Possible projects

 

1. Object-Tracking Develop an algorithm to track an object in a video scene. Examples including tracking a soccer ball in a soccer game, cars driving down a street, or people moving in a room. The algorithm may be fully automatic, or semi-automatic where the user initializes the algorithm by telling it where the object(s) is (are) in the first frame. (groups of 2-3 students)

References:

  1. Terrence Chen, Mei Han, Wei Hua, Yihong Gong and Thomas S. Huang, “A New Tracking Technique: Object Tracking and Identification from Motion,” LNCS Volume 2756/2003.
  2.  J. Berclaz, F. Fleuret, P. Fua,  “Multiple Object Tracking using Flow Linear Programming,” EPFL / IDIAP, Technical Report, Nr. 10, June 2009.
  3. Hidekazu Iwaki, Gaurav Srivastava, Akio Kosaka, Johnny Park, and Avinash Kak, “A Novel Evidence Accumulation Framework for Robust Multi Camera Person Detection,” ACM/IEEE International Conference on Distributed Smart Cameras, 2008.
  4. Ruth Devlaeminck, "Human Motion Tracking With Multiple Cameras Using a Probabilistic Framework for Posture Estimation,"  Master's Thesis, School of Electrical and Computer Engineering, Purdue University, August 2006. 
  5. Mazzeo, P.L.   Spagnolo, P.   Leo, M.   D'Orazio, T.  , “Visual Players Detection and Tracking in Soccer Matches” Advanced Video and Signal Based Surveillance, 2008. AVSS '08. IEEE Fifth International Conference on
    Publication Date: 1-3 Sept. 2008.
  6. Tao Zhao, Ram Nevatia, "Tracking Multiple Humans in Crowded Environment," IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'04) - Volume 2, 2004.

2. Motion Estimation Compare different algorithms for performing motion estimation. Algorithms may include different methods for gradient-based and/or block-based estimation, single-layer versus multi-layer estimation, Advanced algorithms (global motion estimation, mesh-based, object-based) Comparison criteria could include closeness to the true motion in the scene, performance when used for compression (e.g. energy in MC-prediction error), and complexity. (group of 2 students)

References:

  1. Efficient block-matching motion estimation based on Integral frame attributes,
    IEEE CSVT 16, No. 3, March 2006, pp. 375-385.
  2. Tseng, S.Y.[Shou-Yi],  Motion estimation using a frame-based adaptive thresholding approach, RealTimeImg(10), No. 1, February 2004, pp. 1-7.
  3. Minoo, K.[Koohyar], Nguyen, T.Q.,  Reciprocal Subpixel Motion Estimation: Video Coding With Limited Hardware Resources, IEEE CSVT 17, No. 6, June 2007, pp. 707-718.
  4. Liu, S.W.[Shao-Wei], Wei, S.D.[Shou-Der], Lai, S.H.[Shang-Hong],
    Fast Optimal Motion Estimation Based on Gradient-Based Adaptive Multilevel Successive Elimination, IEEE CSVT 18, No. 2, February 2008, pp. 263-267.
  5. Nisar, H.[Humaira], Choi, T.S.[Tae-Sun],  Multiple initial point prediction based search pattern selection for fast motion estimation, Pattern Recognition(42), No. 3, March 2009, pp. 475-486.
  6. Lee, H.S.[Hwal-Suk], Jung, J.H.[Jik-Han], Park, D.J.[Dong-Jo],
    An effective successive elimination algorithm for fast optimal block-matching motion estimation, ICIP08(1984-1987).

 

3. Seam Carving Seam carving is an effective technique for content aware image retargeting. A naive extension of seam carving to video is to treat each video frame as an image and resize it independently. Instead of this design an algorithm that treats treat video as a 3D cube and extend seam carving from 1D paths on 2D images, to 2D manifolds in a 3D volume. Develop an algorithm for combined image plus depth seam carving. (group of 2 students)

 

References:

 

  1. http://www.seamcarving.com/
  2. Michael Rubinstein, Ariel Shamir and Shai Avidan, ”Improved Seam Carving for Video Retargeting,” ACM Transactions on Graphics (SIGGRAPH), volume 27, number 3, 2008.
  3. Vikas Ramachandra, Matthias Zwicker, Truong Q. Nguyen, "Combined image plus depth seam carving for multiview 3D images,"  IEEE International Conference on Acoustics, Speech and Signal Processing, 2009, pp.737-740,

 

 

Restoration and Noise Reduction Develop an algorithm to deblur a (blurred or out of focus) video signal and reduce other artifacts (e.g. motion picture film is often afflicted by scratches and salt-and-pepper noise). (group of 1 student)

References:

1.      Bhagavathy, S.   Llach, J. , Adaptive Spatio-Temporal Video Noise Filtering for High Quality Applications, ICASSP 2007.

2.      Szostakowski J.: Genetic filters for video noise reduction, Machine Graphics & Vision International Journal, vol 15, no 3, 2006.

 

5. Video Stabilization Handheld video cameras are often afflicted by unintentional camera movement. Develop an algorithm that identifies this unintentional movement and compensates for it.  (group of 1 student)

References:

  1. Feng Liu, Michael Gleicher, Hailin Jin and Aseem Agarwala. Content-Preserving Warps for 3D Video Stabilization, ACM Transactions on Graphics (Proceedings of SIGGRAPH 2009), 2009.
  2. Ken-Yi Lee, Yung-Yu Chuang, Bing-Yu Chen, Ming Ouhyoung, Video Stabilization using Robust Feature Trajectories. Proceedings of IEEE International Conference on Computer Vision 2009 (ICCV 2009), pp. 1397-1404, September 2009, Kyoto, Japan.

6. Error control in video transport: Error resilient video coding, Error concealment techniques, Video over Internet, Video over peer to peer networks. (groups of 2 students)

References:

  1. Xinguang Xiang, Debin Zhao, Qiang Wang, Xiangyang Ji, and Wen Gao, A Novel Error Concealment Method For Stereoscopic Video Coding, The 14th IEEE International Conference on Image Processing, San Antonio, Texas, pp.101-104, Sep.16-19, 2007.
  2. Song, K., Chung, T., Oh, Y., and Kim, C. 2009. Error concealment of multi-view video sequences using inter-view and intra-view correlations. J. Vis. Comun. Image Represent. 20, 4 (May. 2009), 281-292.

7. Video analysis and summarization: Video shot/scene segmentation, Key frame selection, Video retrieval based on motion/color similarity. (groups of 2 students)

References:

  1. Liu, T.Y.[Tie-Yan], Lo, K.T.[Kwok-Tung], Zhang, X.D.[Xu-Dong], Feng, J.[Jian],
    A new cut detection algorithm with constant false-alarm ratio for video segmentation, JVCIR(15), No. 2, June 2004, pp. 132-144.
  2. Bescos, J., Cisneros, G., Menendez, J.M.,  Multidimensional comparison of shot detection algorithms, ICIP02(II: 401-404).
  3. Yuan, J., Wang, H., Xiao, L., Zheng, W., Li, J., Lin, F., Zhang, B.,  A Formal Study of Shot Boundary Detection, IEEE CirSysVideo(17), No. 2, February 2007, pp. 168-186.
  4. Murai, Y.[Yosuke], Fujiyoshi, H.[Hironobu],  Shot boundary detection using co-occurrence of global motion in video stream, ICPR08(1-4).