• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.27 no.3A
• /
• pp.268-275
• /
• 2002

This paper proposes a region-based segmentation algorithm fur extracting a video object by using the cost of potential of frame-difference energies. In the first step of a region-based segmentation using spatial intensity, each frame is segmented into a partition of homogeneous regions finely so that each region does not contain the contour of a video object. The fine partition is used as an initial partition for the second step of spatio-temporal segmentation. In spatio-temporal segmentation, the homogeneity cost for each pair of adjacent regions is computed which reflects the potential between the frame-difference energy on the common contour and the frame-difference energy of the lower potential region of the two. The pair of adjacent regions whose cost is minimal then is searched. The two regions of minimum cost ale merged, which result in updating the partition. The merging is recursively performed until only the contours remain which have Same difference energies of high potential. In the fecal step of post-processing, the video object is extracted removing the contours inside the object.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.40 no.5
• /
• pp.303-311
• /
• 2003

Since the MPEG-4 visual standard enables content-based functionalities, it is necessary to extract video object from natural video sequences. Segmentation algorithms can largely be classified into automatic segmentation and user-assisted segmentation. In this paper, we propose a user-assisted VOP generation method based on the geometric active contour. Since the geometric active contour, unlike the parametric active contour, employs the level set method to evolve the curve, we can draw the initial curve independent of the shape of the object. In order to generate the edge function from a smoothed image, we propose a vector-valued diffusion process in the LUV color space. We also present a discrete 3-D diffusion model for easy implementation. By combining the curve shrinkage in the vector field space with the curve expansion in the empty vector space, we can make accurate extraction of visual objects from video sequences.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.41 no.4
• /
• pp.9-21
• /
• 2004

The current paper proposes a genetic algorithm (GA)-based segmentation method that can automatically extract and track moving objects. The proposed method mainly consists of spatial and temporal segmentation; the spatial segmentation divides each frame into regions with accurate boundaries, and the temporal segmentation divides each frame into background and foreground areas. The spatial segmentation is performed using chromosomes that evolve distributed genetic algorithms (DGAs). However, unlike standard DGAs, the chromosomes are initiated from the segmentation result of the previous frame, then only unstable chromosomes corresponding to actual moving object parts are evolved by mating operators. For the temporal segmentation, adaptive thresholding is performed based on the intensity difference between two consecutive frames. The spatial and temporal segmentation results are then combined for object extraction, and tracking is performed using the natural correspondence established by the proposed spatial segmentation method. The main advantages of the proposed method are twofold: First, proposed video segmentation method does not require any a priori information second, the proposed GA-based segmentation method enhances the search efficiency and incorporates a tracking algorithm within its own architecture. These advantages were confirmed by experiments where the proposed method was success fully applied to well-known and natural video sequences.

• JSTS:Journal of Semiconductor Technology and Science
• /
• v.12 no.2
• /
• pp.175-185
• /
• 2012

Predictive watershed transform is a popular object segmentation algorithm which achieves a speed-up by identifying image regions that are different from the previous frame and performing object segmentation only for those regions. However, incorrect segmentation is often generated by the predictive watershed transform which uses only local information in merge-split decision on boundary regions. This paper improves the predictive watershed transform to increase the accuracy of segmentation results by using the additional information about the root of boundary regions. Furthermore, the proposed algorithm is processed in a block-based manner such that an image frame is decomposed into blocks and each block is processed independently of the other blocks. The block-based approach makes it easy to implement the algorithm in hardware and also permits an extension for parallel execution. Experimental results show that the proposed watershed transform produces more accurate segmentation results than the predictive watershed transform.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.1C
• /
• pp.92-101
• /
• 2004

This paper proposes a algorithm to extract the variety region (object) from video for the real-time encoding of MPEG-4 based. The previous object segmentation methods cannot used the videophone or videoconference required by real-time processing. It is difficult to transfer a video to real-time because it increased complexity for the operation of each pixel on the spatial segmentation and temporal segmentation method proposed by MPEG-4 Working Group. But algorithm proposed for this thesis not operates a pixel unit but operates a macro block unit. Thus this enables real-time transfer. But this algorithm cannot extract several object for a image using proposed algorithm as previous algorithm. On system constructed by encoder and decoder. A proposed algorithm inserted for encoder as pre-process.

• Journal of KIISE:Software and Applications
• /
• v.33 no.10
• /
• pp.851-861
• /
• 2006

The paper proposes a novel unsupervised video object segmentation algorithm for image sequences with low depth-of-field (DOF), which is a popular photographic technique enabling to represent the intention of photographer by giving a clear focus only on an object-of-interest (OOI). The proposed algorithm largely consists of two modules. The first module automatically extracts OOIs from the first frame by separating sharply focused OOIs from other out-of-focused foreground or background objects. The second module tracks OOIs for the rest of the video sequence, aimed at running the system in real-time, or at least, semi-real-time. The experimental results indicate that the proposed algorithm provides an effective tool, which can be a basis of applications, such as video analysis for virtual reality, immersive video system, photo-realistic video scene generation and video indexing systems.

• Proceedings of the IEEK Conference
• /
• 2006.06a
• /
• pp.299-300
• /
• 2006

In this paper, we propose a segmentation algorithm which combines the ideas from local watershed transforms and the region merging algorithm based hierarchical queue. Only the process of watershed and region merging algorithm can be restricted area. A fast region merging approach is proposed to extract the video object from the regions of watershed segmentation. Results show the effectiveness and convenience of the approach.

• Journal of Broadcast Engineering
• /
• v.21 no.5
• /
• pp.782-791
• /
• 2016

The object segmentation algorithm from the background could be used for object recognition and tracking, and many applications. To segment objects, this paper proposes a method that refer to several initial frames with real-time processing at fixed camera. First we suggest the probability model to segment object and background and we enhance the performance of algorithm analyzing the color consistency and focus characteristic of camera for several initial frames. We compensate the segmentation result by using human skeleton characteristic among extracted objects. Last the proposed method has the applicability for various mobile application as we minimize computing complexity for real-time video processing.

• Journal of Broadcast Engineering
• /
• v.25 no.7
• /
• pp.1081-1094
• /
• 2020

With the recent development of deep learning, most computer vision-related tasks are being solved with deep learning-based network technologies such as CNN and RNN. Computer vision tasks such as object detection or object segmentation use intermediate features extracted from the same backbone such as Resnet or FPN for training and inference for object detection and segmentation. In this paper, an experiment was conducted to find out the compression efficiency and the effect of encoding on task inference performance when the features extracted in the intermediate stage of CNN are encoded. The feature map that combines the features of 256 channels into one image and the original image were encoded in HEVC to compare and analyze the inference performance for object detection and segmentation. Since the intermediate feature map encodes the five levels of feature maps (P2 to P6), the image size and resolution are increased compared to the original image. However, when the degree of compression is weakened, the use of feature maps yields similar or better inference results to the inference performance of the original image.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.12 no.4
• /
• pp.115-121
• /
• 2016

Recently, it has become an important problem to extract semantic objects from videos, which are useful for improving the performance of video compression and video retrieval. In this thesis, an automatic extraction method of moving objects of interest in video is suggested. We define that an moving object of interest should be relatively large in a frame image and should occur frequently in a scene. The moving object of interest should have different motion from camera motion. Moving object of interest are determined through spatial continuity by the AMOS method and moving histogram. Through experiments with diverse scenes, we found that the proposed method extracted almost all of the objects of interest selected by the user but its precision was 69% because of over-extraction.