Input Video Frames Research Articles

Dynamosaicing: Mosaicing of Dynamic Scenes

This paper explores the manipulation of time in video editing, enabling to control the chronological time of events. These time manipulations include slowing down (or postponing) some dynamic events while speeding up (or advancing) others. When a video camera scans a scene, aligning all the events to a single time interval will result in a panoramic movie. Time manipulations are obtained by first constructing an aligned space-time volume from the input video, and then sweeping a continuous 2D slice (time front) through that volume, generating a new sequence of images. For dynamic scenes, aligning the input video frames poses an important challenge. We propose to align dynamic scenes using a new notion of "dynamics constancy", which is more appropriate for this task than the traditional assumption of "brightness constancy". Another challenge is to avoid visual seams inside moving objects and other visual artifacts resulting from sweeping the space-time volumes with time fronts of arbitrary geometry. To avoid such artifacts, we formulate the problem of finding optimal time front geometry as one of finding a minimal cut in a 4D graph, and solve it using max-flow methods.

가상 객체 합성을 위한 단일 프레임에서의 안정된 카메라 자세 추정

본 논문에서는 실시간 증강현실 시스템에서의 가상 객체 삽입을 위한 빠르고 안정된 카메라 자세 추정 방법을 제안한다. 단일 프레임에서 마커의 특징점 추출을 통해 카메라의 회전행렬과 이동벡터를 추정한다. 카메라 자세 추정을 위해 정사영 투영모델에서의 분해기법을 사용한다. 정사영 투영모델에서의 분해기법은 객체의 모든 특징점의 깊이좌표가 동일하다고 가정하기 때문에 깊이좌표의 기준이 되는 참조점의 설정과 점의 분포에 따라 카메라 자세 계산의 정확도가 달라진다. 본 논문에서는 실제 환경에서 일반적으로 잘 동작하고 융통성 있는 참조점 설정 방법과 이상점 제거 방법을 제안한다. 제안된 카메라 자세추정 방법에 기반하여 탐색된 마커 위치에 가상객체를 삽입하기 위한 비디오 증강 시스템을 구현하였다. 실 환경에서의 다양한 비디오에 대한 실험 결과, 제안된 카메라 자세 추정 기법은 기존의 자세추정 기법만큼 빠르고 기존의 방법보다 안정적이고 다양한 증강현실 시스템 응용에 적용될 수 있음을 보여주었다. This Paper describes a fast and stable camera pose estimation method for real-time augmented reality systems. From the feature tracking results of a marker on a single frame, we estimate the camera rotation matrix and the translation vector. For the camera pose estimation, we use the shape factorization method based on the scaled orthographic Projection model. In the scaled orthographic factorization method, all feature points of an object are assumed roughly at the same distance from the camera, which means the selected reference point and the object shape affect the accuracy of the estimation. This paper proposes a flexible and stable selection method for the reference point. Based on the proposed method, we implemented a video augmentation system that inserts virtual 3D objects into the input video frames. Experimental results showed that the proposed camera pose estimation method is fast and robust relative to the previous methods and it is applicable to various augmented reality applications.

An Unsupervised Approach for Video Text Localization

A new video text localization approach is proposed. First, some pre-processing techniques, including color space conversion and histogram equalization, are applied to the input video frames to obtain the enhanced gray-scale images. Features are then extracted using wavelet transform to represent the texture property of text regions. Next, an unsupervised fuzzy c-means classifier is performed to discriminate candidate text pixels from background. Effective operations such as the morphological dilation operation and logical AND operation are applied for locating text blocks. A projection analysis technique is then employed to extract text lines. Finally, some geometric heuristics are used to remove noise regions and refine location of text lines. Experimental results indicate that the proposed approach is superior to other three representative approaches in term of total detection rate.

Subband video coding with scene-adaptive hierarchical motion estimation

This paper presents a new motion-compensated subband video-coding technique using variable reference-frame positions for motion estimation. The work builds on temporal segmentation for determining the reference-frame positions and incorporates multiresolution motion estimation in the subband domain. The key advantage of the new algorithm is the complexity reduction in motion estimation that uses the multiresolution property of subband decomposition. Temporal segmentation is performed with the lowest spatial subband, based on the detection of two types of scene change. The frames of input video are split into seven spatial subbands, and the motion vectors for each subband are generated by a hierarchical motion-estimation algorithm. Blockwise differential pulse code modulation (DPCM) and a uniform quantizer are used for the lowest subband of the first frame only, and the subbands of all other cases are coded by PCM with a dead zone quantizer. Simulation results show that our scene-adaptive scheme compares favorably with a fixed interpolation structure.