The Experts below are selected from a list of 24819 Experts worldwide ranked by ideXlab platform

Yun Q. Shi - One of the best experts on this subject based on the ideXlab platform.

  • Unified Optical Flow Field approach to motion analysis from a sequence of stereo images
    Pattern Recognition, 1994
    Co-Authors: Yun Q. Shi, C. Q. Shu, J.n. Pan
    Abstract:

    Abstract In this paper a new approach to motion analysis from stereo image sequences using unified temporal and spatial Optical Flow Field (UOFF) is reported. That is, based on a four-frame rectangular model and the associated six UOFF Field quantities, a set of equations is derived from which both position and velocity can be determined. It does not require feature extraction and correspondence establishment, which are known to be difficult, and only partial solutions suitable for simplistic situations have been developed. Furthermore, it is capable of detecting multiple moving objects even when partial occlusion occurs, and is potentially suitable for nonrigid motion analysis. Unlike the current existing techniques for motion analysis from stereo imagery, the recovered motion by using this new approach is for a whole continuous Field instead of only for some features. It is a purely Optical Flow approach. Two experiments are presented to demonstrate the feasibility of the approach.

  • Direct recovering of Nth order surface structure using unified Optical Flow Field
    Pattern Recognition, 1993
    Co-Authors: C. Q. Shu, Yun Q. Shi
    Abstract:

    Abstract There are two different approaches for estimation of structure and/or motion of objects from image sequences in the computer vision community today. One is the Optical Flow approach, and the other is the feature correspondence approach. There are many difficulties and limitations encountered with the feature correspondence method, while the Optical Flow method requires a substantial amount of extra calculations if the Optical Flow is to be computed as an intermediate step. Direct methods have been developed, that use the Optical Flow approach, but avoid computing the full Optical Flow Field as an intermediate step for recovering structure and motion. The unified Optical Flow Field (UOFF) theory was recently established. It is an extension of the Optical Flow formulations to the temporal-spatial domain. In this paper, a direct method is developed to reconstruct the curved surface structure characterized by an N -degree polynomial equation based on the UOFF. It is a direct method since it also directly recovers surface structure, without computing the quantities in the UOFF. However, it is different from the direct method in that it is based on the theoretical framework of the unified spatial-and-temporal Optical Field instead of the Optical Flow Field determined. Hence, the structure is recovered from a given pair of stereo images instead of from a monocular image sequence. Two computer simulations: a sphere which is a second-order surface and an unbounded α-shaped surface which is a third-order one are presented. The fairly good results demonstrate the effectiveness of our direct method using the UOFF. Some numerical consideration and error analysis are also included. Compared with the existing techniques of the direct method where only the first-order surface can be recovered, the new method has made significant progress in the recovery of curved structure.

  • On unified Optical Flow Field
    Pattern Recognition, 1991
    Co-Authors: C. Q. Shu, Yun Q. Shi
    Abstract:

    Abstract A new approach to motion analysis from a sequence of stereo images has been developed recently (C. Q. Shu and Y. Q. Shi, A new approach to motion analysis from a sequence of stereo images, Technical Report No. 18, Electronic Imaging Laboratory, Department of Electrical and Computer Engineering, New Jersey Institute of Technology, Newark, NJ, 1990) in which the Optical Flow determined by B. K. P. Horn and B. G. Schunck (Determining Optical Flow, Artif. Intell . 17 , 185–203, 1981) is extended to a spatial image sequence resulting in a unified Optical Flow Field (UOFF). A set of equations is established to characterize the UOFF. Another set of equations is derived from which 3D motion can be recovered based on the UOFF. There is no need for feature correspondence in the approach. The recovered 3D motion is for a whole continuous Field. It is therefore a purely Optical Flow approach. In this paper, the new concept of the UOFF is presented in a more general and compact manner. This paper discusses two main aspects about the UOFF. Firstly, the brightness function of an image is considered as not only a function of time but also a function of sensor's spatial position. The concept of imaging space is presented as an accurate description of the set of all possible brightness functions. Secondly, the brightness invariance is recognized not only for the time variation but also for the space variation so that the brightness invariance equations for both time and space domains are established. It is noted that the Optical Flow discussed in Horn and Schunck (1981) and the Optical Flow for a spatial image sequence developed in Shu and Shi (1990) are both special cases within the framework of the UOFF.

C. Q. Shu - One of the best experts on this subject based on the ideXlab platform.

  • Unified Optical Flow Field approach to motion analysis from a sequence of stereo images
    Pattern Recognition, 1994
    Co-Authors: Yun Q. Shi, C. Q. Shu, J.n. Pan
    Abstract:

    Abstract In this paper a new approach to motion analysis from stereo image sequences using unified temporal and spatial Optical Flow Field (UOFF) is reported. That is, based on a four-frame rectangular model and the associated six UOFF Field quantities, a set of equations is derived from which both position and velocity can be determined. It does not require feature extraction and correspondence establishment, which are known to be difficult, and only partial solutions suitable for simplistic situations have been developed. Furthermore, it is capable of detecting multiple moving objects even when partial occlusion occurs, and is potentially suitable for nonrigid motion analysis. Unlike the current existing techniques for motion analysis from stereo imagery, the recovered motion by using this new approach is for a whole continuous Field instead of only for some features. It is a purely Optical Flow approach. Two experiments are presented to demonstrate the feasibility of the approach.

  • Direct recovering of Nth order surface structure using unified Optical Flow Field
    Pattern Recognition, 1993
    Co-Authors: C. Q. Shu, Yun Q. Shi
    Abstract:

    Abstract There are two different approaches for estimation of structure and/or motion of objects from image sequences in the computer vision community today. One is the Optical Flow approach, and the other is the feature correspondence approach. There are many difficulties and limitations encountered with the feature correspondence method, while the Optical Flow method requires a substantial amount of extra calculations if the Optical Flow is to be computed as an intermediate step. Direct methods have been developed, that use the Optical Flow approach, but avoid computing the full Optical Flow Field as an intermediate step for recovering structure and motion. The unified Optical Flow Field (UOFF) theory was recently established. It is an extension of the Optical Flow formulations to the temporal-spatial domain. In this paper, a direct method is developed to reconstruct the curved surface structure characterized by an N -degree polynomial equation based on the UOFF. It is a direct method since it also directly recovers surface structure, without computing the quantities in the UOFF. However, it is different from the direct method in that it is based on the theoretical framework of the unified spatial-and-temporal Optical Field instead of the Optical Flow Field determined. Hence, the structure is recovered from a given pair of stereo images instead of from a monocular image sequence. Two computer simulations: a sphere which is a second-order surface and an unbounded α-shaped surface which is a third-order one are presented. The fairly good results demonstrate the effectiveness of our direct method using the UOFF. Some numerical consideration and error analysis are also included. Compared with the existing techniques of the direct method where only the first-order surface can be recovered, the new method has made significant progress in the recovery of curved structure.

  • On unified Optical Flow Field
    Pattern Recognition, 1991
    Co-Authors: C. Q. Shu, Yun Q. Shi
    Abstract:

    Abstract A new approach to motion analysis from a sequence of stereo images has been developed recently (C. Q. Shu and Y. Q. Shi, A new approach to motion analysis from a sequence of stereo images, Technical Report No. 18, Electronic Imaging Laboratory, Department of Electrical and Computer Engineering, New Jersey Institute of Technology, Newark, NJ, 1990) in which the Optical Flow determined by B. K. P. Horn and B. G. Schunck (Determining Optical Flow, Artif. Intell . 17 , 185–203, 1981) is extended to a spatial image sequence resulting in a unified Optical Flow Field (UOFF). A set of equations is established to characterize the UOFF. Another set of equations is derived from which 3D motion can be recovered based on the UOFF. There is no need for feature correspondence in the approach. The recovered 3D motion is for a whole continuous Field. It is therefore a purely Optical Flow approach. In this paper, the new concept of the UOFF is presented in a more general and compact manner. This paper discusses two main aspects about the UOFF. Firstly, the brightness function of an image is considered as not only a function of time but also a function of sensor's spatial position. The concept of imaging space is presented as an accurate description of the set of all possible brightness functions. Secondly, the brightness invariance is recognized not only for the time variation but also for the space variation so that the brightness invariance equations for both time and space domains are established. It is noted that the Optical Flow discussed in Horn and Schunck (1981) and the Optical Flow for a spatial image sequence developed in Shu and Shi (1990) are both special cases within the framework of the UOFF.

J.n. Pan - One of the best experts on this subject based on the ideXlab platform.

  • Unified Optical Flow Field approach to motion analysis from a sequence of stereo images
    Pattern Recognition, 1994
    Co-Authors: Yun Q. Shi, C. Q. Shu, J.n. Pan
    Abstract:

    Abstract In this paper a new approach to motion analysis from stereo image sequences using unified temporal and spatial Optical Flow Field (UOFF) is reported. That is, based on a four-frame rectangular model and the associated six UOFF Field quantities, a set of equations is derived from which both position and velocity can be determined. It does not require feature extraction and correspondence establishment, which are known to be difficult, and only partial solutions suitable for simplistic situations have been developed. Furthermore, it is capable of detecting multiple moving objects even when partial occlusion occurs, and is potentially suitable for nonrigid motion analysis. Unlike the current existing techniques for motion analysis from stereo imagery, the recovered motion by using this new approach is for a whole continuous Field instead of only for some features. It is a purely Optical Flow approach. Two experiments are presented to demonstrate the feasibility of the approach.

Hanshellmut Nagel - One of the best experts on this subject based on the ideXlab platform.

  • matching object models to segments from an Optical Flow Field
    European Conference on Computer Vision, 1996
    Co-Authors: Henner Kollnig, Hanshellmut Nagel
    Abstract:

    The temporal changes of gray value structures recorded in an image sequence contain significantly more information about the recorded scene than the gray value structures of a single image. By incorporating Optical Flow estimates into the measurement function, our 3D pose estimation process exploits interframe information from an image sequence in addition to intraframe aspects used in previously investigated approaches. This increases the robustness of our vehicle tracking system and facilitates the correct tracking of vehicles even if their images are located in low contrast image areas. Moreover, partially occluded vehicles can be tracked without modeling the occlusion explicitly. The influence of interframe and intraframe image sequence data on pose estimation and vehicle tracking is discussed systematically based on various experiments with real outdoor scenes.

Michael Brady - One of the best experts on this subject based on the ideXlab platform.

  • self calibration of the intrinsic parameters of cameras for active vision systems
    Computer Vision and Pattern Recognition, 1993
    Co-Authors: Michael Brady
    Abstract:

    A new technique for the calibration of the intrinsic parameters of cameras for active vision systems is presented. By making deliberate camera motions, the intrinsics of the cameras can be calibrated based either on the positional difference of Optical Flow Field (PDOFF) or the trajectories of features (TOF) on the image plane. A way to detect the distortion of a camera lens is also presented. The calibration method is simple, fast, reliable, and very easy to combine with task performing processes. The performance of the technique is illustrated. The method can be used for general calibration of camera intrinsics. >

  • CVPR - Self-calibration of the intrinsic parameters of cameras for active vision systems
    Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, 1
    Co-Authors: Michael Brady
    Abstract:

    A new technique for the calibration of the intrinsic parameters of cameras for active vision systems is presented. By making deliberate camera motions, the intrinsics of the cameras can be calibrated based either on the positional difference of Optical Flow Field (PDOFF) or the trajectories of features (TOF) on the image plane. A way to detect the distortion of a camera lens is also presented. The calibration method is simple, fast, reliable, and very easy to combine with task performing processes. The performance of the technique is illustrated. The method can be used for general calibration of camera intrinsics. >