Automatic segmentation of moving objects in video sequences: a region labeling approach

Tsaig, Y.; Averbuch, Amir

doi:10.1109/tcsvt.2002.800513

Cited by 141 publications

(73 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After segmenting a frame into many regions, a motion tracking and projection algorithm is used to track each region between consecutive frames. Tsaig's algorithm [30] employs similar concepts with watershed and hierarchical region matching. An extension of the conventional watershed transform, 3-D watershed, is proposed by Tsai et al [29], and a Bayesian approach is proposed to merge watershed volumes to form video objects.…”

Section: Analysis Of Existing Algorithmsmentioning

confidence: 99%

“…Ours [7] Gradient, change detection, background registration, post-processing Kim [13] Change detection, watershed Mech [19] Change detection, relaxation, optical flow, edge detection, edge fitting Meier [20] Morphological motion filter, optical flow, Canny edge detection, Hausdorff distance Kim [12] Canny edge detection, morphological operation Wang [32] Multiscale gradient, watershed, motion tacking and projection Tsaig [30] Watershed, hierarchical region matching Tsai [29] 3-D watershed, Bayesian volume merging Shamim [27] Global-to-local motion segmentation, morphology operations Xu [35] Motion segmentation, Canny edge detection, Hausdorff distance, watershed [23]. Motion estimation related operations generate motion field information with motion estimation algorithms.…”

Section: Algorithmmentioning

confidence: 99%

“…Several video segmentation algorithms have been proposed [4,5,7,12,13,19,20,27,29,30,32,35]. Most of these algorithms can be covered by the video segmentation framework proposed in MPEG-4 standard [21], which is shown in Fig.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Reconfigurable Morphological Image Processing Accelerator for Video Object Segmentation

Chien

Chen

2008

J Sign Process Syst

View full text Add to dashboard Cite

Video object segmentation is an important pre-processing task for many video analysis systems. To achieve the requirement of real-time video analysis, hardware acceleration is required. In this paper, after analyzing existing video object segmentation algorithms, it is found that most of the core operations can be implemented with simple morphology operations. Therefore, with the concepts of morphological image processing element array and stream processing, a reconfigurable morphological image processing accelerator is proposed, where by the proposed instruction set, the operation of each processing element can be controlled, and the interconnection between processing elements can also be reconfigured. Simulation results show that most of the core operations of video object segmentation can be supported by the accelerator by only changing the instructions. A prototype chip is designed to support real-time change-detection-andbackground-registration based video object segmentation algorithm. This chip incorporates eight macro processing elements and can support a processing capacity of 6,200 9-bit morphological operations per second on a SIF image. Furthermore, with the proposed tiling and pipelined-parallel techniques, a realtime watershed transform can be achieved using 32 macro processing elements.

show abstract

Section: Analysis Of Existing Algorithmsmentioning

confidence: 99%

Section: Algorithmmentioning

confidence: 99%

See 1 more Smart Citation

Reconfigurable Morphological Image Processing Accelerator for Video Object Segmentation

Chien

Chen

2008

J Sign Process Syst

View full text Add to dashboard Cite

show abstract

“…A variety of models has been proposed including: 2D mesh [30,31], binary model [32], color histogram [29], deformable templates [33], corners and lines [34], active contour [9], 2D regions [35], etc. To localize the object in subsequent frames, a typical approach is to place the model to its possible positions and locate it where the best match is found.…”

Section: Related Workmentioning

confidence: 99%

Applying the multi-category learning to multiple video object extraction

Liu¹,

Zheng

Shen

2008

Pattern Recognition

View full text Add to dashboard Cite

“…In this way, background plane is updated progressively and the moving object is detected by thresholding the difference between the current frame and the registered background plane. A number of other adaptive background models have also been reported [4]- [6]. Although these algorithms produce better modelling towards real world scenarios by background learning process, most of them fail to deal with multi-modal background distribution.…”

Section: Video Segmentation Algorithmsmentioning

confidence: 99%

Hardware Accelerator Design for Video Segmentation with Multi-modal Background Modelling

Jiang

Ardö

Öwall³

2005 IEEE International Symposium on Circuits and Systems

View full text Add to dashboard Cite

Abstract-Among many of the algorithms for video segmentation, one based on statistical background model [1] was developed with the unique feature of robustness in multi-modal background scenarios. However, with large amount of calculations due to pixel wise processing of each frame, such an algorithm could only achieve a low frame rate far from real-time requirements on computers. In this paper, a hardware accelerator is proposed, with a dedicated architecture aiming to address the computation as well as memory bandwidth demand. The whole system is targeted to an FPGA platform, which is served as a real-time test bench where long term effects caused by fixed point quantization and various parameter settings can be studied. Meanwhile, memory bandwidth as well as memory size are investigated and reduction by up to 60 percent through similarity exploitation for neighboring Gaussian parameters is envisioned. Furthermore, an controller synthesis tool is used to relieve the effort for the manual design of complex control unit, scheduling the operations of the whole system.

show abstract

Automatic segmentation of moving objects in video sequences: a region labeling approach

Cited by 141 publications

References 17 publications

Reconfigurable Morphological Image Processing Accelerator for Video Object Segmentation

Reconfigurable Morphological Image Processing Accelerator for Video Object Segmentation

Applying the multi-category learning to multiple video object extraction

Hardware Accelerator Design for Video Segmentation with Multi-modal Background Modelling

Contact Info

Product

Resources

About