← Back to Patent Explorer
EP0596409A2 Expired / Lapsed EP ⏱️ 0.0 years remaining

Detecting apparatus of motion vector

Assignee: Panasonic Holdings Corp
•
Filing: 1993-10-28
•
Granted: —
•
Expires: 2013-10-28
📄 Original PDF 🌐 Google Patents 🔄 Sync Now

Abstract

Abstract 57 By expanding technique of detection of motion vector of time-space differential method, (1) repetitive calculations are not needed, (2) different motion vectors near boundary of object can be detected, and (3) coupling of region segmentation and framework is enabled. For this, a horizontal direction differentiating filter (104), a vertical direction differentiating filter (105), and a time direction differentiating filter (106) calculate the time-space differential (∂l/∂x, ∂l/∂y, ∂l/∂t) in formula (2) necessary for motion vector estimation in every pixel. A feature vector combining part (110) generates a sample vector coupling the time-space differential value and position for random imageposition (x, y), and clusters from pairs of samples and classes to minimize the difference in a maximum likelihood class determining part (112) and a maximum likelihood class data changing part (113). The motion vector is obtained from the third eigen vector of covariance matrix of the time-space differential value.

Inventors

  • 👤 Minoru Etoh

Bibliographic Details

Application Number —
Jurisdiction EP
Data Source google_patents
Last Synchronized 2026-11-08 09:30
CPC Classifications
H; H04; H04N; H04N19/00; H04N19/50; H04N19/503; H04N19/51; G; G06; G06T; G06T7/00; G06T7/20; G06T7/269; G06T7/277

Claims Analysis

Total Claims: 4
Claim 1
Independent Claim 281 words
A detecting apparatus of motion vector comprising: (a) a memory (102,103) for holding video signals which are coded and composed of frame units, (b) a horizontal differentiating filter (104) for reading out luminance data from the memory and differentiating (executing a differential method ) or differencing (executing a difference method) in a horizontal direction of arbitrary image coordinates, (c) a vertical differentiating filter (105) for reading out luminance datafrom the memory and differentiating or differencing in the vertical direction of the image coordinates, (d) a time differentiating filter(106)for reading out the luminance data of preceding and succeeding frames from the memory, and differentiating or differencing in a time direction, (e) feature vector combining means (110) for combining luminance differential vector (lx, ly, It) comprising results of the horizontal differentiating filter, the vertical differentiating filter and the time differentiating filter, and position vector (x, y) of the image coordinates ,to obtain a sample vector, (f) a memory (114) for holding a plurality of an estimation of a motion vector (u, v) and a position vector mean (x, y) of the sample vector as class data, (g) nearest class determining means (112) for determining a distance between the class data and the sample vector from a formula (x-x, y-y) and a formula (ulx + v * ly + It), and achieving a correspondence between the sample vector and nearest class data, and (h) class data changing means (113)for changing the class data in a manner that a distance sum between the class data and one or more sample vectors becomes smaller, from one or more sample vectors and the class data of which correspondence has been achieved by the nearest class determining means.
Claim 2
Dependent Claim 281 words
A detecting apparatus of motion vector comprising: (a) a memory (102,103) for holding video signals which are coded and composed of frame units, (b) a horizontal differentiating filter (104) for reading out luminance data from the memory and differentiating (executing a differential method ) or differencing (executing a difference method) in a horizontal direction of arbitrary image coordinates, (c) a vertical differentiating filter (105) for reading out luminance datafrom the memory and differentiating or differencing in the vertical direction of the image coordinates, (d) a time differentiating filter(106)for reading out the luminance data of preceding and succeeding frames from the memory, and differentiating or differencing in a time direction, (e) feature vector combining means (110) for combining luminance differential vector (lx, ly, It) comprising results of the horizontal differentiating filter, the vertical differentiating filter and the time differentiating filter, and position vector (x, y) of the image coordinates ,to obtain a sample vector, (f) a memory (114) for holding a plurality of an estimation of a motion vector (u, v) and a position vector mean (x, y) of the sample vector as class data, (g) nearest class determining means (112) for determining a distance between the class data and the sample vector from a formula (x-x, y-y) and a formula (ulx + v * ly + It), and achieving a correspondence between the sample vector and nearest class data, and (h) class data changing means (113)for changing the class data in a manner that a distance sum between the class data and one or more sample vectors becomes smaller, from one or more sample vectors and the class data of which correspondence has been achieved by the nearest class determining means.
Claim 3
Dependent Claim 326 words
A detecting apparatus of motion vector comprising: (a) a memory for holding video signals which are coded and composed of frame units, (b) a horizontal differentiating filter for reading out luminance data from the memory and differentiating (executing a differential method ) or differencing (executing a difference method) in a horizontal direction of arbitrary image coordinates, (c) a vertical differentiating filter for reading out luminance data from the memory and differentiating or differencing in the vertical direction of the image coordinates, (d) a time differentiating filter for reading out the luminance data of preceding and succeeding frames from the memory, and differentiating or differencing in a time direction, (d) sample vector combining means for reading out color data consisting of an array of one or more luminance values differing in color from the memory, combining (a) the color data, (b) luminance differential vector (lx, ly, It) comprising results of the horizontal differentiating filter, the vertical differentiating filter and the time differentiating filter , and (c) position vector (x, y) of the image coordinates , to obtain sample vector, (e) a memory for holding a plurality of a position vector mean (x, y) , an estimation of a motion vector (u, v) ,and a mean of the color data of the sample vector , as class data, (f) nearest class determining means for determining a distance between the class data and the sample vector from a formula of (x-x, y-y) ,a formula of (u * lx + v * ly + It) and a difference between the color data and color data mean, and achieving a correspondence between the sample vector and nearest class data, and (g) class data changing means for changing the class data in a manner that a distance sum between the class data and one or more sample vectors becomes smaller, from one or more sample vectors and the class data of which correspondence has been achieved by the nearest class determining means.
Claim 4
Dependent Claim 326 words
A detecting apparatus of motion vector comprising: (a) a memory for holding video signals which are coded and composed of frame units, (b) a horizontal differentiating filter for reading out luminance data from the memory and differentiating (executing a differential method ) or differencing (executing a difference method) in a horizontal direction of arbitrary image coordinates, (c) a vertical differentiating filter for reading out luminance data from the memory and differentiating or differencing in the vertical direction of the image coordinates, (d) a time differentiating filter for reading out the luminance data of preceding and succeeding frames from the memory, and differentiating or differencing in a time direction, (d) sample vector combining means for reading out color data consisting of an array of one or more luminance values differing in color from the memory, combining (a) the color data, (b) luminance differential vector (lx, ly, It) comprising results of the horizontal differentiating filter, the vertical differentiating filter and the time differentiating filter , and (c) position vector (x, y) of the image coordinates , to obtain sample vector, (e) a memory for holding a plurality of a position vector mean (x, y) , an estimation of a motion vector (u, v) ,and a mean of the color data of the sample vector , as class data, (f) nearest class determining means for determining a distance between the class data and the sample vector from a formula of (x-x, y-y) ,a formula of (u * lx + v * ly + It) and a difference between the color data and color data mean, and achieving a correspondence between the sample vector and nearest class data, and (g) class data changing means for changing the class data in a manner that a distance sum between the class data and one or more sample vectors becomes smaller, from one or more sample vectors and the class data of which correspondence has been achieved by the nearest class determining means.

References Cited (Backward Citations)

No citation records indexed.

USPTO Annuity & Maintenance Windows

Maintenance schedule is calculated for granted US utility patents.

Assigned Categories & Tags

No categories assigned to this patent yet.

Assign Category Tag