Showing papers on "Video tracking published in 1992"

Video editing system operator interface for visualization and interactive control of video material

Abstract: An operator interface for a video editing system provides a visual sense of the content of video sequences, as well as their length, while also providing enhanced interactive control of locations and time alignments of the video. As the video sequence is processed into the system, a small but representative sample of each frame is saved in a local memory, while the video itself is stored in mass storage. These samples are used to provide a video pictorial timeline of the underlying stored video. The location of an operator's view into the video sequence is controlled by a cursor's movement along a detailed video pictorial timeline, a reverse motion area and a forward motion area to provide VTR control for location changes on the video tape. The cursor's movement can be controlled by a mouse or a knob. Icons, either static or dynamic, are produced within the motion areas to indicate the amount of selected velocity. Timelines can be marked with time marks, roughly aligned and then automatically fine aligned by the system according to their respective time markers. The editing results associated with these timelines are also time aligned as a result of this process.

A magnifier tool for video data

Abstract: We describe an interface prototype, the Hierarchical Video Magnifier, which allows users to work with a video source at fine-levels of detail while maintaining an awareness of temporal context. The technique allows the user to recursively magnify the temporal resolution of a video source while preserving the levels of magnification in a spatial hierarchy. We discuss how the ability to inspect and manipulate hierarchical views of temporal magnification affords a powerful tool for navigating, analyzing and editing video streams.

Video merging employing pattern-key insertion

Abstract: Disclosed is a technique for deriving a composite video image by merging foreground and background video image data supplied from a plurality of separate video signal sources employing pattern-key insertion, rather than prior-art color-key insertion, for this purpose. Pattern-key insertion involves replacing a first pattern (202) in a video scene (204A) with a second pattern (204B). This is accomplished by first detecting the first pattern (202) in the video scene and estimating the pose of this detected first pattern with respect to a reference object in the video scene. The second pattern is then geometrically transformed using the pose estimate of the detected first pattern. Finally, the detected first pattern is replaced with the geometrically-transformed second pattern.

Video indexing using motion vectors

Abstract: This paper presents a video indexing method that uses motion vectors to 'identify' video sequences. To visualize and interactively control video sequences, we propose a new video index and corresponding icons. The index is based on the identification of discrete cut points and camera operations made possible by analyzing motion vectors. Simulations and experiments confirm the practicality of the index and icons.© (1992) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.

Model-Based Object Tracking in Traffic Scenes

Abstract: This contribution addresses the problem of detection and tracking of moving vehicles in image sequences from traffic scenes recorded by a stationary camera. In order to exploit the a priori knowledge about the shape and the physical motion of vehicles in traffic scenes, a parameterized vehicle model is used for an intraframe matching process and a recursive estimator based on a motion model is used for motion estimation. The initial guess about the position and orientation for the models are computed with the help of a clustering approach of moving image features. Shadow edges of the models are taken into account in the matching process. This enables tracking of vehicles under complex illumination conditions and within a small effective field of view. Results on real world traffic scenes are presented and open problems are outlined.

Audio/video synchronization for application programs

Abstract: A synchronization process in an application program records audio fields with video synchronization counts, and plays back the audio and video fields in synchronism by tracking the video fields against the video sync counts in the audio fields. The video sync counts correspond to the number of video field processed when the audio field is processed. During recording of audio and video fields for the multimedia presentation, the video fields are counted. The video field count is appended to and recorded with each audio field. During playback, the system compares the count of video fields displayed against the video field count appended to the audio field being presented. If the counts are different, the system either skips video fields, or repeats video fields to bring the video fields into synchronism with the audio fields.

Video game having audio player interaction with real time video synchronization

Abstract: The video game system is configured so that when a player speaks, a video object representing the player in the video game is synchronized with the player's speech in real-time. The audio output is transmitted from the video display unit and is thus associated with having come from the image rather than from the player. The synchronization is accomplished by matching the loudness of syllables in the player's speech with the facial expression of the video object. This video game system includes an audio input means (18) for receiving audio input (19) from a player as well as a video display (10) for displaying video images. Further, the video system includes a data processing means (38) that is programmed to generate and coordinate the activity of the video game. Each player may be provided with a headset (14) that includes a microphone (18) and earphones (16) to facilitate player interaction and interaction with the video game system. The video game system may also include a distortion means for distorting the audio output to reflect the nature of a player's video object. The video game system also provides a method for storing (52, 54, 60) video/audio information for retrieval and play back.

Active object recognition

Abstract: The concept of active object recognition is introduced, and a proposal for its solution is described. The camera is mounted on the end of a robot arm on a mobile base. The system exploits the mobility of the camera by using low-level image data to drive the camera to a standard viewpoint with respect to an unknown object. From such a viewpoint, the object recognition task is reduced to a two-dimensional pattern recognition problem. The system uses an efficient tree-based, probabilistic indexing scheme to find the model object that is likely to have generated the observed data, and for line tracking uses a modification of the token-based tracking scheme of J.L. Crowley et al. (1988). The system has been successfully tested on a set of origami objects. Given sufficiently accurate low-level data, recognition time is expected to grow only logarithmically with the number of objects stored. >

Helicopter virtual image display system incorporating structural outlines

Abstract: A virtual image display system provides video displays based upon virtual images of the external world having synchronized structural outlines superimposed on the video displays to a pilot operating an aircraft such as a helicopter in non-visual flight conditions. The virtual image display system includes a virtual imaging subsystem for generating virtual images of the external world, a video display subsystem for generating video images based upon the virtual images and for displaying the video images for the pilot's viewing, a sensing means for providing signals corresponding to the spatial location and perspective of the video display subsystem, a map comprising structural outlines corresponding to structural members forming the canopy structure of the helicopter, and a computer subsystem providing electronic interfacing between the elements of the virtual image display system, for synchronizing the orientation of the virtual imaging subsystem with the video display subsystem, and for processing the virtual image signals to provide signals to the video display subsystem to generate video displays. The computer utilizes the helmet position signals to define the relative position and orientation of the video display subsystem in the cockpit, and utilizes such definition to reconstruct structural outlines from the map that are synchronized to the perspective of the video images. The synchronized structural images are superimposed upon the video display.

Low power video security monitoring system

Abstract: If motion occurs in an area viewed by a lens (14) of a video camera (12), a video security monitoring system (10) establishes a communication link with a video monitoring facility and begins transmitting compressed video images of the area The system (10) is fabricated from CMOS integrated circuits, and operates at a reduced clock frequency while motion is not detected Reducing the clock frequency lowers the required power thus permitting operation of the system (10) on energy supplied by an ISDN basic access communication channel If motion occurs, a digital video image compression subsystem (16) begins producing low quality compressed video data for transmission to the monitoring facility If motion occurs in the central region of the area viewed by the lens (14), then the subsystem (16) produces a single high quality compressed video image Commands transmitted from the monitoring facility to the video security monitoring system (10) may control its entire operation

Iterative design of video communication systems

Abstract: This paper reviews the design and implementation of several video telephony systems at Bellcore as a case study in iterative design. In contrast to single user compuer applications, communication systems consists of both the interconnection technology and the people who are interconnected. From a user’s point of view, the capabilities provided by the system, the rules for its use, and its reaction to their actions depend jointly on what its developers implemented and how other users behave. This fact has wide-ranging implications for system design, use, and evaluation. In reviewing our design experience, we identify four dilemmas for iterative design that flow from the inherently social nature of communication systems. We conclude with methodological and theoretical suggestions to supplement conventional iterative design principles as applied to communications systems.

Region-Based Tracking in an Image Sequence

Abstract: This paper addresses the problem of object tracking in a sequence of monocular images. The use of regions as primitives for tracking enables to directly handle consistent object-level entities. A motion-based segmentation process based on normal flows and first order motion models provide instantaneous measurements. Shape, position and motion of each region present in such segmented images are estimated with a recursive algorithm along the sequence. Occlusion situations can be handled. We have carried out experiments on sequences of real images depicting complex outdoor scenes.

A window-based editor for digital video and audio

Abstract: The authors present a window-based editor for manipulating digital video and audio The editor supports real-time recording, playback, and editing (cut, copy, and paste) of several multimedia objects Using the X Window system, the authors have implemented the editor on an environment of Sun SPARCstations, and PC-ATs equipped with video compression hardware The user interface of the multimedia editor consists of a main editing window for each display device, and rope windows, which represent synchronized sequences of digital video and audio being accessed, called ropes Experience shows that the editor provides a simple and easy to use, but powerful system for multimedia document preparation, and it can act as a basis for supporting applications such as multimedia mail, electronic distribution of television news and video entertainment, etc >

Object-oriented video: interaction with real-world objects through live video

Abstract: Graphics and live video are widely employed in remotely-controlled systems like industrial plants. Interaction with live video is, however, more limited compared with graphics as users cannot interact with objects being observed in the former. Object-Oriented Video techniques are described allowing object-oriented interactions, including the use of real-world objects in live video as reference cues, direct manipulation of them, and graphic overlays based on them, which enable users to work in a real spatial context conveyed by the video. Users thereby understand intuitively what they are operating and see the result of their operation.

Tracking Moving Contours Using Energy-Minimizing Elastic Contour Models

Abstract: This paper proposes a method for tracking an arbitrary object contour in a sequence of images. In the contour tracking, energy-minimizing elastic contour models are utilized, which is newly presented in this paper. The proposed method makes it possible to establish object tracking even when complex texture and occluding edges exist in or near the target object. We also newly present an algorithm which efficiently solves energy minimization problems within dynamic programming framework. The algorithm enables us to obtain optimal solution even when the variables to be optimized are not ordered.

A miniaturized active vision system

Abstract: The authors have developed a prototype miniaturized active vision system whose sensor architecture is based on a logarithmically structured space-variant pixel geometry. This system integrates a CCD sensor, miniature pan-tilt actuator, controller, general purpose processors and display. Due to the ability of space-variant sensors to cover large work-spaces yet provide high acuity with an extremely small number of pixels, space-variant active vision system architectures provide the potential for radical reductions in system size and cost. The authors describe a prototype space-variant active vision system which performs tasks such as moving object tracking and functions as a video telephone. The potential application domains for systems of this type include vision systems for mobile robots and robot manipulators, traffic monitoring systems, security and surveillance, and consumer video communications. >

Dynamic Visual Feedback Control For A Hand-eye Manipulator

Abstract: This paper proposes a visual feedback control scheme for a manipulator with a camera on the hand. Incorporating the dynamics of the visual information into the manipulator control, we formulate a state space representation of the visual servo mechanism. An optimal control approach to visual servoing is developed based on the state space formulation. The proposed algorithm gives a simple time-invariant state feedback controller, which allows a high sample rate control system. Real-time experiments of object tracking with a PUMA 560 manipulator are conducted to show the validity of the optimal control scheme. Experimental results show the superiority of the proposed approach compared to the conventional visual feedback control algorithms.

System and method for video compression with artifact dispersion control

Abstract: Systems and methods that enable digital video compression techniques to manage and control artifact presence in each compressed frame of the video clip. Wherein specific embodiments are applicable to interframe and intraframe video compression methods and can be used in the compression of digital images and digital video clips. Other embodiments are employable in digital video compression and are applicable to interframe compression methods. A mechanism to increase the amount of video compression, while maintaining video quality that may otherwise be sacrificed with such increases in video compression, by threshold value management to accommodate the human eye's ability to more readily discern local image features or artifacts at central image locations or focused-upon areas, while tolerating, to a greater extent, artifacts dispersed elsewhere in the image.

Hybrid video compression system and method capable of software-only decompression in selected multimedia systems

Abstract: Hybrid compression processes for digital color video data that enables software only playback of the compressed digital video in low-end computers, wherein intraframe and interframe compression techniques are brought together through a sequence of procedures that analyze local frame regions, integrate unique processes with block truncation coding compression, and adopt the advantages of visual pattern image coding for color video. The process determines the appropriate encoding of each local frame region with one of various compression techniques, based upon its image properties. The compression methods retain the fidelity of the original video data to provide high quality video during decompression and reconstruction of high motion and textured video clips, while simultaneously providing sufficient compression and ease of decoding for software-only decompression thereby exhibiting properties that enable good quality video to be displayed in low-end computers.

Method and apparatus for capturing the motion of an object in motion video

Abstract: A method and apparatus for analysing the motion of an object in an motion video in which the frame of a video image (suitably converted to graphics format) is displayed on a video display unit and overlaid by a graphics image including a mouse pointer. The mouse is manipulated by the user to capture the pixel coordinates of the desired object in successive frames of the video thereby providing data which represents the variation in position of the object with time.

Method and apparatus for merging video data signals from multiple sources and multimedia system incorporating same

Abstract: A method for merging first and second digital video signals generated by first (32) and second (40) video controllers, respectively, for merged transmission to a digital video decoder. The first video controller (32) transmits the first digital video signal to the decoder while monitoring the signal of a luminance component which designates the boundary (75) between a first image (74) constructable from the first video signal and a second image (76) constructable from the second video signal. When the luminance component is detected, a colorkey signal is generated by the first video controller (32) and transmitted to the second video controller (40) to initiate transmission of the second digital video signal to the decoder in place of the first digital video signal. The first video controller continues to monitor the first video signal until the absence of the luminance component is detected.

System and method for frame-differencing video compression/decompression using perceptually-constant information and image analysis

Abstract: A frame-differencing based method for coding and decoding color video data suitable for real-time, software-only based decompression and playback in low-end personal computers wherein the computational demands required of a computer microprocessor to implement the method are readily met by microprocessors such as an Intel 80386SX microprocessor running at 16 Mhz. Frame-to-frame differences are detected in a manner analogous to human perception of luminance data, rather than by the differences in the actual numerical video data. This permits greater compression of data without added computational complexity to the decompression process. Image analysis techniques are employed to ameliorate the appearance of the video. A lossless coding method that unifies two separate compressed data entities is used to obtain a greater amount of compression and simultaneously to reduce the computational complexity of the decompression process.

Web defect continuous surveillance system

Abstract: A video surveillance system for monitoring a continuous web of material negotiating the tortuous path through a paper making machine employs a plurality of video cameras for the continuous monitoring of the web arranged in pairs, each pair addressing a different location of interest along the paper making path. All of the cameras are operated using a single external sync signal and produce video output signals which, in turn, are fed to a plurality of video image splitters, each splitting the video output from a pair of cameras. Video recorders are provided for recording and playing back the split video output signals from each video image splitter through video monitors. The system is computer controlled and responsive to input signals indicative of web failure.

Adaptive coding and decoding of frames and fields of video signals

Abstract: Improved compression of digital signals relating to high resolution video images is accomplished by an adaptive and selective coding of digital signals relating to frames and fields of the video images. Digital video input signals are analyzed and a coding type signal is produced in response to this analysis. This coding type signal may be used to adaptively control the operation of one or more types of circuitry which are used to compress digital video signals so that less bits, and slower bit rates, may be used to transmit high resolution video images without undue loss of quality. For example, the coding type signal may be used to improve motion compensated estimation techniques, quantization of transform coefficients, scanning of video data, and variable word length encoding of the data. The improved compression of digital video signals is useful for video conferencing applications and high definition television, among other things.

Method and apparatus for capturing video images

Abstract: Apparatus and method are provided which receive and sample an incoming video image signal asynchronously, and then processes the signal to recover the video image, including video format, for conversion into a preselected video format. The apparatus and methods first sample the video signal using a stable (crystal oscillator) time base clock to reconstruct the frequency of the video signal, i.e., to recover the video format and then using a contrast optimization process to determine the video signal pixel clock rate.

Multiple object tracking system with three level continuous processes

Abstract: Reports a system for detecting human like moving objects in time-varying images. The authors show how it is possible to detect the image trajectories of people moving in ordinary indoor scenes. The system consists of three subprocesses: changing region detection, moving object tracking and movement interpretation. The processes are executed in parallel so hat each one can recover from the others' errors. This ensures the reliable detection of the trajectories in difficult cases such as movement across complicated backgrounds. The authors have built a trial detection system using a parallel image processing system. The details of the trial system and experimental results of walking person detection are described. >

Automatic Face Location to Enhance Videophone Picture Quality

Abstract: New video communication and multi-media products open up a range of machine vision applications, in which the potential size of the market can justify a substantial investment in the development of sophisticated algorithms Face location can be used to enhance the subjective performance of videophones, while still conforming with international video compression standards This paper gives an overview of the location techniques employed, describes a red-time implementation, and presents the results of the subjective tests which confirmed the improvement in picture quality

Object tracking apparatus and method of camcorder

Abstract: An object tracking apparatus and method of a camcorder which can detect the travelling object and can automatically track the object for shooting by utilizing infra-red incident upon light receiving element from the object. Two embodiments of the object tracking apparatus and method thereof can detect the moving direction of an object so that the shooting direction of a camcorder can be caused to change by comparing mutually the changing electrical signals as the output of a photoelectric converter which converts the light incident from the object to electrical signals changes according to the movement of an object.