Resume

Papers

F. Porikli, "Needle picking for very low SNR target detection in radar signals", Proceedings of SPIE Defense & Security, 2010 (oral)
A. Joshi and F. Porikli, "Scene-Adaptive human detection with incremental active learning", IEEE International Conference on Pattern Recognition (ICPR), 2010
A. Joshi, F. Porikli, N. Papanikolopoulos, "Breaking the interactive bottleneck in multi-class classification with active selection and binary feedback", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2010
T. Lee, A. Chaudhuri, F. Porikli, H.W. Chen, "CycleStack: inferring periodic behavior via temporal sequence visualization in ultrasound video", IEEE Pacific Visualization Conference (PacVis), 2010 (oral)
F. Porikli, P. Pan, "Regressed importance sampling on manifolds for efficient object tracking", IEEE Advanced Video and Signal based Surveillance (AVSS), 2009 (oral)
A. Joshi, F. Porikli, N. Papanikolopoulos, "Multi-class batch-mode active learning for image classification", IEEE International Conference on Robotics and Automation (ICRA), 2010
A. Joshi, F. Porikli, N. Papanikolopoulos, "Multi-class active learning for image classification", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2009
O. Tuzel, F. Porikli, P. Meer, "Kernel methods for weakly supervised mean-shift clustering", IEEE International Conference on Computer Vision (ICCV), 2009 (oral, 3.1% acceptance rate)
P. Pan, F. Porikli, D. Schonfeld, "Recurrent tracking using multifold consistency", IEEE International Conference on Computer Vision (CVPR), PETS workshop, 2009 (oral)
K. Sengupta, F. Porikli, "Geometric sequence imaging with Bayesian smoothing for optical and capacitive imaging sensors", IEEE Workshop on Object Tracking and Classification in and Beyond the Visible Spectrum, (OTBVS - CVPR), 2009 (oral)
M. Hussein, F. Porikli, L. Davis, "Object detection via boosted deformable features", IEEE International Conference on Image Processing (ICIP), 2009 (oral)
A. Joshi, F. Porikli, N. Papanikolopoulos, "Multi-class active learning with binary user feedback, "Advances in Neural Information Processing Systems (NIPS), Workshop on Analysis and Design of Algorithms for Interactive Machine Learning (ADA-IML), 2009.
F. Porikli, "Constant Time O(1) Bilateral Filtering", IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2008 (oral)
O. Tuzel, F. Porikli, P. Meer, "Human detection via classification on Riemannian manifolds", IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2008
M. Hussein, F. Porikli, L. Davis, "Pedestrian detection in images: a practical comparative Study, IEEE Transaction on Intelligent Transportation Systems, 2009
O. Tuzel, F. Porikli, P. Meer, "Regression based class-specific tracking for fast object detectors", IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2008
T. Parag, F. Porikli, A. Elgammal, "Adaptive linear weak classifiers for online boosting", IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2008
M. Hussein, F. Porikli, L. Davis, "Kernel integral spaces", IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2008
P. Pan, F. Porikli, D. Schonfeld, "A new method for tracking performance evaluation based on a reflective model and perturbation analysis", Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Taiwan, 2009
O. Tuzel, F. Porikli, P. Meer, "Human detection via classification on Riemannian manifolds", IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2007 (oral) (Best paper prize)
Z. Yin, F. Porikli, R. Collins, "Likelihood map fusion for visual object tracking", IEEE Workshop on Application of Computer Vision (WACV), Colorado, 2008 (oral)
X. Mei, F. Porikli, "Joint tracking and video registration by factorial Hidden Markov Models", Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Las Vegas, 2008
F. Porikli, O. Tuzel, "Learning on Lie groups for invariant detection via tracking", International Workshop On Object Recognition, Lake Como, 2008 (Invited)
F. Porikli, Z. Yin, "Temporally static region detection in multi-camera systems", IEEE International Conference on Computer Vision (ICCV), PETS workshop, Rio De Janeiro, 2007 (oral)
F. Porikli, "Detection of temporarily static regions by processing video at different frame rates", IEEE Advanced Video and Signal based Surveillance (AVSS), London, 2007 (oral)
F. Porikli, T. Kocak, "Fast distance transform computation using dual scan line propagation", Proceedings of SPIE, Real-Time Imaging Conference, San Jose, 2007 (oral)
X. Mei, K. Zhou, F. Porikli, "Probabilistic visual tracking via robust template matching & incremental subspace update", IEEE International Conference on Multimedia and Expo (ICME), Beijing, 2007 (oral) (Best paper nomination)
F. Porikli, O. Tuzel, P. Meer, Covariance tracking using model update based on Lie algebra, IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), New York, 2006
F. Porikli, Achieving real-time object detection and tracking under extreme conditions, Journal of Real-Time Image Processing, Springer, 2006
F. Porikli, O. Tuzel, Covariance tracker, Video Proceedings, IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), New York, 2006
O. Tuzel, F. Porikli, P. Meer, Region covariance: a fast descriptor for detection and classification, IEEE European Conference on Computer Vision (ECCV), Gratz, 2006
F. Porikli, F. Bashir, A complete performance evaluation platform including matrix-based measures for joint object detector and tracker systems, PETS Workshop, CVPR, New York, 2006
F. Porikli, O. Tuzel, Fast construction of covariance matrices for arbitrary size image windows, IEEE International Conference on Image Processing, Atlanta, 2006
J. Shao, R. Chellappa, F. Porikli, Shape-regulated particle filtering for tracking non-rigid objects, IEEE International Conference on Image Processing, Atlanta, 2006
F.Porikli, T. Kocak, Robust license plate detection using covariance descriptor in a neural network framework, IEEE Advanced Video And Signal based Surveillance, Sydney, 2006
F. Porikli, Automatic spatial alignment of visible and infrared images by fast image registration via joint gradient maximization, SPIE Security & Defense, Electro-Optical And Infrared Systems, Sweden, 2006
F. Porikli, Making silicon a little bit less blind: seeing and tracking humans, SPIE OE Magazine, Newsroom Edition, 2006
F. Bashir, F. Porikli, Collaborative tracking of objects in EPTZ cameras, SPIE Video Communication and Image Processing (VCIP) , San Jose, 2007
F. Porikli, Integral histogram: a fast way to extract histogram features, IEEE Int. Conference on Computer Vision and Pattern Recognition (CVPR), Santa Barbara, 2005
F. Porikli, J. Thornton, Shadow flow: A recursive method to learn moving cast shadows, IEEE International Conference on Computer Vision (ICCV), Beijing, 2005
F. Porikli, J. Katz, E. Goubet, Pedestrian tracking using thermal infrared imaging, SPIE Defense & Security Symposium (DSS), Orlando, 2006
F. Porikli, O. Tuzel, Multi-kernel object tracking, Proceedings of IEEE International Conference on Multimedia and Expo, Amsterdam, 2005
F. Porikli, Multiplicative background-foreground estimation under uncontrolled illumination using intrinsic images, Proceedings of IEEE International Multi-Workshop Motion, Breckenridge, 2005
F. Porikli, Ambiguity detection by data fusion: spectral clustering approach, Proceedings of IEEE Intl. Conference on Integration of Knowledge Intensive Multi-Agent Systems, April 2005
F. Porikli, J. Shao, H. Maehara, Extracting roads from aerial images using feature based classifiers, Proceedings of IAPR Conference on Machine Vision Applications, May 2005
F. Porikli, O. Tuzel, Object tracking in low-frame-rate video, Proceedings of SPIE - Image and Video Communication and Processing, January 2005
O. Tuzel, F. Porikli, P. Meer, A Bayesian approach to background modeling and low frame rate tracking, CVPR Workshop on Real-time Machine Vision for Intelligent Vehicles, Santa Barbara, 2005
F. Porikli, Computationally efficient histogram extraction for rectangular image regions, Proceedings of Real-Time Image Processing, January 2005
C. Wren, F. Porikli, Waviz: spectral similarity for object detection, Proceedings of IEEE International Multi-Workshop PETS, Breckenridge, January 2005
F. Porikli, O. Tuzel, Bayesian background generation based foreground detection, 3rd ACM International Workshop on Video Surveillance & Sensor Networks, ACM Multimedia, Singapore, 2005
F. Bashir, A. Khokhar, F. Porikli, D. Schonfeld, Trajectory analysis: A powerful tool for semantics-based indexing and retrieval in multimedia databases, IEEE Signal Processing Magazine, 2005
F. Zilani, S. Velastin, F. Porikli, L. Marcenaro, T. Kelliher, A. Cavallaro, P. Bruneaut, Performance evaluation of event detection solutions: the CREDS experience, IEEE Conference on Advanced Video and Signal Based Surveillance, September 2005
F. Porikli, T. Haga, Event detection by eigenvector decomposition using object and frame features, Proceedings of IEEE Intl. Conference on Computer Vision and Pattern Recognition (CVPR), 2004
F. Porikli, Y. Wang, Automatic video object segmentation using volume growing and hierarchical clustering, Journal of Applied Signal Processing, special issue on Object-Based and Semantic Image and Video Analysis, July 2004
F. Porikli, Trajectory distance metric using Hidden Markov Model based representation, Proceedings of IEEE European Conference on Computer Vision (ECCV), Workshop on PETS, Prague, 2004
F. Porikli, Clustering variable length sequences by eigenvector decomposition using HMMs, Proceedings of IEEE Intl. Conference on Pattern Recognition (ICPR), Workshop SSPR, Portugal, 2004
F. Porikli, X. Li, Traffic congestion analysis in compressed video without tracking, Proceedings of IEEE International Conference on Intelligent Vehicles, Parma, 2004
F. Porikli, Trajectory pattern detection by HMM parameter space features and eigenvector clustering, Proceedings of IEEE International Conference on Multimedia and Expo, Taipei, 2004
F. Porikli, Nonlinear warping function recovery by scan-line search using dynamic programming, Proceedings of IEEE International Conference on Image Processing, Singapore, 2004
X. Li, F. Porikli, A hidden Markov model framework for traffic event detection using video features, Proceedings of IEEE International Conference on Image Processing, Singapore, 2004
F. Porikli, Automatic image segmentation by solving Eikonal equation based on Gaussian mixture models, Proceedings of IS&T/SPIE Symposium on Electronic Imaging, San Jose, 2004
F. Porikli, Real-time video object segmentation for MPEG encoded video sequences, Proceedings of IS&T/SPIE Symposium on Electronic Imaging, San Jose, 2004
F. Porikli, Analysis of down conversion filters, Technical Report, MERL, 2004
Book Chapter: F. Porikli, Multi-camera object recognition and object-based summary generation system, Advanced Video-Based Surveillance Systems, Kluwer Press, 2003
F. Porikli, O. Tuzel, Human body tracking by adaptive background models and mean-shift analysis, Proceedings of IEEE Intl. Conference on Computer Vision Systems (ICVS), Workshop on PETS, 2003
F. Porikli, Road extraction by point-wise Gaussian models, 17th SPIE-AeroSense, Algorithms and Technologies for Multi-spectral, Hyper-spectral, Ultra-spectral Imagery Conference, 2003
F. Porikli, Sensitivity characteristics of cross-correlation distance metric and model function, Proceedings of Conference on Information Sciences and Systems, 2003
F. Porikli, A. Divakaran, Multi-camera calibration, object tracking and query generation, invited paper, IEEE International Conference on Multimedia and Expo, 2003
F. Porikli, Inter-camera color calibration by correlation model functions, Proceedings of IEEE International Conference on Image Processing, Barcelona, 2003
F. Porikli, Y. Wang, Constrained region extraction of video objects by color masks and MPEG-7 descriptors, Proceedings of IEEE Intl. Conference on Multimedia and Expo, Lausanne, 2002
F. Porikli, Automatic threshold determination of centroid-linkage region growing by MPEG-7 dominant color descriptors, Proceedings of IEEE International Conference on Image Processing, Rochester, 2002
F. Porikli, Accurate detection of edge orientation for color and multi spectral imagery, Proceedings of IEEE International Conference on Image Processing, Thessaloniki, Greece, 2001
F. Porikli, Video object segmentation by volume growing using feature-based motion estimator, Proceedings of 16th Intl. Symposium On Computer and Information Sciences, 2001
F. Porikli, Z. Sahinoglu, An online renegotiation-based bandwidth management with circuit assignment for VBR traffic in communication networks, Proceedings of 6th SCI, Orlando, 2002
F. Porikli, Z. Sahinoglu, Dynamic bandwidth allocation with optimal number of renegotiations in ATM networks, Proceedings of 10th IEEE ICCCN 2001, Scottsdale, Arizona, 2001
F. Porikli, Image simplification by robust estimator based reconstruction filter, Proceedings of 16th International Symposium On Computer and Information Sciences, Antalya, Turkey, 2001
F. Porikli, Y. Wang, An unsupervised multi-resolution object extraction algorithm using video-cubes, Proceedings of IEEE International Conference on Image Processing, Thessaloniki, Greece, 2001
F. Porikli, Object segmentation of color video sequences, Proceedings of International Conference on Computer Analysis of Images and Pattern, Warsaw, Poland, 2001
F. Porikli, T. Keaton, Unsupervised road extraction algorithm for low-resolution satellite imagery, Proceedings of IEEE International Conference on Pattern Recognition and Remote Sensing, Andorra, 2000
F. Porikli, Y. Wang, C. Swain, Adaptive stripe based patch matching for depth estimation, Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing, 1997
F. Porikli, Stripe mesh based disparity estimation by using 3-D Hough transform, Proceedings of IEEE International Conference on Image Processing, Santa Barbara, 1997
F. Porikli, Y. Wang, Disparity estimation by patch matching, Proceedings of IEEE PCS, Munich, 1997

PhD Thesis: "Video Object Segmentation" (Download low-res version)

Excerpt from the introduction:
More and more visual information is available in digital form, in various places and on various media. The emergence of digital video and its proliferation in multimedia applications has created a significant demand for content-based representation of visual information. Main purpose of video segmentation is to enable content-based representation by extracting objects of interest from a series of consecutive video frames. Briefly, the motivation behind video segmentation can be categorized as the applications in indexing and retrieval, compression and coding, recognition, identification, and understanding of video scenes, editing, manipulation, and animation.

Video databases on the market today allow only limited capability of or domain limited searching for video using characteristics like color, texture, and simpler motion statistics. If video can be stored in the form of individual objects, indexing and retrieval of visual information is as simple as that of textual information. An essential tool in the management of visual records is the ability to automatically describe and index the content of video sequences in a meaningful manner. Such a facility would allow recovery of desired video segments or objects from a very large database of video sequences. The efficient use of stock film archives and identification of specific activities in surveillance videos are among the potential applications.

From a compression point of view, video segmentation is essential for object-based video coding standards, i.e. MPEG-4. Due to the vast data size of video sequences, communicating digital video over the bandwidth limited network sources demands competent coding techniques. Having an object-based representation scheme that identifies the important parts of image frames, video sequences can also be encoded efficiently to satisfy transmission requirements. Videoconferencing is one of the applications that benefit from object-based coding.

Video segmentation is key to many robotic vision applications. Most vision based autonomous vehicles acquire information on their surroundings by analyzing video. Particularly, it is required for high-level image understanding and scene interpretation such as spotting and tracking of special events in surveillance video. For instance, pedestrian and highway traffic can be regularized using density evaluations obtained by segmenting people and vehicles. By object segmentation, speeding and suspicious moving cars, road obstacles, strange activities can be detected. Forbidden zones, parking lots, elevators can be monitored automatically. Gesture recognition as well as visual biometric extraction can be done for user interfaces.

With a good segmentation, it is possible to access and manipulate objects in video. To illustrate, traffic enforcement currently employs supervised video segmentation tools to acquire identity of speeding or trespassing cars. Infotainment industry utilizes video segmentation for editing, manipulating, and animation.

Although the human being can quickly interpret the embedded semantic content from the information carried by different modalities, computer understanding of visual information is still in its primitive stage. Good segmentation tools are crucial to the success of the future standards. But tasks of automatically segmenting image sequences into semantic meaningful objects prove to be very challenging. We have currently a reasonably good understanding of the basic mechanisms underlying visual information processing, still, many questions are still open to investigation, some desperately waiting for an answer.