Showing papers on "Video tracking published in 1990"

Apparatus and method for editing a video recording by selecting and displaying video clips

Abstract: A video editing system comprising a computer system having a mass storage and a display, a video source, such as a video cassette recorder (VCR), camera, or optical disc player, and a video processor/controller linking the computer to the video source. The computer system functions under the direction of standard operating software and video editing software which provide the user with an interface for controlling both playback and clip editing of video information from the video source. Upon initialization of the editing system, the user is presented with at least a video window for displaying the video information, a control window for regulating playback of the video information, and a clip list window having a number of rows of edit windows organized under begin, end, and clip columns. The user controls playback of video from the video source within the video window through manipulation of standard playback direction and speed indicators. To mark a video frame in the video window as either a begin or end point of a video clip, the user clicks on the desired video frame with a mouse associated with the editing system. A small digitized version of the requested video frame is then created and attached to the cursor. This small digitized frame (SDF) can then be moved in tandem with the cursor from the video window to an edit window and released. Begin and end points of clips are created by releasing an SDF within an edit window under the appropriate column. Releasing an SDF within an edit window under the clip column causes that SDF to be entered as both the begin and end point of the clip. Numerous rows of edit windows can be created in a similar manner. When the begin and end edit windows in the same row are filled with different SDFs, the video frames between those respective points are digitized and automatically inserted into the clip column for that row in an animated form. SDFs can likewise be directly manipulated to modify the content or sequence of edit windows or to change the video frame being played within the video window.

Stereoscopic video-graphic coordinate specification system

Abstract: A stereoscopic image generator for superimposing a stereographic pointer video signal onto a composite standard video signal, the genrator comprises a computer for generating the stereographic pointer video signal in response to an input signal representive of the three dimensional coordinates of a point in a three dimensional video image, a video synchronizing circuit for receiving the composite standard video signal and delivering a synchronization signal to the computer, and a video keying circuit for receiving the composite standard video signal and the stereographic pointer video signal and superimposing the stereographic pointer video signal onto the composite standard video signal to produce a single combined video signal, the single combined video signal allowing the stereographic pointer video signal and the composite standard video signal to be viewed together simultaneously on the same video screen.

RAPID - a video rate object tracker.

Abstract: Three-dimensional (3D) Model-Based Vision enables observed image features to be used to determine the pose (ie. position and attitude) of a known 3D object with respect to the camera (or alternatively, the viewpoint of the camera with respect to the model) [1]. The knowledge concerning the object that is used to perform Model-Based Vision is the 3D locations of salient and easily observed object features, such as corners and high-contrast edges (eg. surface marking sand crease edges).

Content oriented visual interface using video icons for visual database systems

Abstract: This paper clarifies the importance of content oriented visual user interfaces using video icons for visual database systems. Effectiveness of both still and live video images, especially for user's browsing and interaction, is shown by usage of the 'MediaBENCH' (hyperMedia Basic ENvironment for Computer and Human interactions) which is a basic prototype multimedia database system. Various methods of handling video data on the MediaBENCH are introduced and discussed to show how video data can be manipulated on visual database systems which deal with spatial and temporal factors. A visual interface using video icons is quite suitable to video editing systems, video mail systems, or other electronic video document systems. Brief application profiles are shown for guidance.

Surveillance systems for automatically recording transactions

Abstract: A system for making and reviewing video recordings of transactions occurring at cashier lanes uses a television camera for developing frames of video signals of the transactions at two or more cashier lanes. A register at each lane generates digital signals representing events that occur at the lanes. A computer responsive to the digital signals generates a digital transaction signal. A VCR records the camera video signal and the computer digital transaction signal on a cassette, the digital transaction signal being recorded in a certain relation (e.g. in synchrony) with the camera video signal and in such a manner as to substantially not affect the clarity of each video frame. In a playback mode, the VCR generates a playback video frame signal, and the computer generates an overlay control signal. An overlay means responsive to various signals generates a composite video signal of an alpha-numeric display of the digital transaction information relating to the desired cashier lane overlaying the video signal, the alpha-numeric information being positioned in the composite video signal so as not to obscure that portion of the video frame that pertains to the desired cashier lane. In another aspect of the invention, a computer responds to the register signals and generates a video storage signal at the start of a subsequent transaction and a transaction summary signal. The overlay means generates a summary snapshot video frame signal comprising alpha-numeric transaction summary information overlaying the picture of the merchandise at the start of the transaction.

Method and apparatus for manipulating digital video data

Abstract: Disclosed is a digital data processing system for scanning, compressing, storing, decompressing, and displaying digital video data (Fig. 3), e.g., full motion video sequences such as those from a color television sequence or still photographs, in real time, e.g., at a rate of 30 frames per second for full motion video. The system operates in a personal computer environment, e.g., Macintosh IIR, using commonly available microprocessors, filing systems, and display units (30).

Autonomous real-time object tracking with an adaptive joint transform correlator

Abstract: A hybrid optical/digital system for tracking an object in a sequence of images is described. Since a joint transform correlator does not require a matched spatial filter in the correlation process, object tracking can be carried out by continuously updating the reference image with the object image in the previous frame. This adaptive property of a joint transform correlator, together with the parallelism and high processing speed of an optical system, ensure high correlation between objects in two sequential frames. The relative position of the object can then be determined based on the location of the correlation peak. System performance is evaluated and experimental demonstrations are presented.

An improved video-based computer tracking systems for soft biomaterials testing

Abstract: An improved video-based computer system is presented for online tracking of small markers moving in a plane. The system consists of a charge-coupled device (CCD) camera, a video monitor, a dedicated 80386/20 microcomputer, a video frame grabber, and custom software. Up to four markers can be tracked at the 30-Hz video frame rate using a two-step, correlation based search procedure. The requisite hardware and software requirements are discussed, and how this tracking system can be used to collect strain data during biaxial stretching tests on planar soft tissues is shown. Operating at 30 Hz, this system is an improvement over those previously reported, which either are slower or yield less information. >

Video signal parocessing apparatus with memory and crossfader

Abstract: A video signal processing apparatus for performing editing of video signals includes a memory into which one field or one frame of a moving picture video signal from a video camera is written and a crossfading circuit, wherein a still picture of the video signal is written in the memory at a selected time or at a time the video camera stops operation. Thereafter, when the video camera resumes operation, the contents of the memory are read out, so that the real moving picture video signal being currently provided by the video camera and the previous still picture video signal read out from the memory are crossfaded. The video signal processing apparatus can also cooperate with a video tape recorder for storing in the memory a still picture derived from the video tape recorder, so that when the video camera starts its operation, the real moving picture video signal produced by the video camera and a still picture video signal from the memory are crossfaded.

Method for storing and reproducing video signals

Abstract: A method for storing and reproducing video signals is described, the picture information of which is structured into video frames. As a means for carrying out such a method, a known hybrid coder can be used which codes the video data coming from a video data source either in accordance with the intraframe principle or the interframe principle for reducing the bit rates. So that the hybrid decoder connected between memory and monitor does not need to run at a higher speed than normal during a fast check (fast forward or fast rewind) it is provided to code a prescribed section, which can be recognised again in isolation, of predetermined video frames in accordance with the so-called intraframe principle during the storage. During an accelerated check of the stored picture information, the prescribed sections are read out and only these are decoded and reproduced on the monitor.

Video frame reduction/reconstruction method and apparatus

Abstract: A method and apparatus for reducing the amount of video information which is transmitted to a receiver, while still enabling the receiver to reconstruct a representation of the original video source material. In a preferred embodiment, a 60 frames per second progressively scanned video signal is transmitted at a 30 frames per second rate accompanied by decoding information. In short, every other frame is deleted and a respective nearest neighbor is selected to represent the deleted frame. This selection is represented by a digital selection information. Thus the transmitted frame information can be reconstructed into the original video source material after decoding with the digital selection information.

A low-latency 60 Hz stereo vision system for real-time visual control

Abstract: The author presents an image acquisition and processing system designed for real-time six-dimensional object tracking with the precise temporal semantics and low latency required for use within the feedback loops of robotic applications. To achieve real-time performance, the system must extract from the image only the information needed to accomplish the task. Successful task performance depends on an integrated system. rather than on a collection of components. The hardware design takes the form of two large complementary VME-compatible cards: TRIAX, capable of simultaneously acquiring and processing two high-resolution video streams, and JIFFE, capable of 20 MFLOPS for the three-dimensional calculations. Algorithms are described that enable the system to track a rectangular solid, intended to track objects held by a robot hand. The algorithms hinge on scanning only small line segments of the image, followed by techniques for reconstructing object location from sparse edge points. The system tracks a cardboard box. >

Apparatus for producing a composite signal from real moving picture and still picture video signals

Abstract: A video signal processing apparatus has an input terminal receiving a real moving picture video signal, for example, from a video camera, a memory for storing at least one field of the real moving picture video signal so as to form a still picture video signal, a key signal generator which may be constituted by an additional memory storing data characteristic of a key picture, and a circuit responsive to reading of the data stored in the additional memory for switching between the real moving picture video signal and the still picture video signal and thereby forming a composite video signal therefrom.

Video-data processor

Abstract: A video-data processor is disclosed in which a video data produced from the laser disk or the like is processed in four stages of video memory. The video data is first A/D converted and written into a first video memory. Then, the video data in the first video memory is subjected to the special effect such as mosaicking and written into a second video memory. A part of the video data in the second video memory is cut out, projected and written into a third video memory, in which the video data, graphics and letters visually projected are combined. A part of the resulting data is cut out, projected and written into a fourth video memory as a window. The data thus projected as a window is displayed on a display unit from the fourth video memory. The visual projection, window projection and the special effect between the video memories are defined to realize the special effect, scroll or partial cut-out of the video data in a multi-window environment. Also, a method is disclosed in which even if there is only one video memory, the definition of the special effect, visual projection and window projection permits computation of the result of the assumed presence of four video memories and realizes the special effect, scroll or partial cut-out of the video data in a multi-window environment.

Features for automated quality assessment of digitally transmitted video

Abstract: This report describes an automated method of video quality assessment based on extraction and classification of features from sampled input and output video. The first subsystem of the automated video quality measurement system is the feature extraction subsystem. Features are extracted from the sampled video that quantify many of the distortions present in modern digital compression and transmission systems. The feature measurements may then be injected into a quality classification subsystem which will determine the overall quality rating of the video. This report discusses the first subsystem of the automated video quality assessment system, namely the feature extraction subsystem. The measurement techniques used to extract a number of useful features are discussed in detail. Results are presented using sampled video teleconferencing data that contained common video compression artifacts.

System and method for eliminating interlace motion artifacts in captured digital video data

Abstract: Analog video data input is received by a video display adapter of a digital video capture system. Most of the resolution of the captured full interlaced image is retained while eliminating the image shake of fast moving components. A first and second sequential field comprising a full frame of video data are captured and digitized. These fields are then processed to determine areas corrupted by fast movement of components of the image which were captured. In the areas of detected fast movement, an estimate for pels is substituted in one field based upon the other field. Resolution loss is thereby confined to small areas which, due to rapid motion, were not well defined prior to processing.

Motion measurement using the Peak Performance Technologies system

Abstract: The motions studied In biomechanics today are Increasingly more complex, requiring spatial, force and myographic measures. The Peak system employs off-the-shelf video equipment and an AT compatible microcomputer to perform spatial and analog data acquisition. Every video field can be analyzed in either NTSC (North American) or PAL (European) video formats. Video sampling rates can vary from 50 to 2000Hz, depending upon the video hardware used. The body locations of interest may be obtained using any of three methods. The manual acquisition method superimposes a colored cursor over the video image and its position is controlled by a handheld mouse. The semi-automatic option controls the initial position of the cursor by predicting the position based upon its location in previous frames. The value of these options is that they can be applied in difficult experimental settings or for digitizing points that are internal to the body (e.g., joint centers). The third method is automatic tracking, which determines the center of area of a marker that contrasts with its immediate background. An individual criterion may be set for each marker to discriminate it from noise, background and other markers. Hidden markers can be treated via manual digitization, interpolation or ignored if seen by other cameras. Once collected, spatial data can be translated and/or rotated with respect to external reference frames, or to internal reference frames within the moving subject. An analog to digital sampling module acquires data from sensors and synchronizes them with the video generated spatial data. Subsequently, complete motion information can be generated rapidly and accurately for countless applications. The performance of the video measurement system was assessed by measuring its precision and accuracy in two dimensional static tests. The precision for manual digitizing was found to be 1 in 2422 and for automatic digitizing, 1 in 5280. The accuracy for manual digitizing was found to be 1 in 3267 and for automatic digitizing, I in 4310.

Eliminating Distance in Scientific Computing: an Experiment in Televisualization

Abstract: The utility of video distribution of visualization results was demonstrated. Phillips had shown this previously in a local area. However, with the satellite connection and projection screen, the authors were able to demonstrate the concept over a long distance to 1,000 people in an evening. This form of image distribution is certainly feasible over campus- or community-wide geographies today. Many academic and industry facilities are already wired for video distribution. One of the authors (R.A.E.) lives in a community where the cable service is implemented with fiber- optic distribution of up to 120 channels. Video displays fully integrated into computer workstations are rapidly becoming a reality. While full-motion video in a window is still expensive, video interfaces at slower rates are readily available. A separate video monitor adjacent to the workstation can also be used. Finally, video compression and decompression techniques make possible transmission at less than the full broadcast bandwidths. The capabilities the authors demonstrated will not become routine until there are wide-geography, fiber-optic networks dedicated to supporting scientific computing. These networks will carry image (both compressed and uncompressed), graphical, and numerical data at high speeds from centralized sources of computation, and image generation to users located around themore » country. The first high-speed network facilities are currently being implemented. The development of computer software and hardware to implement and take advantage of these local networks will prepare us for the day when they can be expanded nationally and internationally.« less

Scrambling video by time shifting

Abstract: A system for scrambling and descrambling the image associated with a video signal employs the shifting in time of a video image after removal of synchronization and color burst reference signals. Coded data which contains information necessary for unscrambling the video image is transmitted in the video signal itself during the vertical blanking interval. A high level of simplification in the decoding is achieved by merely restoring synchronization and color reference data without the need for returning the video image to its original timing. This system provides the significant advantage of permitting unscrambling of the video image using inexpensive circuitry at the decoder end, while affording the operator of the transmitter to select whether the unscrambled signal is recordable using a conventional video tape recorder.

Video signal processing using vector median

Abstract: In the vector median approach the samples of the vector-valued input signal are processed as vectors as opposed to componentwise scalar processing. The VM-type filters utilize the correlation between different components in video signal. This makes the VM-filters attractive in video signal processing. In this paper the performance of vector median filters for color video signals is investigated. Vector median FIR median hybrid filters (VFMH) for cross luma and cross color cancellation are introduced. In the VFMH filter the vector median operation is combined with linear substructures resulting in improved cross color and cross luma attenuation and in very good noise attenuation.

Video signal encoder

Abstract: PURPOSE:To prevent a coding efficiency from being deteriorated with simple constitution by executing an in-frame coding processing when a scene change takes place from an input video signal. CONSTITUTION:When a video signal is sent while being subject to high efficiency coding processing, a scene change caused in a 1st digital video signal S20 is detected based on a difference data S23 between a 1st digital video signal S20 and a 2nd digital video signal S20. Then the video signal from which a scene change is caused is subject to in-frame coding processing. Thus, even when the scene change takes place, the deterioration in the coding efficiency is improved with simple circuit constitution.

Apparatus for generating time information for a frame of video information using interpolation

Abstract: In a time information generator for generating time information in an arbitrary frame of video information varying with changes in time on the basis of time information delivered at a predetermined time interval from a video information forming device for forming video information, there is employed a scheme to discriminate between operational modes of the video information forming device to form, by an interpolative operation, time information in an arbitrary frame of video information from time information delivered from the video information forming device every n (n=2, 3, 4, . . .) frames of video information on the basis of the result indicative of the discriminated operational mode.

Video camera and video recorder arrangement

Abstract: Mechanical and electronic means are commonly provided in video cameras to reduce the effect on the video signal of shocks unintentionally imparted to the camera. The aim of the present invention is to make these means largely independent of the video camera, both in their operation and location. The signal (K) representing the unintentional movements is recorded together with the video signal (V) on the recorder (3) and used during reproduction to modify the video signal (V). Application: portable light-weight camcorders in particular.

Video quality gradient measures for digital networks

Abstract: Two of the most significant video quality degradations produced by digital compression in codecs are image blurring and distortion of edges in areas of motion. These degradations become more evident at reduced transmission rates. Two objective measures of video quality, one based on Laplacian and the other on Sobel gradient operators, are proposed. They are validated with desktop video teleconferencing (VTC) data for digital networks with sequences containing significant motion and complex detail. The measured results are compared over a range of transmission bit rates. The sensitivity and reliability of the measures are enhanced by determining the optimum Gray level thresholds for computing the measures. Both measures correlate well with transmission rate and subjective opinion of the video quality, particularly for blurring. >

Video motion detection for physical security applications

Abstract: Physical security specialists have been attracted to the concept of video motion detection for several years. Claimed potential advantages included additional benefit from existing video surveillance systems, automatic detection, improved performance compared to human observers, and cost-effectiveness. In recent years, significant advances in image-processing dedicated hardware and image analysis algorithms and software have accelerated the successful application of video motion detection systems to a variety of physical security applications. Early video motion detectors (VMDs) were useful for interior applications of volumetric sensing. Success depended on having a relatively well-controlled environment. Attempts to use these systems outdoors frequently resulted in an unacceptable number of nuisance alarms. Currently, Sandia National Laboratories (SNL) is developing several advanced systems that employ image-processing techniques for a broader set of safeguards and security applications. The Target Cueing and Tracking System (TCATS), the Video Imaging System for Detection, Tracking, and Assessment (VISDTA), the Linear Infrared Scanning Array (LISA); the Mobile Intrusion Detection and Assessment System (MIDAS), and the Visual Artificially Intelligent Surveillance (VAIS) systems are described briefly.

Jim Blinn's corner-wonderful world of video (animation)

Abstract: An overview of video animation for computer graphics is given. Signal timing, color encoding, tape formats, tracking, genlocking, time code, editing, VTR communication, and software are covered. Terminology is defined. >

Object Tracking From Image Sequences Using Stereo Camera And Range Radar

Abstract: The problem of estimating the position of and tracking an object undergoing 3-D translational and rotational motion using passive and active sensors is considered. The passive sensor used in this study is a stereo camera, whereas the active is a range radar. Three different estimation approaches are considered. The first involves estimation of the object position by direct registration of stereo images. In the second approach, the Extended Kalman Filter is used for estimation with measurements the stereo images. In the third approach, an integral filter based on stereo images and range radar measurements is used for tracking. The three different approaches are compared via simulation in the tracking of an object undergoing a 3-D motion with random translational and angular acceleration.