Multiple Video Frames Research Articles

Semi-Automatic Video Object Segmentation Using LVQ with Color and Spatial Features

This paper presents a semi-automatic algorithm for video object segmentation. Our algorithm assumes the use of multiple key video frames in which a semantic object of interest is defined in advance with human assistance. For video frames between every two key frames, the specified video object is tracked and segmented automatically using Learning Vector Quantization (LVQ). Each pixel of a video frame is represented by a 5-dimensional feature vector integrating spatial and color information. We introduce a parameter K to adjust the balance of spatial and color information. Experimental results demonstrate that the algorithm can segment the video object consistently with less than 2% average error when the object is moving at a moderate speed.

Salient stills

Salient Stills are a class of images that reflect the aggregation of the temporal changes that occur in a moving-image sequence with the salient features of individual frames preserved. They convey the intended expression of an entire series of moving frames---a visual summary of camera and object movements. The original frames, which may include variations in focal length or field of view, or moving objects, are combined to create a single still image. The still image may have multiresolution patches, a larger field of view, or higher overall resolution than any individual frame in the original image sequence. Salient Stills may also contain selected significant objects from individual or multiple video frames. Salient Stills attempt to retain much of the original content (detail) and spatial and temporal extent (context) of the original video or film sequence.

Robust color histogram descriptors for video segment retrieval and identification

Effective and efficient representation of color features of multiple video frames or pictures is an important yet challenging task for visual information management systems. Key frame-based methods to represent the color features of a group of frames (GoF) are highly dependent on the selection criterion of the representative frame(s), and may lead to unreliable results. We present various histogram-based color descriptors to reliably capture and represent the color properties of multiple images or a GoF. One family of such descriptors, called alpha-trimmed average histograms, combine individual frame or image histograms using a specific filtering operation to generate robust color histograms that can eliminate the adverse effects of brightness/color variations, occlusion, and edit effects on the color representation. We show the efficacy of the alpha-trimmed average histograms for video segment retrieval applications, and illustrate how they consistently outperform key frame-based methods. Another color histogram descriptor that we introduce, called the intersection histogram, reflects the number of pixels of a given color that is common to all the frames in the GoF. We employ the intersection histogram to develop a fast and efficient algorithm for identification of the video segment to which a query frame belongs. The proposed color histogram descriptors have been included in the ISO standard MPEG-7 after extensive evaluation experiments.

Three-dimensional bubbly flow measurement using PIV

The experimental flow visualization tool, Particle Image Velocimetry (PIV), is being extended to determine the velocity fields in three-dimensional, two-phase fluid flows. In the past few years, the technique has attracted quite a lot of interest. PIV enables fluid velocities across a region of a flow to be measured at a single instant in time in the whole volume (global) of interest. This instantaneous velocity profile of a given flow field is determined by digitally recording particle (microspheres or bubbles) images within the flow over multiple successive video frames and then conducting flow pattern identification and analysis of the data. This paper presents instantaneous velocity measurements in various three-dimensional, bubbly two-phase flow situations. This information is useful for developing or improving existing computer constitutive models that simulate this type of flow field. It is also useful for understanding the detailed structure of two-phase flows.

Increasing spatial resolution through temporal super-sampling of digital video

A general method is outlined to increase the spatial resolution of digital video sequences containing uncontrolled camera motion. This is accomplished by combining multiple frames of video into a composite image of a higher spatial sampling rate than the original video. Fundamental to this technique is the computation of optical flow. This technique has the greatest impact on camera systems where the focal plane array spatially undersamples the projected optical image. Implicit to the technique is the potential trade-off between frame rate, latency, and display resolution in a digital imaging system.

Fluorescent Vesicle System: A New Technique for Measuring Blood Flow in the Retina

To measure blood flow in the retinal circulation and optic nerve head capillaries with an innovative fluorescent vesicle system. Carboxyfluorescein was encapsulated into liposomes; the vesicles ranged from 0.1 to 2 microns in diameter. After intravenous injection of the liposome suspension, the fundus was viewed using a scanning laser ophthalmoscope. Images of the fundus showing circulating liposomes were stored on videotape. An image analyzing system was used to digitize the captured video frames and transfer them to a computer's hard disk for permanent storage. Software developed in the authors' laboratory allowed them to overlay multiple video frames to create a single image that provided a visible record of the path taken by a particular vesicle in a given time period. The information on this image was used to calculate the velocity of the vesicle, and hence the velocity of the blood flow in the vessel. With this system, individual liposomes as small as 100 nm were visible in all retinal vessels (arteries, capillaries, and veins). Quantitative analysis of vesicle movement in the major retinal vessels of the cynomolgus monkey yielded an average velocity of 9.33 +/- 1.67 mm/second in a large vein (diameter, 130 microns) and 16.10 +/- 5.7 mm/second in a large retinal artery (diameter, 64 microns). The average velocity in the macular capillaries was 0.76 mm/second (range, 0.45-1.33 mm/second), whereas the average velocity in the optic nerve head capillaries was 1.39 mm/second (range, 0.96-2.25 mm/second). The fluorescent vesicle system can be used for simultaneous measurement of blood flow in the retinal arteries, veins, and capillaries of the macula and optic nerve.

Full-field bubbly flow velocity measurements using a multiframe particle tracking technique

The study is an examination of two-phase dispersed air bubble flow about a cylindrical conductor emitting a constant heat flux. The technique of Particle Image Velocimetry is utilized in order to obtain a full-field non-invasive measurement of the resulting bubbly flow velocity field. The employed approach utilizes a flow visualization technique in which the instantaneous velocity profile of a given flow field is determined by digitally recording particle or bubble images within the flow over multiple successive video frames and then conducting a completely computational analysis of the data. The use of particle tracking algorithms which perform a point-by-point matching of seed images from one frame to the next allows construction of particle or bubble pathlines and instantaneous velocity field. Results were initially obtained for a synthetically created flow field and a single phase liquid convective field seeded with flow-following tracer particles. The method was additionally extended to measurements within a gas/liquid system in which bubble rise velocities over a substantial two-dimensional flow area were determined in order to demonstrate the effectiveness of the developed digital data acquisition and analysis methodology.

Investigation of basic imaging properties in digital radiography. 7. Noise Wiener spectra of II-TV digital imaging systems.

We used Wiener spectral analysis in order to investigate the different noise sources and the effects of various parameters such as pixel size, image intensifier (II) field size, and exposure level on the noise in an II-TV digital system. The digital Wiener spectra in terms of relative x-ray intensity were determined directly from the digital noise data in terms of pixel values, by use of the characteristic curve of the imaging system. From averaged, subtracted, and/or combination images, the amount of structure mottle relative to the amount of quantum mottle was estimated. We found that a substantial amount of structure mottle was included in our II-TV digital subtraction angiography system, whereas the electronic noise of the TV system was quite small relative to the quantum and structure mottle. The effects of time jitter on the noise in single-frame images (consisting of multiple video frames) and in subtracted and averaged images were also investigated.