Earticle

Semantic segmentation can be used to analyze the video data taken by UAV in the flood monitoring system. An accurate analysis can help rescue teams to assess and mitigate flood disasters. This paper proposed an improved Efficient Neural Network architecture to segment the UAV video of flood disaster. The proposed method consists of atrous separable convolution as the encoder and depth-wise separable convolution as the decoder. The experimental results reveal that the proposed method outperforms Efficient Neural Networks’ other architecture and gives the highest frame per second.

Based on the analysis of human motion with the development of computer vision technology gradually become the research focus, while intelligent monitoring and other related real needs also contributed to its rapid development, attracting more and more researchers to join them. It includes both limbs motion tracking, as well as tracking the movement of the whole body, but does not include the subtle body movement, such as facial expressions and gestures of the track. The monocular video motion tracking method in this article are used in a variety of models, including the human body geometry, said camera imaging model and motion model used. Geometric model of the human body by the appearance of the model human skeleton model and composition of each joint skeleton model the relative proportions of the length of a value obtained from anthropometric measurements, and the establishment of a local coordinate system at each joint. Camera imaging using fluoroscopy model and a mathematical model based on this request to the relative three-dimensional coordinates of each joint between the sports model based on kinematics knowledge polynomial representation.

Based on analyzing the related technologies of the original video retrieval, we proposed an algorithm of adaptive dual-threshold shot boundary detection for the game video of TV. At the beginning, we convert each frame to the HSV space, set high and low ratio of threshold according to the frame difference. Then, the average value of frame difference in the sliding window is calculated to receive the dual-threshold. Finally, the shot and the gradual are detected by comparing the frame difference and threshold.

Automatic video segmentation plays an important role in real-time MPEG-4 encoding systems. This paper presents a video segmentation algorithm for MPEG-4 camera system with change detection, background registration techniques and real time adaptive threshold techniques. This algorithm can give satisfying segmentation results with low computation load. Besides, it has shadow cancellation mode, which can deal with light changing effect and shadow effect. Furthermore, this algorithm also implemented real time adaptive threshold techniques by which the parameters can be decided automatically.

Image Segmentation is to simplify and/or change the representation of an image into something that is more meaningful and easier to analyze. Pre-processing of the image makes it more clear and visible, while parallelizing of the algorithm optimizes the speed at which the image is processed. This paper presents the performance analysis of parallelizing the video frame segmentation using region growing technique on varying of processors. Region growing Technique is also classified as pixel-based image segmentation method since it involves the selection of initial seed points where determining of whether the pixel neighbors should be added to the region or not is done. The process is iteratively carried out and the region is correspondingly grown for each image. Video is divided into frames, which are passed to different cores. The processing of frames is carried out simultaneously in cores, hence parallelizing the technique. Time analysis for serial and parallel implementation is done. Analysis of time required for processing the frames on different number of cores is carried out.

The basketball segmentation in close shots is studied. According to the consistency of basketball color, color segmentation is implemented. Then with the help of steerable filters, the method detects image edges and the orientations of them. Finally, based on edges and their orientations, Hough transform is improved to get the circle center and the radius of basketball.

In the basketball segmentation in long shots, Gauss filter is adopted to smooth noise in the image firstly. Secondly, the background is separated by the difference of inter-frame and the connected regions are labeled. Thirdly, a strategy is designed to identify basketball by the characteristic of basketball. Finally, the edge deviation is revised and the optimal result is obtained using improved Snakes.

In recent years, the use of video in GIS is considered to be an important subject and many related studies result in VideoGIS. The virtual navigation is an important function that can be applied to various VideoGIS applications. For virtual navigation by video, the following problems must be solved. 1) Because the video route may be not exactly coincided with route that user wants to navigate, parts of several video clips may be required for single navigation. Virtual navigation should allow the user to move from one video to another at the proper position. We suggest the video segmentation method based on geographic data combined with video. 2) From a point to a destination, the change frequency of video must be minimized. The frequent change of video make user to mislead navigation route and cause the wasteful use of computing resource. We suggest methods that structure video segments and calculate weight value of each node and link.

In this paper, we have proposed the efficient algorithm that can segment the video scene change using a various statistical characteristics obtained from by applying the wavelet transformation for each frames. Our method firstly extracts the histogram features from low frequency subband of wavelet-transformed image and then uses these features to detect the abrupt scene change. Second, it extracts the edge information from applying the mesh method to the high frequency subband of transformed image. We quantify the extracted edge information as the values of variance characteristic of each pixel and use these values to detect the gradual scene change. And we have also proposed an algorithm how extract the proper key frame from segmented video scene. Experiment results show that the proposed method is both very efficient algorithm in segmenting video frames and also is to become the appropriate key frame extraction method.

본 논문은 MPEG-4 내용 기반 비디오 코딩을 위한 객체 추출기법을 소개한다. MPEG-4 표준화는 비디오 객체에 대한 접근성, 사용자와 객체의 상호작용, 높은 압축률을 위한 비디오 코딩 알고리즘을 요구한다. 비디오 장면에서

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.

비디오에서 움직이는 객체의 외곽선은 객체를 정확하게 분할하기 위하여 매우 중요하다. 그러나 움직이는 객체의 외곽선에는 단락된 외곽선들이 존재하게 된다. 우리는 단락된 외곽선을 연결할 수 있는 새로운 외곽선 연결 알고리즘을 개발하였다. 외곽선 연결 알고리즘은 단락된 외곽선의 말단 픽셀에 사분면을 형성하고 동심원을 구성하면서 반지름 내에서 다른 말단 픽셀을 찾는 탐색을 전진하면서 수행한다. 외곽선 연결 알고리즘은 객체의 외곽선에서 가장 짧게 외곽선을 연결한다. 그리고 시스템은 비디오로부터 배경을 구하여 저장한다. 시스템은 외곽선 연결로부터 객체 마스크를 생성하고, 배경된 저장으로부터 또 하나의 객체 마스크를 생성하여 이 두 개의 객체 마스크를 보완적으로 사용하여 움직이는 객체를 분할한다. 논문의 주요 장점은 정확한 객체 분할을 위한 새로운 객체 외곽선 연결 알고리즘의 개발이다. 제안된 알고리즘은 개발된 새로운 객체 외곽선 연결 알고리즘과 배경 저장을 이용하여 정확한 객체 분할, 다중 객체 분할, 내부에 구멍이 존재하는 객체의 분할, 가느다란 객체의 분할, 그리고 복잡한 배경을 가진 객체를 자동으로 분할하여 보여주었다. 우리는 알고리즘들을 표준 MPEG-4 실험 영상과 카메라로 입력된 실제 영상을 가지고 실험하였다. 제안된 알고리즘들은 매우 효율이 좋으며 펜티엄-IV 3.4GHz CPU에서 평균적으로 QCIF 영상을 1초당 70.20 프레임 그리고 CIF 영상을 1초당 19.7 프레임을 실시간 객체 응용을 위하여 처리할 수 있다.

Moving object boundary is very important for the accurate segmentation of moving object. We extract the moving object boundary from the moving object edge. But the object boundary shows broken boundaries so we develop a novel boundary linking algorithm to link the broken boundaries. The boundary linking algorithm forms a quadrant around the terminating pixel in the broken boundaries and searches for other terminating pixels to link in concentric circles clockwise within a search radius in the forward direction. The boundary linking algorithm guarantees the shortest distance linking. We register the background from the image sequence using the stationary background filtering. We construct two object masks, one object mask from the boundary linking and the other object mask from the initial moving object, and use these two complementary object masks to segment the moving objects. The main contribution of the proposed algorithms is the development of the novel object boundary linking algorithm for the accurate segmentation. We achieve the accurate segmentation of moving object, the segmentation of multiple moving objects, the segmentation of the object which has a hole within the object, the segmentation of thin objects, and the segmentation of moving objects in the complex background using the novel object boundary linking and the background automatically. We experiment the algorithms using standard MPEG-4 test video sequences and real video sequences of indoor and outdoor environments. The proposed algorithms are efficient and can process 70.20 QCIF frames per second and 19.7 CIF frames per second on the average on a Pentium-IV 3.4GHz personal computer for real-time object-based processing.

In this paper, we propose the color fuzzy decision algorithm to face segmentation in a color image. Our algorithm can segment without the user's interaction by fuzzy decision marking. And it removes small parts such as a noise using wavelet morphology in the image obtained by applying the fuzzy decision algorithm. Also, it merges and chooses the face region in each quantization image through rough sets. This video object division algorithm is shown to be superior to a conventional algorithm.

Multi-view video consists of a set of multiple video sequences from multiple viewpoints or view directions in the same scene. It contains extremely a large amount of data and some extra information to be stored or transmitted to the user. This paper presents inter-view correlations among video objects and the background to reduce the prediction complexity while achieving a high coding efficiency in multi-view video coding. Our proposed algorism is based on object-based segmentation scheme that utilizes video object information obtained from the coded base view. This set of data help us to predict disparity vectors and motion vectors in enhancement views by employing object registration, which leads to high compression and low-complexity coding scheme for enhancement views. An experimental results show that the superiority can provide an improvement of PSNR gain 2.5.3 dB compared to the simulcast.

The numbers of digital video cameras are fast increased. Accordingly, digital video data management is becoming more important. Efficient storing method and fast browsing method still remains to be one of significant issue. In this paper, an optimized data storing process without losing information and an organized appearance features indexing method are proposed. Also, the data removing policy could be used to reduce large amount of space and it facilitates fast sequential search. The appearance features index constructs key information of moving objects to answer queries about what people are doing, particularly when, where and who they move. The evaluation results showed better performance in the transfer time and the saving in storage space.

This paper describes an image segmentation technique for the object-oriented coding at very low bit rates. By noting that, in the object-oriented coding technique, each objects are represented by 3 parameters, namely, shape, motion, and color informations, we propose a segmentation technique, in which the 3 parameters are fully exploited. To achieve this goal, starting with the color space conversion and the noise reduction, the input image is divided into many small regions by the K-menas algorithm on the O-K-S color space. Then, each regions are merged, according to the shape and motion information. In simultations, it is shown that the proposed technique segments the input image into relevant objects, according to the shape and motion as well as the colors. In addition, in order to evaluate the performance of the proposed technique, we introduce the notion of the interesting regions, and provide the results of encoding the image with emphasizing the interesting regions.

본 논문에서는 비디오 저장이나 검색과 같은 비디오 정보 처리를 위한 중요한 기초 연구로써 비디오의 표현을 위한 효과적인 기법을 제안한다. 비디오 데이타 세트는 수초에서 수분 사이의 상연 시간을 갖는 비디오 클립들의 집합이며, 각 비디오 클립은 연속된 비디오 프레임들로 구성되어 있다. 이 비디오 클립은 다차원 데이타 시퀀스(multidimensional data sequence: MDS)로 표현될 수 있으며, 프레임 사이의 시간적인 정보를 고려하여 비디오 세그먼트로 나누어 지고, 한 클립 내에서 서로 유사한 세그먼트들은 다시 비디오 클러스터로 군집화된다. 따라서, 각 비디오 클립은 소수 개의 비디오 클러스터로 표현되어 진다. 본 논문에서 제안한 비디오 세그멘테이션 및 클러스터링 알고리즘 VDCLuster는 사전에 정의된 일정 수준의 클러스터링 품질을 보장하고 있으며, 다양한 비디오 시퀀스에 대한 실험을 통하여 알고리즘의 효과를 입증한다.

In this paper, we investigate video representation techniques that are the foundational work for the subsequent video processing such as video storage and retrieval. A video data set if a collection of video clips, each of which is a sequence of video frames and is represented by a multidimensional data sequence (MDS). An MDS is partitioned into video segments considering temporal relationship among frames, and then similar segments of the clip are grouped into video clusters. Thus, the video clip is represented by a small number of video clusters. The video segmentation and clustering algorithm, VDCluster, proposed in this paper guarantee clustering quality to south an extent that satisfies predefined conditions. The experiments show that our algorithm performs very effectively with respect to various video data sets.

본 논문에서는 고정된 카메라에서 초기 프레임을 참조하여 현재 프레임에 새롭게 유입된 물체의 실시간 분류 방법을 제안한다. 제안한 알고리즘의 실시간 분류 처리를 위하여 복잡도를 최소화 하였다. 먼저 전경과 배경을 구분하는 이진 분류 영상을 추출하기 위하여 DCT(Discrete Cosine Transform) 기법을 사용한다. DCT는 기존 공간영역에서 Texture를 분석하는 방식보다 더욱 정확하게 Texture를 분석할 수 있다. 이는 주파수 영역에서 Texture 특징 분석이 더욱 용이하고 각 요소 안에 intensity와 texture 정보를 종합적으로 고려할 수 있기 때문이다. 또한 DCT 계산 복잡도를 최소화하기 위하여 DCT 수행 전에 색 정보를 이용하여 미리 분류 영역을 분석함으로써 처리 효율을 극대화 하였다. 마지막으로 생성된 이진 분류 영상을 자연스럽게 matting하기 위하여 Guided 필터 사용을 제안한다. Guided 필터는 guidance 정보를 통해 입력 영상을 전반적으로 개선할 수 있지만 intensity가 평탄한 영역 등에서 그 한계를 보여주므로 본 논문에서는 Guided 필터의 단점을 개선하는 방법을 추가적으로 제안한다.

In this paper, we present a novel segmentation method that can extract new foreground objects from a current frame in real-time. It is performed by detecting differences between the current frame and reference frame taken from a fixed camera. We minimize computing complexity for real-time video processing. First DCT (Discrete Cosine Transform) is utilized to generate rough binary segmentation maps where foreground and background regions are separated. DCT shows better result of texture analysis than previous methods where texture analysis is performed in spatial domain. It is because texture analysis in frequency domain is easier than that in special domain and intensity and texture in DCT are taken into account at the same time. We maximize run-time efficiency of DCT by considering color information to analyze object region prior to DCT process. Last we use Guided filter for natural matting of the generated binary segmentation map. In general, Guided filter can enhance quality of intermediate result by incorporating guidance information. However, it shows some limitations in homogeneous area. Therefore, we present an additional method which can overcome them.

비디오 분할의 목적은 같은 내용들을 가지는 프레임들의 순서를 표현하는 각 샷의 비디오 순서 분할을 위한 것이다. 그리고 색인에 대한 각 샷으로부터 키 프레임을 선택한다. 존재하는 비디오 분할 방법들은 2가지 그룹들로 분류될 수 있다. 먼저 경계값이 할당되어야만 하는 샷 전환 검출(SCD) 접근과 클러스터 수의 사전 지식이 요구되는 클러스터 접근이다. 본 논문에서는 컬러-$x^2$명도 히스토그램 기반 FCM(fuzzy c-means) 클러스터링 알고리즘을 사용하는 비디오 분할 방법을 제안하였다. 이 알고리즘은 앞에서 기술한 2가지 접근의 혼합이다. 그리고 이것은 두 가지 접근들의 결점을 극복하도록 설계 되었다. 실험 결과들은 컬러-$x^2$명도 히스토그램 기반 FCM 클러스링 알고리즘이 강건하고 비디오 시퀀스들의 다양한 형태들에 응용할 수 있다고 제안한다.