Duan Z and Zhang C (2019). Audio–Visual Deep Clustering for Speech Separation, IEEE/ACM Transactions on Audio, Speech and Language Processing, 27:11, (1697-1712), Online publication date: 1-Nov-2019.
- Qi Q, Zhao S, Zhao W, Lei Z, Shen J, Zhang L and Pang Y (2019). High-speed video salient object detection with temporal propagation using correlation filter, Neurocomputing, 356:C, (107-118), Online publication date: 3-Sep-2019.
- Kang K and Cho S (2019). Interactive and automatic navigation for 360° video playback, ACM Transactions on Graphics, 38:4, (1-11), Online publication date: 31-Aug-2019.
- Sajid H, Cheung S and Jacobs N (2019). Motion and appearance based background subtraction for freely moving cameras, Image Communication, 75:C, (11-21), Online publication date: 1-Jul-2019.
- Siam M, Jiang C, Lu S, Petrich L, Gamal M, Elhoseiny M and Jagersand M Video Object Segmentation using Teacher-Student Adaptation in a Human Robot Interaction (HRI) Setting 2019 International Conference on Robotics and Automation (ICRA), (50-56)
- Yang H and Yin L Learning Temporal Information From A Single Image For AU Detection 2019 14th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2019), (1-8)
- Xie Y, Liu Z, Zhou X, Liu W and Zou X (2019). Video co-segmentation based on directed graph, Multimedia Tools and Applications, 78:8, (10353-10372), Online publication date: 1-Apr-2019.
- Sultana M, Mahmood A, Javed S and Jung S (2019). Unsupervised deep context prediction for background estimation and foreground segmentation, Machine Vision and Applications, 30:3, (375-395), Online publication date: 1-Apr-2019.
- Lau C, Lai Y and Lui L (2019). Variational Models for Joint Subsampling and Reconstruction of Turbulence-Degraded Images, Journal of Scientific Computing, 78:3, (1488-1525), Online publication date: 1-Mar-2019.
- Leon Lopez K, Galvis Carreno L and Arguello Fuentes H (2019). Temporal Colored Coded Aperture Design in Compressive Spectral Video Sensing, IEEE Transactions on Image Processing, 28:1, (253-264), Online publication date: 1-Jan-2019.
- Kamenick? J, ?Roubek F, Zitová B, Hannuksela J and Turtinen M (2019). Image Restoration in Portable Devices, Journal of Signal Processing Systems, 91:1, (9-20), Online publication date: 1-Jan-2019.
- Chen D and Wang H Handheld Food Localization and Food Recognition Using Convolutional Neural Network Proceedings of the 2018 International Conference on Digital Medicine and Image Processing, (61-64)
- Zhang X, Dekel T, Xue T, Owens A, He Q, Wu J, Mueller S and Freeman W MoSculp Proceedings of the 31st Annual ACM Symposium on User Interface Software and Technology, (275-285)
- Wu T, Liu Z, Zhou X and Li K (2018). Spatiotemporal salient object detection by integrating with objectness, Multimedia Tools and Applications, 77:15, (19481-19498), Online publication date: 1-Aug-2018.
- Zhang P, Zhuo T, Huang H, Chen K, Zhang B and Kankanhalli M (2018). Robust tracking based on H-CNN with low-resource sampling and scaling by frame-wise motion localization, Multimedia Tools and Applications, 77:14, (18781-18800), Online publication date: 1-Jul-2018.
- Xie Q, Remil O, Guo Y, Wang M, Wei M and Wang J (2018). Object Detection and Tracking Under Occlusion for Object-Level RGB-D Video Segmentation, IEEE Transactions on Multimedia, 20:3, (580-592), Online publication date: 1-Mar-2018.
- Calagari K, Elgharib M, Didyk P, Kaspar A, Matusik W and Hefeeda M (2018). Data Driven 2-D-to-3-D Video Conversion for Soccer, IEEE Transactions on Multimedia, 20:3, (605-619), Online publication date: 1-Mar-2018.
- Ullah J, Khan A and Jaffar M (2018). Motion cues and saliency based unconstrained video segmentation, Multimedia Tools and Applications, 77:6, (7429-7446), Online publication date: 1-Mar-2018.
- Ramachandra R and Busch C (2017). Presentation Attack Detection Methods for Face Recognition Systems, ACM Computing Surveys, 50:1, (1-37), Online publication date: 31-Jan-2018.
- Zhou D, Frmont V, Quost B, Dai Y and Li H (2017). Moving object detection and segmentation in urban environments from a moving platform, Image and Vision Computing, 68:C, (76-87), Online publication date: 1-Dec-2017.
- Liu W, Yan C, Liu J and Ma H (2017). Deep learning based basketball video analysis for intelligent arena application, Multimedia Tools and Applications, 76:23, (24983-25001), Online publication date: 1-Dec-2017.
- Yao C, Chang C and Chien S Occlusion-aware Video Temporal Consistency Proceedings of the 25th ACM international conference on Multimedia, (777-785)
- Skupin R, Sanchez Y, Podborski D, Hellge C and Schierl T Viewport-dependent 360 degree video streaming based on the emerging Omnidirectional Media Format (OMAF) standard 2017 IEEE International Conference on Image Processing (ICIP), (4592-4592)
- Yang X, Feng Z, Xu T, Tang H and Jiang Y Motion-compensated frame interpolation for multiview video using inter-view and intra-view correlations 2017 IEEE International Conference on Image Processing (ICIP), (4312-4316)
- Choi D, Choi J, Choi J and Song B CNN-based pre-processing and multi-frame-based view transformation for fisheye camera-based AVM system 2017 IEEE International Conference on Image Processing (ICIP), (4073-4077)
- Le T, Almansa A, Gousseau Y and Masnou S Motion-consistent video inpainting 2017 IEEE International Conference on Image Processing (ICIP), (2094-2098)
- Zhu Q, Wong C, Fu C and Wu M Fitness heart rate measurement using face videos 2017 IEEE International Conference on Image Processing (ICIP), (2000-2004)
- Mullan P, Cozzolino D, Verdoliva L and Riess C Residual-based forensic comparison of video sequences 2017 IEEE International Conference on Image Processing (ICIP), (1507-1511)
- Sarkar S, Venugopalan V, Reddy K, Ryde J, Jaitly N and Giering M (2017). Deep Learning for Automated Occlusion Edge Detection in RGB-D Frames, Journal of Signal Processing Systems, 88:2, (205-217), Online publication date: 1-Aug-2017.
- Frémont V, Florez S and Wang B Mono-vision based moving object detection in complex traffic scenes 2017 IEEE Intelligent Vehicles Symposium (IV), (1078-1084)
- Liu L, Zhou Y and Shao L DAP3D-Net: Where, what and how actions occur in videos? 2017 IEEE International Conference on Robotics and Automation (ICRA), (138-145)
- Kang K, Cao Y and Wang Z (2017). Simultaneously retargeting and super-resolution for stereoscopic video, Multimedia Tools and Applications, 76:8, (11081-11095), Online publication date: 1-Apr-2017.
- Li Y, Lee C and Monga V (2017). A Maximum a Posteriori Estimation Framework for Robust High Dynamic Range Video Synthesis, IEEE Transactions on Image Processing, 26:3, (1143-1157), Online publication date: 1-Mar-2017.
- (2017). Detecting anomalous events in videos by learning deep representations of appearance and motion, Computer Vision and Image Understanding, 156:C, (117-127), Online publication date: 1-Mar-2017.
- Yun K, Yoo Y and Choi J (2017). Motion interaction field for detection of abnormal interactions, Machine Vision and Applications, 28:1-2, (157-171), Online publication date: 1-Feb-2017.
- Min X, Zhai G, Gu K and Yang X (2016). Fixation Prediction through Multimodal Analysis, ACM Transactions on Multimedia Computing, Communications, and Applications, 13:1, (1-23), Online publication date: 17-Jan-2017.
- Yang T, Wang X, Wang H and Li X Depth Map Enhancement with Interaction in 2D-to-3D Video Conversion LNCS on Transactions on Edutainment XIII - Volume 10092, (183-193)
- Xue T, Wu J, Bouman K and Freeman W Visual dynamics Proceedings of the 30th International Conference on Neural Information Processing Systems, (91-99)
- Huang J, Kang S, Ahuja N and Kopf J (2016). Temporally coherent completion of dynamic video, ACM Transactions on Graphics, 35:6, (1-11), Online publication date: 11-Nov-2016.
- Kurnianggoro L, Shahbaz A and Jo K Dense optical flow in stabilized scenes for moving object detection from a moving camera 2016 16th International Conference on Control, Automation and Systems (ICCAS), (704-708)
- Levinkov E, Tompkin J, Bonneel N, Kirchhoff S, Andres B and Pfister H Interactive multicut video segmentation Proceedings of the 24th Pacific Conference on Computer Graphics and Applications: Short Papers, (33-38)
- Yun Y and Gu I (2016). Human fall detection in videos by fusing statistical features of shape and motion dynamics on Riemannian manifolds, Neurocomputing, 207:C, (726-734), Online publication date: 26-Sep-2016.
- Zhang P, Zhuo T, Xie L and Zhang Y (2016). Deformable object tracking with spatiotemporal segmentation in big vision surveillance, Neurocomputing, 204:C, (87-96), Online publication date: 5-Sep-2016.
- Kaviani H and Shirani S (2016). Frame Rate Upconversion Using Optical Flow and Patch-Based Reconstruction, IEEE Transactions on Circuits and Systems for Video Technology, 26:9, (1581-1594), Online publication date: 1-Sep-2016.
- Pun C and Lin C (2016). A real-time detector for parked vehicles based on hybrid background modeling, Journal of Visual Communication and Image Representation, 39:C, (82-92), Online publication date: 1-Aug-2016.
- Yun Y and Gu I (2016). Human fall detection in videos via boosting and fusing statistical features of appearance, shape and motion dynamics on Riemannian manifolds with applications to assisted living, Computer Vision and Image Understanding, 148:C, (111-122), Online publication date: 1-Jul-2016.
- Luo Y, Yuan J and Lu J (2016). Finding spatio-temporal salient paths for video objects discovery, Journal of Visual Communication and Image Representation, 38:C, (45-54), Online publication date: 1-Jul-2016.
- Tong M, Guo J, Tao S and Wu Y (2016). Independent detection and self-recovery video authentication mechanism using extended NMF with different sparseness constraints, Multimedia Tools and Applications, 75:13, (8045-8069), Online publication date: 1-Jul-2016.
- Zhang S, Klein D, Bauckhage C and Cremers A (2016). Fast moving pedestrian detection based on motion segmentation and new motion features, Multimedia Tools and Applications, 75:11, (6263-6282), Online publication date: 1-Jun-2016.
- Jeon D, Choi I and Kim M Multisampling compressive video spectroscopy Proceedings of the 37th Annual Conference of the European Association for Computer Graphics, (467-477)
- Suo J, Bian L, Chen F and Dai Q (2016). Signal-dependent noise removal for color videos using temporal and cross-channel priors, Journal of Visual Communication and Image Representation, 36:C, (130-141), Online publication date: 1-Apr-2016.
- Le T and Sugimoto A Contrast Based Hierarchical Spatial-Temporal Saliency for Video Image and Video Technology, (734-748)
- Dekel T, Michaeli T, Irani M and Freeman W (2015). Revealing and modifying non-local variations in a single image, ACM Transactions on Graphics, 34:6, (1-11), Online publication date: 4-Nov-2015.
- Bonneel N, Tompkin J, Sunkavalli K, Sun D, Paris S and Pfister H (2015). Blind video temporal consistency, ACM Transactions on Graphics, 34:6, (1-9), Online publication date: 4-Nov-2015.
- Chang K and Li B (2015). Joint modeling and reconstruction of a compressively-sensed set of correlated images, Journal of Visual Communication and Image Representation, 33:C, (286-300), Online publication date: 1-Nov-2015.
- Hu J and Luo Y (2015). Noise-robust video super-resolution using an adaptive spatial-temporal filter, Multimedia Tools and Applications, 74:21, (9259-9278), Online publication date: 1-Nov-2015.
- Jeon Y, Sandhan T and Choi J Robust Feature Extraction for Shift and Direction Invariant Action Recognition Proceedings, Part II, of the 16th Pacific-Rim Conference on Advances in Multimedia Information Processing -- PCM 2015 - Volume 9315, (321-329)
- Deng J and Tan Y (2015). Motion-compensated orthonormal expansion ℓ1 -minimization for reference-driven MRI reconstruction using Augmented Lagrangian methods, Journal of Visual Communication and Image Representation, 31:C, (112-124), Online publication date: 1-Aug-2015.
- Kannan R, Ghinea G and Swaminathan S (2015). Discovering salient objects from videos using spatiotemporal salient region detection, Image Communication, 36:C, (154-178), Online publication date: 1-Aug-2015.
- Heide F, Heidrich W, Hullin M and Wetzstein G (2015). Doppler time-of-flight imaging, ACM Transactions on Graphics, 34:4, (1-11), Online publication date: 27-Jul-2015.
- Zhao H and Fu Y Semantic single video segmentation with robust graph representation Proceedings of the 24th International Conference on Artificial Intelligence, (2219-2225)
- Li Y, Tan Y, Yu J, Qi S and Tian J (2015). Kernel regression in mixed feature spaces for spatio-temporal saliency detection, Computer Vision and Image Understanding, 135:C, (126-140), Online publication date: 1-Jun-2015.
- Liu Z, Yuan L, Tang X, Uyttendaele M and Sun J (2014). Fast burst images denoising, ACM Transactions on Graphics, 33:6, (1-9), Online publication date: 19-Nov-2014.
- Liu S, Wang J, Cho S and Tan P (2014). TrackCam, ACM Transactions on Graphics, 33:6, (1-11), Online publication date: 19-Nov-2014.
- Heide F, Steinberger M, Tsai Y, Rouf M, Pająk D, Reddy D, Gallo O, Liu J, Heidrich W, Egiazarian K, Kautz J and Pulli K (2014). FlexISP, ACM Transactions on Graphics, 33:6, (1-13), Online publication date: 19-Nov-2014.
- Bonneel N, Sunkavalli K, Tompkin J, Sun D, Paris S and Pfister H (2014). Interactive intrinsic video editing, ACM Transactions on Graphics, 33:6, (1-10), Online publication date: 19-Nov-2014.
- Buso V, Benois-Pineau J and Domenger J Geometrical Cues in Visual Saliency Models for Active Object Recognition in Egocentric Videos Proceedings of the 1st International Workshop on Perception Inspired Video Processing, (9-14)
- Su H, Hajj-Ahmad A, Wong C, Garg R and Wu M ENF Signal Induced by Power Grid Proceedings of the 2nd ACM International Workshop on Immersive Media Experiences, (13-18)
- Li K, Ye J and Hua K What's Making that Sound? Proceedings of the 22nd ACM international conference on Multimedia, (147-156)
- Cao Y, Zhang S, Zha Z, Zhang J and Chen C (2014). A novel segmentation based video-denoising method with noise level estimation, Information Sciences: an International Journal, 281, (507-520), Online publication date: 1-Oct-2014.
- Trocan M, Tramel E, Fowler J and Pesquet B (2014). Compressed-sensing recovery of multiview image and video sequences using signal prediction, Multimedia Tools and Applications, 72:1, (95-121), Online publication date: 1-Sep-2014.
- Geng W, Yang Y, Ju R, Ren T and Wu G Fast Binocular Depth Inference via Bidirectional Motion Based Interpolation Proceedings of International Conference on Internet Multimedia Computing and Service, (213-216)
- Kalantari N, Shechtman E, Barnes C, Darabi S, Goldman D and Sen P (2013). Patch-based high dynamic range video, ACM Transactions on Graphics, 32:6, (1-8), Online publication date: 1-Nov-2013.
- Zhuo T, Zhang Y, Zhang P, Huang W and Sahli H Non-rigid target tracking based on 'flow-cut' in pair-wise frames with online hough forests Proceedings of the 21st ACM international conference on Multimedia, (489-492)
- Ji S, Fan X, Roberts D, Hartov A and Paulsen K Flow-Based Correspondence Matching in Stereovision Proceedings of the 4th International Workshop on Machine Learning in Medical Imaging - Volume 8184, (106-113)
- Márquez-Valle P, Gil D, Hernàndez-Sabaté A and Kondermann D When is a confidence measure good enough? Proceedings of the 9th international conference on Computer Vision Systems, (344-353)
- Bai J, Agarwala A, Agrawala M and Ramamoorthi R Automatic cinemagraph portraits Proceedings of the Eurographics Symposium on Rendering, (17-25)
- Popa M, Rothkrantz L, Shan C, Gritti T and Wiggers P (2013). Semantic assessment of shopping behavior using trajectories, shopping related actions, and context information, Pattern Recognition Letters, 34:7, (809-819), Online publication date: 1-May-2013.
- Sindeev M, Konushin A and Rother C Alpha-Flow for video matting Proceedings of the 11th Asian conference on Computer Vision - Volume Part III, (438-452)
- Sen P, Kalantari N, Yaesoubi M, Darabi S, Goldman D and Shechtman E (2012). Robust patch-based hdr reconstruction of dynamic scenes, ACM Transactions on Graphics, 31:6, (1-11), Online publication date: 1-Nov-2012.
- Chen D, Chen H and Chang L Video object cosegmentation Proceedings of the 20th ACM international conference on Multimedia, (805-808)
- Zhang B, Zhao H and Cao X Video object segmentation with shortest path Proceedings of the 20th ACM international conference on Multimedia, (801-804)
- Jiang H, Liu H, Tan P, Zhang G and Bao H 3D Reconstruction of Dynamic Scenes with Multiple Handheld Cameras Proceedings, Part II, of the 12th European Conference on Computer Vision --- ECCV 2012 - Volume 7573, (601-615)
- Márquez-Valle P, Gil D and Hernàndez-Sabaté A A complete confidence framework for optical flow Proceedings of the 12th international conference on Computer Vision - Volume 2, (124-133)
- Cui X, Huang J, Zhang S and Metaxas D Background subtraction using low rank and group sparsity constraints Proceedings of the 12th European conference on Computer Vision - Volume Part I, (612-625)
- Karsch K, Liu C and Kang S Depth extraction from video using non-parametric sampling Proceedings of the 12th European conference on Computer Vision - Volume Part V, (775-788)
- Sun D and Liu C Non-causal temporal prior for video deblocking Proceedings of the 12th European conference on Computer Vision - Volume Part V, (510-523)
- Trulls E, Sanfeliu A and Moreno-Noguer F Spatiotemporal descriptor for wide-baseline stereo reconstruction of non-rigid and ambiguous scenes Proceedings of the 12th European conference on Computer Vision - Volume Part III, (441-454)
- Kowdle A and Chen T Learning to segment a video to clips based on scene and camera motion Proceedings of the 12th European conference on Computer Vision - Volume Part III, (272-286)
- Lim T, Han B and Han J (2012). Modeling and segmentation of floating foreground and background in videos, Pattern Recognition, 45:4, (1696-1706), Online publication date: 1-Apr-2012.
- Li L, Feng W, Zhang J and Jiang J Video motion estimation with temporal coherence Proceedings of the 10th International Conference on Virtual Reality Continuum and Its Applications in Industry, (315-320)
- Popa M, Gritti T, Rothkrantz L, Shan C and Wiggers P Detecting customers' buying events on a real-life database Proceedings of the 14th international conference on Computer analysis of images and patterns - Volume Part I, (17-25)
- Qin C, Bao X, Roy Choudhury R and Nelakuditi S TagSense Proceedings of the 9th international conference on Mobile systems, applications, and services, (1-14)
- Liu C and Freeman W A high-quality video denoising algorithm based on reliable motion estimation Proceedings of the 11th European conference on computer vision conference on Computer vision: Part III, (706-719)
- Ghafarianzadeh M, Blaschko M and Sibley G Efficient, dense, object-based segmentation from RGBD video 2016 IEEE International Conference on Robotics and Automation (ICRA), (2310-2317)
- Purica A, Cagnazzo M, Pesquet-Popescu B, Dufaux F and Ionesc B View synthesis based on temporal prediction via warped motion vector fields 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), (1150-1154)
- Ji S, Fan X, Roberts D and Paulsen K Efficient Stereo Image Geometrical Reconstruction at Arbitrary Camera Settings from a Single Calibration Medical Image Computing and Computer-Assisted Intervention – MICCAI 2014, (440-447)
- Amir-Khalili A, Peyrat J, Abinahed J, Al-Alao O, Al-Ansari A, Hamarneh G and Abugharbieh R Auto Localization and Segmentation of Occluded Vessels in Robot-Assisted Partial Nephrectomy Medical Image Computing and Computer-Assisted Intervention – MICCAI 2014, (407-414)
Recommendations
Beyond pixels and regions: A non-local patch means (NLPM) method for content-level restoration, enhancement, and reconstruction of degraded document images
A patch-based non-local restoration and reconstruction method for preprocessing degraded document images is introduced. The method collects relative data from the whole input image, while the image data are first represented by a content-level ...
High-quality image deblurring with panchromatic pixels
Image deblurring has been a very challenging problem in recent decades. In this article, we propose a high-quality image deblurring method with a novel image prior based on a new imaging system. The imaging system has a newly designed sensor pattern ...
Silicon retina with correlation-based, velocity-tuned pixels
A functional two-dimensional silicon retina that computes a complete set of local direction-selective outputs is reported. The chip motion computation uses unidirectional delay lines as tuned filters for moving edges. Photoreceptors detect local changes ...