19.3.4.12 Moving Object Extraction Using Edges

Chapter Contents (Back)
Object Segmentation. Sequence Analysis. Motion Segmentation.

Mutch, K.M.[Kathleen M.], and Thompson, W.B.[William B.],
Analysis of Accretion and Deletion at Boundaries in Dynamic Scenes,
PAMI(7), No. 2, March 1985, pp. 133-138. BibRef 8503
Earlier: Univ. of MinnesotaTR 84-7, Computer Science Dept, May 1984. Analysis of the changes (adding and removing) in regions at boundaries when one object moves relative to the other. This can give the optic flow data for the region near the boundary. BibRef

Thompson, W.B.,
Combining Motion and Contrast for Segmentation,
PAMI(2), No. 6, November 1980, pp. 543-549. Brightness is used for static segmentation then merge regions based on motion similarities.
See also Velocity Determination in Scenes Containing Several Moving Objects. BibRef 8011

Thompson, W.B., and Pong, T.C.,
Detecting Moving Objects,
IJCV(4), No. 1. January 1990, pp. 39-58.
Springer DOI BibRef 9001
Earlier: ICCV87(201-208). Several different restricted techniques are developed for motion detection using camera motion or scene structure and flow fields. BibRef

Kim, B.G.[Byung-Gyu], Kim, D.J.[Do-Jong], Park, D.J.[Dong-Jo],
Novel precision target detection with adaptive thresholding for dynamic image segmentation,
MVA(12), No. 5, 2001, pp. 259-270.
Springer DOI 0103

See also Fast image segmentation based on multi-resolution analysis and wavelets. BibRef

Kim, B.G.[Byung-Gyu], Park, D.J.[Dong-Jo],
Novel target segmentation and tracking based on fuzzy membership distribution for vision-based target tracking system,
IVC(24), No. 12, 1 December 2006, pp. 1319-1331.
Elsevier DOI 0610
Image segmentation, Target detection, Three-dimensional feature; Fuzzy membership value, Optimal membership value BibRef

Kim, B.G.[Byung-Gyu], Park, D.J.[Dong-Jo],
Novel Noncontrast-Based Edge Descriptor for Image Segmentation,
CirSysVideo(16), No. 9, September 2006, pp. 1086-1095.
IEEE DOI 0610
BibRef

Kim, B.G.[Byung-Gyu], Park, D.J.[Dong-Jo],
Unsupervised video object segmentation and tracking based on new edge features,
PRL(25), No. 15, November 2004, pp. 1731-1742.
Elsevier DOI 0411
Track regions for coding applications. BibRef

Kim, B.G.[Byung-Gyu], Mah, P.S.[Pyeong-Soo], Park, D.J.[Dong-Jo], Jung, J.H.[Jik-Han], Park, J.S.[Ju-Seok],
Non-contrast based edge descriptor for image segmentation,
ICPR04(I: 572-575).
IEEE DOI 0409
BibRef

Pundlik, S.J.[Shrinivas J.], Birchfield, S.T.[Stanley T.],
Real-Time Motion Segmentation of Sparse Feature Points at Any Speed,
SMC-B(37), No. 3, June 2007, pp. 731-742.
IEEE DOI 0711
BibRef
Earlier:
Motion Segmentation at Any Speed,
BMVC06(I:427).
PDF File. 0609
BibRef

Pundlik, S.J.[Shrinivas J.], Birchfield, S.T.[Stanley T.],
Motion-Based View-Invariant Articulated Motion Detection and Pose Estimation Using Sparse Point Features,
ISVC09(I: 425-434).
Springer DOI 0911
BibRef
Earlier:
Joint tracking of features and edges,
CVPR08(1-6).
IEEE DOI 0806
BibRef

Direkoglu, C.[Cem], Nixon, M.S.[Mark S.],
Moving-edge detection via heat flow analogy,
PRL(32), No. 2, 15 January 2011, pp. 270-279.
Elsevier DOI 1101
BibRef
And:
Shape Extraction Via Heat Flow Analogy,
ACIVS07(553-564).
Springer DOI 0708
BibRef
Earlier:
Low Level Moving-Feature Extraction Via Heat Flow Analogy,
ISVC06(I: 243-252).
Springer DOI 0611
Moving-edges, Feature extraction, Image processing, Heat flow BibRef

Direkoglu, C.[Cem], Nixon, M.S.[Mark S.],
Shape classification via image-based multiscale description,
PR(44), No. 9, September 2011, pp. 2134-2146.
Elsevier DOI 1106
BibRef
Earlier:
Image-Based Multiscale Shape Description Using Gaussian Filter,
ICCVGIP08(673-678).
IEEE DOI 0812
Shape classification, Fourier-based description, Multiscale representation, Gaussian filter, Feature extraction BibRef

Subudhi, B.N.[Badri Narayan], Nanda, P.K.[Pradipta Kumar], Ghosh, A.[Ashish],
A Change Information Based Fast Algorithm for Video Object Detection and Tracking,
CirSysVideo(21), No. 7, July 2011, pp. 993-1004.
IEEE DOI 1107
BibRef

Subudhi, B.N.[Badri Narayan], Nanda, P.K.[Pradipta Kumar], Ghosh, A.[Ashish],
Entropy based region selection for moving object detection,
PRL(32), No. 15, 1 November 2011, pp. 2097-2108.
Elsevier DOI 1112
Object detection, MAP estimation, Simulated annealing, Entropy; Thresholding, Gaussian distribution
See also Change detection for moving object segmentation with robust background construction under Wronskian framework.
See also Integration of Gibbs Markov Random Field and Hopfield-Type Neural Networks for Unsupervised Change Detection in Remotely Sensed Multitemporal Images. BibRef

Subudhi, B.N.[Badri Narayan], Veerakumar, T., Esakkirajan, S., Ghosh, A.[Ashish],
Kernelized Fuzzy Modal Variation for Local Change Detection From Video Scenes,
MultMed(22), No. 4, April 2020, pp. 912-920.
IEEE DOI 2004
Principal component analysis, Surveillance, Kernel, Visualization, Probability density function, Object detection, Jamming, modal variation BibRef

Ghosh, A.[Ashish], Subudhi, B.N.[Badri Narayan], Ghosh, S.,
Object Detection From Videos Captured by Moving Camera by Fuzzy Edge Incorporated Markov Random Field and Local Histogram Matching,
CirSysVideo(22), No. 8, August 2012, pp. 1127-1135.
IEEE DOI 1208
BibRef

Subudhi, B.N.[Badri Narayan], Nanda, P.K.[Pradipta Kumar],
An Evolutionary Based Slow and Fast Moving Video Object Detection Scheme Using Compound Markov Random Field Model,
ICCVGIP08(398-405).
IEEE DOI 0812
BibRef

Panda, S.[Sucheta], Nanda, P.K.,
Unsupervised Color Image Segmentation Using Compound Markov Random Field Model,
PReMI09(291-296).
Springer DOI 0912
BibRef


Chen, K., Wang, J., Yang, S., Zhang, X., Xiong, Y., Loy, C.C., Lin, D.,
Optimizing Video Object Detection via a Scale-Time Lattice,
CVPR18(7814-7823)
IEEE DOI 1812
Lattices, Object detection, Detectors, Image edge detection, Spatial resolution, Computational efficiency, Pipelines BibRef

Yang, Y.C.[Ying-Chun], Peng, Y.C.[Yu-Chen], Han, S.D.[Shou-Dong],
Video segmentation based on patch matching and enhanced Onecut,
ICIVC17(346-350)
IEEE DOI 1708
Color, Image color analysis, Image edge detection, Optical imaging, Optical noise, Optical sensors, Shape, enhanced onecut, local classifier, patch matching, video, segmentation BibRef

Vantaram, S.R.[Sreenath Rao], Saber, E.[Eli],
Unsupervised video segmentation by dynamic volume growing and multivariate volume merging using color-texture-gradient features,
ICIP12(305-308).
IEEE DOI 1302
BibRef

Danielsson, O.[Oscar], Carlsson, S.[Stefan],
Generic Object Class Detection Using Feature Maps,
SCIA11(348-359).
Springer DOI 1105
BibRef
Earlier:
Generic Object Class Detection Using Boosted Configurations of Oriented Edges,
ACCV10(II: 1-14).
Springer DOI 1011
BibRef

Danielsson, O.[Oscar], Carlsson, S.[Stefan], Sullivan, J.[Josephine],
Automatic learning and extraction of multi-local features,
ICCV09(917-924).
IEEE DOI 0909
BibRef
Earlier:
Object Detection Using Multi-local Feature Manifolds,
DICTA08(612-618).
IEEE DOI 0812
Each feature a collection of local features. BibRef

Zhang, J.S.[Jia-Shu], Zhang, L., and Tai, H.M.[Heng-Ming],
Efficient video object segmentation using adaptive background registration and edge-based change detection techniques,
ICME04(II: 1467-1470). BibRef 0400

Hwang, T.L., Clark, J.J.[James J.],
On local detection of moving edges,
ICPR90(I: 180-184).
IEEE DOI 9006
BibRef

Chapter on Motion Analysis -- Low-Level, Image Level Analysis, Mosaic Generation, Super Resolution, Shape from Motion continues in
Moving Object Extraction with Moving Cameras .


Last update:Mar 16, 2024 at 20:36:19