1 / 22

Golnaz Abdollahian , Cuneyt M. Taskiran , Zygmunt Pizlo , and Edward J. Delp

C AMERA M OTION -B ASED A NALYSIS OF U SER G ENERATED V IDEO IEEE TRANSACTIONS ON MULTIMEDIA, VOL. 12, NO. 1, JANUARY 2010. Golnaz Abdollahian , Cuneyt M. Taskiran , Zygmunt Pizlo , and Edward J. Delp. I ntroduction.

alina
Download Presentation

Golnaz Abdollahian , Cuneyt M. Taskiran , Zygmunt Pizlo , and Edward J. Delp

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. CAMERA MOTION-BASED ANALYSISOF USER GENERATEDVIDEOIEEE TRANSACTIONS ON MULTIMEDIA, VOL. 12, NO. 1, JANUARY 2010 GolnazAbdollahian, Cuneyt M. Taskiran, ZygmuntPizlo, and Edward J. Delp

  2. Introduction • UGV generally has a rich camera motion structure that is generated by the person taking the video and it is typically unedited and unstructured. • The main application of our system is for mobile devices which have become more popular for recording, sharing, downloading and watching UGV  use computationally efficient methods • We propose a new location-based saliency map which uses camera motion information to determine the saliency values of pixels with respect to their spatial location in the frame.

  3. Motion-based frame labeling • Global Motion Estimation • In the majority of UGV, camera motion is limited to a few operations, e.g. pan, tilt, and zoom; more complex camera movements, such as rotation, rarely occur in UGV • our goal here is to be computationally efficient to be able to target devices with low processing power such as mobile devices • use a simplified three-parameter global camera motion model in the three major directions H :horizontal V : vertical R : radial

  4. Motion-based frame labeling • Template • The iteration stops when a local minimum is found L1 distance between the 2-D template in the current frame and the previous template

  5. Motion-based frame labeling • Motion Classification – support vector machine(SVM) is used • We first classify it as having a zoom or not, using the 3-Dmotion vector as the feature vector • SVM classifiers are trained on an eight-dimensional feature vector derived from the parameters H and V over a temporal sliding window. The size of sliding window is different for blurry(N=7) and shaky(N=31) • The frames that are not labeled as zoom, blurry or shaky are identified as stable motion with no zooms.

  6. Motion-based frame labeling

  7. Temporal video segmentation basedon the useof camera view • Two frames are considered to be correlated if they have overlap with each other • Camera View : a temporal concept defined as a set of consecutive framesthat are all correlated with each other. • View boundaries occur when the camera is displaced or there is a change of viewing angle • To detect view boundaries for temporally segmenting the video ,we defind the displacement vector between frames i and j as

  8. Temporal video segmentation basedon the useof camera view • A boundary frame is flagged whenever the magnitude of the displacement vector, , for the current frame and that for the previously detected boundary frame is larger than • There is a constraint that boundary frame can’t be chosen during intervals labeled as blurry segments.

  9. Keyframe selection • A keyframe should be the frame with the highest subjective importance in the segment in order to represent the segment it is extracted from • Since our intention was to avoid the complex tasks of object and action recognition in our system, our keyframeselection strategy was only based on camera motion factor. • The following frames are selected as keyframes : • The frame after a zoom-in • The frame after a large zoom-out • The frame where the camera is at pause • For segments during which the camera has constant motion, all frames are considered to be of relatively same importance. In this case, the frame closest to the middle of the segment and having the least amount of motion is chosen as the keyframe in order to minimize blurriness

  10. Keyframe Saliency MapsandROI Extraction Combine several saliency map to generate the keyframes saliency maps • color contrast saliency • moving objects saliency map • highlighted faces • location-based saliency map

  11. Color Contrast Saliency Map • Use the RGB color space to generate the contrast-based saliency map • The three-dimensional pixel vectors in RGB space are clustered into a small number of color vectors using generalized Lloyd algorithm (GLA) for vector quantization Pij and q : RGB pixel value Θ : neighborhood of pixel (i,j) (5*5) d : gaussian distance

  12. Moving objectSaliency Map • To determine the moving object saliency map, we examine the magnitude and phase of macro block relative motion vectors • Relative motion vector for the macro block at location (m,n) : • If relative motion below a threshold values -> assign 0 • The motion intensity I and motion phase φ are defined as

  13. Moving object Saliency Map • The phase entropy map, Hp, indicates the regions with inconsistent motion which usually belong to the boundary of the moving object the probability of the kthphase whose value is estimated from the histogram

  14. Location-based saliency map • The direction of the camera motion also has a major effect on the regions where a viewer “looks” in the sequence • The global motion parameters were used to generate the location saliency maps for the extracted keyframes kH,kV,Kr: constant (10,5,0.5) r : distance of a pixel from the center rmax: maximum r in the frame

  15. Location-based saliency map • After combining the H and V maps, the peak of the map function is at • The radial map, SR , is either decreasing or increasing as we move from the center to the borders, depending on whether the camera has a zoom-in/no-zoom or zoom-out operation

  16. Combined saliency map • First, the color contrast and moving object saliency maps are superimposed since they represent two independent factors in attracting visual attention • Faces are detected and highlighted after combining the low level saliency maps • The location-based saliency map is then multiplied pixel-wise with this map to yield the combined saliency map

  17. Identificationof ROIs • A region growing algorithm proposed is usedto extract ROI from the saliency map • Fuzzy partitioning is employed to classify the pixelsinto R1: ROI and R0: insignificant regions • seed selection • 1) the seeds must have maximum local contrast • 2) the seeds should belong to the attended areas

  18. Experimental Results

  19. Experimental Results

  20. Experimental Results left Zoom-out left Zoom-in Zoom-out

  21. Experimental Results

  22. conclusion • UGVs contain rich content-based camera motion structure that can be an indicator of “importance” in the scene • Since camera motion in UGV may have both intentional and unintentional behaviors, we used motion classification as a preprocessing step • A temporal segmentation algorithm was proposed based on the concept of camera views which relates each subshot to a different view • We use a simple keyframeselection strategy based on camera motion patterns to represent each view • we employed camera motion in addition to several other factors to generate saliency maps for keyframes and identify ROIs based on visual attention

More Related