US5495536A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Image processing system and method for recognizing and removing shadows from the image of a monitored scene
Assignee: National Technology and Engineering Solutions of Sandia LLC
•
Filing: 1991-05-08
•
Granted: 1996-02-27
•
Expires: 2011-05-08
Abstract
Abstract The shadow contrast sensitivity of the human vision system is simulated by configuring information obtained from an image sensor so that the information may be evaluated with multiple pixel widths in order to produce a machine vision system able to distinguish between shadow edges and abrupt object edges. A second difference of the image intensity for each line of the image is developed and this second difference is used to screen out high frequency noise contributions from the final edge detection signals. These edge detection signals are constructed from first differences of the image intensity where the screening conditions are satisfied. The positional coincidence of oppositely signed maxima in the first difference signal taken from the right and the second difference signal taken from the left is used to detect the presence of an object edge. Alternatively, the effective number of responding operators (ENRO) may be utilized to determine the presence of object edges.
Inventors
- 👤 Gordon C. Osbourn
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-09 12:02
CPC Classifications
G; G06; G06T; G06T7/00; G06T7/10; G06T7/12; G06V; G06V10/00; G06V10/20; G06V10/26; G06V10/273; G06T2207/00; G06T2207/10; G06T2207/10016
Claims Analysis
Total Claims: 71
Claim 1
Independent Claim
75 words
In an image processing system, a method of distinguishing object edges from shadows in a monitored scene comprising: a) configuring a video sensor to multiple pixel widths to simulate the shadow contrast sensitivity of the human vision system; b) receiving an image with said configured video sensor to produce a received video signal; and c) processing said received video signal to monitor image contrast to distinguish between object edges and mach edges produced by shadows.
Claim 2
Dependent Claim
75 words
In an image processing system, a method of distinguishing object edges from shadows in a monitored scene comprising: a) configuring a video sensor to multiple pixel widths to simulate the shadow contrast sensitivity of the human vision system; b) receiving an image with said configured video sensor to produce a received video signal; and c) processing said received video signal to monitor image contrast to distinguish between object edges and mach edges produced by shadows.
Claim 3
Independent Claim
129 words
A device-implemented method of differentiating between object edges and mach edges produced by shadows in a video image containing shadows defined by an image signal produced by an image formed of a plurality of image pixels arranged in a two dimensional array comprising: a) determining the image intensity of each image pixel of the video image; b) monitoring at least an approximation of the first derivative of intensity of said monitored scene to produce edge detection signals; and c) screening said edge detection signals using at least an approximation of the second derivative of intensity of the monitored scene to suppress high frequency aliasing; said steps b) and c) of monitoring and screening distinguishing between object edges and mach edges produced by shadows to identify shadows within the image.
Claim 4
Independent Claim
129 words
A device-implemented method of differentiating between object edges and mach edges produced by shadows in a video image containing shadows defined by an image signal produced by an image formed of a plurality of image pixels arranged in a two dimensional array comprising: a) determining the image intensity of each image pixel of the video image; b) monitoring at least an approximation of the first derivative of intensity of said monitored scene to produce edge detection signals; and c) screening said edge detection signals using at least an approximation of the second derivative of intensity of the monitored scene to suppress high frequency aliasing; said steps b) and c) of monitoring and screening distinguishing between object edges and mach edges produced by shadows to identify shadows within the image.
Claim 5
Dependent Claim
132 words
An image processing system which distinguishes object edges from shadows in a video image of a monitored scene, formed of a plurality of image pixels arranged in a two dimensional array, comprising: means, receiving said video image, for assembling adjacent pixels in said video image to form pixel groups of pixel width Δ, said assembly means assembling said adjacent pixels to varying values of pixel width Δ; pixel image signal production means for determining the image intensity of each image pixel group of said image to produce pixel group image signals for each pixel width Δ assembled by said assembly means; and processing means for processing said pixel group image signals for each pixel width Δ to monitor image contrast to distinguish between object edges and mach edges in said video image.
Claim 6
Dependent Claim
132 words
An image processing system which distinguishes object edges from shadows in a video image of a monitored scene, formed of a plurality of image pixels arranged in a two dimensional array, comprising: means, receiving said video image, for assembling adjacent pixels in said video image to form pixel groups of pixel width Δ, said assembly means assembling said adjacent pixels to varying values of pixel width Δ; pixel image signal production means for determining the image intensity of each image pixel group of said image to produce pixel group image signals for each pixel width Δ assembled by said assembly means; and processing means for processing said pixel group image signals for each pixel width Δ to monitor image contrast to distinguish between object edges and mach edges in said video image.
Claim 7
Dependent Claim
39 words
The method of claim 1 wherein said step a) configures said video sensor to each of a plurality multiple pixel widths Δ, said step c) of processing the image intensity signal for each of said multiple pixel widths Δ.
Claim 8
Dependent Claim
14 words
The method of claim 1 wherein said video sensor includes a video digitizing board.
Claim 9
Dependent Claim
58 words
The method of claim 4 wherein said step c) of processing includes, i) for each pixel width Δ, taking the first difference of said image intensity signal, DI.sub.Δ (x) first ,second, in first and second opposed directions along each line of said image to form first and second directional edge detection signals associated with each pixel width Δ.
Claim 10
Dependent Claim
58 words
The method of claim 6 wherein said first and second edge detection signals, signal.sub.Δ (x), associated with each pixel width, are screened to reduce the aliasing response of the edge detection operator through use of the second difference of each image intensity signal D 2 I.sub.Δ (x) first ,second, to thereby reduce the influence of high frequency noise.
Claim 11
Dependent Claim
108 words
The method of claim 7 wherein said step of reducing the aliasing response includes, ia) for each pixel width Δ, examining each pixel x of the second difference of each image intensity signal, D 2 I.sub.Δ (x) first ,second, for the following conditions: |D.sup.2 I.sub.Δ (x)|>|D.sup.2 I.sub.Δ (x+Δ/2)|>|D.sup.2 I.sub.Δ (x+Δ)| and, sign (D.sup.2 I.sub.Δ (x))=sign (D.sup.2 I.sub.Δ (x+Δ/2)) , and ib) when said conditions in step ia) are satisfied, developing the first and second directional edge detection signals, signal.sub.Δ (x) first ,second, for each pixel width Δ where: ##EQU3## and I m is the difference between the largest and the smallest intensity values in the image intensity signal.
Claim 12
Dependent Claim
92 words
The method of claim 7 wherein said step c) of processing further includes, ii) summing the first and second directional edge detection signals associated with each pixel width Δ to form first and second total directional edge detection signals, signal(x) first ,second, iii) determining the maxima in each of said first and second total directional edge detection signals, signal(x) first ,second, and iv) detecting the substantial positional coincidence of oppositely signed maxima in both said first and second total directional edge detection signals to detect the presence of a contrast object edge.
Claim 13
Dependent Claim
72 words
The method of claim 8 wherein said image intensity signal corresponds to the intensity of said monitored scene at image pixels which are arranged in a two dimensional array, said step i) of taking the first difference of said image intensity signal processing said image intensity along lines of said array in a first orientation and subsequently along lines of said array arranged in a second orientation non-aligned with said first orientation.
Claim 14
Dependent Claim
19 words
The method of claim 10 wherein said first and second orientations along said array are orthogonal rows and columns.
Claim 15
Dependent Claim
42 words
The method of claim 9 wherein said step c) of processing further includes, v) determining that there are no additional maxima closely proximate to the positionally coincident maxima detected by said step iv) to verify that an object edge has been detected.
Claim 16
Dependent Claim
90 words
The method of claim 7 wherein, in said step i), each of said first and second edge detection signals, signal.sub.Δ (x) first ,second, for each pixel width Δ is considered an edge operator, said step c of processing further including, ii) for each x, determining the number of edge operators which exceed a threshold to determining the number of responding operators at each position along each line, and iii) detecting the presence of an object edge at x by determining whether the number of responding operators exceeds a predetermined level.
Claim 17
Dependent Claim
29 words
The method of claim 13 wherein said predetermined level in step iii) exceeds the number of operators responding due to high frequency aliasing response of said image intensity signal.
Claim 18
Dependent Claim
14 words
The method of claim 13 wherein the number of responding operators, ENRO=(Σ Signal.sub.Δ)/max{Signal.sub.Δ }.
Claim 19
Dependent Claim
93 words
The method of claim 13 wherein said step c) of processing further includes, iv) summing the first and second directional edge detection signals associated with each pixel width Δ to form first and second total directional edge detection signals, signal(x) first ,second, v) determining the maxima in each of said first and second total directional edge detection signals, signal(x) first , second, and vi) detecting the substantial positional coincidence of oppositely signed maxima in both said first and second total directional edge detection signals to further establish the presence of an object edge.
Claim 20
Dependent Claim
43 words
The method of claim 16 wherein said step c) of processing further includes, vii) determining that there are no additional maxima closely proximate to the positionally coincident maxima detected by said step iv) to further verify that an object edge has been detected.
Claim 21
Dependent Claim
23 words
The method of claim 1 further comprising suppressing noise in said image intensity signal without first filtering and blurring the image intensity signal.
Claim 22
Dependent Claim
23 words
The method of claim 1 further comprising selectively suppressing the aliasing response of the operators to reduce noise in said image intensity signal.
Claim 23
Dependent Claim
60 words
The method of claim 19 wherein said step of suppressing the aliasing response of the operators is performed by, i) selecting a signal level above that of said aliasing response to establish an aliasing threshold, and ii) passing only those portions of said image intensity signal which exceed said aliasing threshold to remove high frequency noise components from said signal.
Claim 24
Dependent Claim
30 words
The method of claim 10 wherein said step c) of processing further includes further reducing the aliasing response of the operators to further reduce noise in said image intensity signal.
Claim 25
Dependent Claim
61 words
The method of claim 21 wherein said step of further reducing the aliasing response of the operators is performed by, i) selecting a signal level above that of said aliasing response to establish an aliasing threshold, and ii) passing only those portions of said image intensity signal which exceed said aliasing threshold to remove high frequency noise components from said signal.
Claim 26
Dependent Claim
47 words
The method of claim 4 wherein the ratio of maximum pixel width to minimum pixel width is not greater than three to ensure that the aliasing response for the largest pixel width does not overlap the desired signal components produced by use of the smallest pixel width.
Claim 27
Dependent Claim
19 words
The method of claim 23 wherein each pixel width is substantially an integer multiple of the smallest pixel width.
Claim 28
Dependent Claim
34 words
The method of claim 4 wherein the gradiation of pixel widths is finer than an integer relationship in order of improve sensitivity to high contrast edges without increasing sensitivity to undesired high frequency noise.
Claim 29
Dependent Claim
25 words
The method of claim 4 wherein said step a) of configuring is performed by employing more than one image sensor having differing effective pixel widths.
Claim 30
Dependent Claim
34 words
The method of claim 4 wherein said step a) of configuring is performed by zooming a lens of a single image sensor to provide the image sensor with images having different effective pixel widths.
Claim 31
Dependent Claim
56 words
The method of claim 4 wherein sensitivity to high contrast edges may be improved without increasing sensitivity to undesired high frequency noise by, high pass filtering image information signals related to image intensity to recover the high frequency aliasing components therefrom, thereby producing a noise signal, and subtracting the noise signal from said image information signals.
Claim 32
Dependent Claim
87 words
The method of claim 4 wherein said step c) includes recognizing object edges by, i) taking the first difference of said image intensity signal in first and second opposed directions along each line of said image to form first and second directional edge detection signals, ii) determining the maxima in said first and second directional edge detection signals, and iii) detecting the substantial positional coincidence of oppositely signed maxima in both said first and second directional edge detection signals to detect the presence of an object edge.
Claim 33
Dependent Claim
43 words
The method of claim 29 wherein said step of c) of processing further includes, iv) establishing that there are no additional maxima closely proximate to the positionally coincident maxima detected by said step iii) to verify that an object edge has been detected.
Claim 34
Dependent Claim
58 words
The method of claim 29 wherein said first and second edge detection signals, signal.sub.Δ (x), associated with each pixel width, are screened to reduce the aliasing response of the edge detection operator through use of the second difference of each image intensity signal, D 2 I.sub.Δ (x) first ,second, to thereby reduce the influence of high frequency noise.
Claim 35
Dependent Claim
39 words
The method of claim 31 wherein the second difference D 2 I(x)=I(x)-2I(x+Δ)+I(x+2Δ) where x represents the position within a line of the monitored scene, I is the image intensity, and Δ is the width of a single image pixel.
Claim 36
Dependent Claim
88 words
The method of claim 32 wherein high frequency aliasing suppression is performed by, i) for each pixel width Δ, examining each pixel x of the second difference of each image intensity signal, D 2 I.sub.Δ (x) first ,second, for the following conditions: |D.sup.2 I(x)|>|D.sup.2 I(x+Δ/2)|>|D.sup.2 I(x+Δ)| and, sign (D.sup.2 I(x))=sign (D.sup.2 I(x+Δ/2)) , and ii) developing the first and second directional edge detection signals signal(x) first ,second where: ##EQU4## and I m is the difference between the largest and the smallest intensity values in the image intensity signal.
Claim 37
Dependent Claim
109 words
The method of claim 4 wherein said step c) includes recognizing mach edges by, i) taking the first difference of said image intensity signal in first and second opposed directions along each line of said image to form first and second directional edge detection signals, ii) determining the maxima in said first and second directional edge detection signals, and iii) detecting positionally separated oppositely signed maxima pair within each of said first and second directional edge detection signals and determining the presence of a mach edge by determining whether the maxima pair within said first and second directional edge detection signals are of the same sign and positionally correspond.
Claim 38
Dependent Claim
58 words
The method of claim 34 wherein said first and second edge detection signals, signal.sub.Δ (x), associated with each pixel width, are screened to reduce the aliasing response of the edge detection operator through use of the second difference of each image intensity signal D 2 I.sub.Δ (x) first ,second, to thereby reduce the influence of high frequency noise.
Claim 39
Dependent Claim
40 words
The method of claim 35 wherein the second difference is D 2 I(x)=I(x)-2I(x+Δ)+I(x+2Δ) where x represents the position within a line of the monitored scene, I is the image intensity, and Δ is the width of a single image pixel.
Claim 40
Dependent Claim
88 words
The method of claim 36 wherein high frequency aliasing suppression is performed by, i) for each pixel width Δ, examining each pixel x of the second difference of each image intensity signal, D 2 I.sub.Δ (x) first ,second, for the following conditions: |D.sup.2 I(x)|>|D.sup.2 I(x+Δ/2)|>|D.sup.2 I(x+Δ)| and, sign (D.sup.2 I(x))=sign (D.sup.2 I(x+Δ/2)) , and ii) developing the first and second directional edge detection signals signal(x) first ,second where: ##EQU5## and I m is the difference between the largest and the smallest intensity values in the image intensity signal.
Claim 41
Dependent Claim
21 words
The method of claim 29 wherein said step i) of taking is repeated for each one of said multiple pixel widths.
Claim 42
Dependent Claim
21 words
The method of claim 34 wherein said step i) of taking is repeated for each one of said multiple pixel widths.
Claim 43
Independent Claim
130 words
A device-implemented method of detecting edges in a video image comprising: a) providing a video sensor; b) producing an image signal defining a video image containing shadows formed of a plurality of image pixels arranged in a two dimensional array using said video sensor; c) determining the image intensity of each image pixel of said video image; d) monitoring at least an approximation of the first derivative of intensity of said monitored scene to produce edge detection signals; and e) screening said edge detection signals using at least an approximation of the second derivative of intensity of the monitored scene to suppress high frequency aliasing; said steps d) and e) of monitoring and screening distinguishing between object edges and mach edges produced by shadows to identify shadows within the image.
Claim 44
Independent Claim
130 words
A device-implemented method of detecting edges in a video image comprising: a) providing a video sensor; b) producing an image signal defining a video image containing shadows formed of a plurality of image pixels arranged in a two dimensional array using said video sensor; c) determining the image intensity of each image pixel of said video image; d) monitoring at least an approximation of the first derivative of intensity of said monitored scene to produce edge detection signals; and e) screening said edge detection signals using at least an approximation of the second derivative of intensity of the monitored scene to suppress high frequency aliasing; said steps d) and e) of monitoring and screening distinguishing between object edges and mach edges produced by shadows to identify shadows within the image.
Claim 45
Dependent Claim
39 words
The method of claim 40 wherein said step c) of determining image intensity comprises: i) configuring the video sensor to multiple pixel sizes, and ii) monitoring the intensity of the monitored scene for each of said multiple pixel sizes.
Claim 46
Independent Claim
241 words
A device-implemented method of detecting edges in a video image comprising: a) providing a video sensor; b) producing an image signal defining a video image containing shadows formed of a plurality of image pixels arranged in a two dimensional array using said video sensor; c) determining the image intensity of each image pixel of said video image; d) taking at least an approximation of the first derivative of image intensity in a first direction across each row of said array to form a first difference signal; e) taking at least an approximation of the second derivative of image intensity to form a screening signal; f) determining whether the screening signal meets predetermined screening conditions at each location of each row of said array; g) at each location of each row of said array, if said screening signal meets said screening conditions as determined by said step f), using said first difference signal developed in said step d) of determining as a first directional edge detection signal; h) repeating said steps d)-g) in a second direction to form a second directional edge detection signal; i) varying the size of each image pixel in said step c) to produce alternately sized pixels; j) repeating said steps d)-h) for each alternate size of pixels; and k) using said edge detection signals to distinguish between object edges and mach edges in the video image produced by the video sensor to identify shadows within the image.
Claim 47
Independent Claim
241 words
A device-implemented method of detecting edges in a video image comprising: a) providing a video sensor; b) producing an image signal defining a video image containing shadows formed of a plurality of image pixels arranged in a two dimensional array using said video sensor; c) determining the image intensity of each image pixel of said video image; d) taking at least an approximation of the first derivative of image intensity in a first direction across each row of said array to form a first difference signal; e) taking at least an approximation of the second derivative of image intensity to form a screening signal; f) determining whether the screening signal meets predetermined screening conditions at each location of each row of said array; g) at each location of each row of said array, if said screening signal meets said screening conditions as determined by said step f), using said first difference signal developed in said step d) of determining as a first directional edge detection signal; h) repeating said steps d)-g) in a second direction to form a second directional edge detection signal; i) varying the size of each image pixel in said step c) to produce alternately sized pixels; j) repeating said steps d)-h) for each alternate size of pixels; and k) using said edge detection signals to distinguish between object edges and mach edges in the video image produced by the video sensor to identify shadows within the image.
Claim 48
Dependent Claim
96 words
The method of claim 42 wherein said step k) includes recognizing object edges by, i) adding the first directional edge detection signals for each of said pixel sizes together to develop a total first edge detection signal and adding the second directional edge detection signals together to develop a total second edge detection signal, ii) locating the maxima in said total first and second edge detection signals, and iii) detecting the substantial positional coincidence of oppositely signed maxima in both said first and second total edge detection signals to detect the presence of an object edge.
Claim 49
Dependent Claim
118 words
The method of claim 42 wherein said step k) includes recognizing mach edges by, i) adding the first directional edge detection signals for each of said pixel sizes together to develop a total first edge detection signal and adding the second directional edge detection signals together to develop a total second edge detection signal, ii) locating the maxima in said total first and second edge detection signals, and iii) detecting positionally separated oppositely signed maxima pair within each of said total first and second edge detection signals and determining the presence of a mach edge by determining whether the maxima pair within said total first and second edge detection signals are of the same sign and positionally correspond.
Claim 50
Dependent Claim
73 words
The method of claim 42 wherein each of the first and second directional edge detection signals is an edge operator, said step k) including recognizing object edges by, i) determining the number of edge operators which exceed a threshold to determining the number of responding operators at each position along each line, and ii) detecting the presence of an object edge by determining whether the number of responding operators exceeds a predetermined level.
Claim 51
Dependent Claim
93 words
An image processing system which distinguishes object edges from shadows in a monitored scene comprising: a video sensor producing an image intensity signal representative of the monitored scene as an output thereof; means, operatively connected to said video sensor, for configuring the output of said video sensor to multiple pixel widths to simulate the shadow contrast sensitivity of the human vision system; and processor means, responsive to the configured output of said video sensor, for monitoring image contrast and distinguishing between object edges and mach edges produced by shadows in said monitored scene.
Claim 52
Dependent Claim
93 words
An image processing system which distinguishes object edges from shadows in a monitored scene comprising: a video sensor producing an image intensity signal representative of the monitored scene as an output thereof; means, operatively connected to said video sensor, for configuring the output of said video sensor to multiple pixel widths to simulate the shadow contrast sensitivity of the human vision system; and processor means, responsive to the configured output of said video sensor, for monitoring image contrast and distinguishing between object edges and mach edges produced by shadows in said monitored scene.
Claim 53
Dependent Claim
45 words
The system of claim 46 wherein said means for configuring configures at least the output of said video sensor to each of a plurality of multiple pixel widths Δ, said processor means processing the image intensity signal for each of said multiple pixel widths Δ.
Claim 54
Dependent Claim
20 words
The system of claim 47 wherein said means for configuring configures said video sensor to said multiple pixel widths Δ.
Claim 55
Dependent Claim
57 words
The system of claim 47 wherein said processor means includes, means for taking the first difference of said image intensity signal, DI.sub.Δ (x) first ,second, for each pixel width Δ, in first and second opposed directions along each line of said image to form first and second directional edge detection signals associated with each pixel width Δ.
Claim 56
Dependent Claim
60 words
The system of claim 49 further comprising means for screening said first and second edge detection signals, signal.sub.Δ (x), associated with each pixel width, to reduce the aliasing response of the edge detection operator through use of the second difference of each image intensity signal, D 2 I.sub.Δ (x) first ,second, to thereby reduce the influence of high frequency noise.
Claim 57
Dependent Claim
71 words
The system of claim 50 wherein said image intensity signal corresponds to the intensity of said monitored scene at image pixels which are arranged in a two dimensional array, said means for taking the first difference of said image intensity signal processing said image intensity along lines of said array in a first orientation and subsequently along lines of said array arranged in a second orientation non-aligned with said first orientation.
Claim 58
Dependent Claim
92 words
The system of claim 50 wherein said processor means further includes, means for summing the first and second directional edge detection signals associated with each pixel width Δ to form first and second total directional edge detection signals, signal(x) first ,second, means for determining the maxima in each of said first and second total directional edge detection signals, signal(x) first ,second, and means for detecting the substantial positional coincidence of oppositely signed maxima in both said first and second total directional edge detection signals to detect the presence of an object edge.
Claim 59
Dependent Claim
44 words
The system of claim 52 wherein said processor means further includes, means for determining that there are no additional maxima closely proximate to the positionally coincident maxima detected by said means for detecting to verify that a high contrast object edge has been detected.
Claim 60
Dependent Claim
81 words
The system of claim 50 wherein, each of said first and second edge detection signals, signal.sub.Δ (x) first ,second, for each pixel width Δ is considered an edge operator, said processor means further including, means for determining the number of edge operators which exceed a threshold to determining the number of responding operators at each position along each line, and means for detecting the presence of an object edge by determining whether the number of responding operators exceeds a predetermined level.
Claim 61
Dependent Claim
13 words
The system of claim 54 wherein the number of responding operators, ENRO=(Σ Signal.sub.Δ)/max{SignalΔ}.
Claim 62
Dependent Claim
55 words
The system of claim 50 wherein the ratio of maximum pixel width to minimum pixel width of the configured output of said video sensor is not greater than three to ensure that the aliasing response for the largest pixel width does not overlap the desired signal components produced by use of the smallest pixel width.
Claim 63
Dependent Claim
114 words
The system of claim 50 wherein said processor means recognizes lower contrast mach edges and includes, means for taking the first difference of said image intensity signal in first and second opposed directions along each line of said image to form first and second directional edge detection signals, means for determining the maxima in said first and second directional edge detection signals, and means for detecting positionally separated oppositely signed maxima pair within each of said first and second directional edge detection signals and determining the presence of a mach edge by determining whether the maxima pair within said first and second directional edge detection signals are of the same sign and positionally correspond.
Claim 64
Independent Claim
128 words
A device-implemented method of detecting edges in a video image comprising: a) providing a video sensor; b) producing an image signal defining a video image containing shadows formed of a plurality of image pixels arranged in a two dimensional array using said video sensor; c) assembling adjacent pixels in said image to form pixel groups of pixel width Δ; d) determining the image intensity of each image pixel group of said image to produce pixel group image signals; e) repeating steps c) and d) for varying values of Δ to form multiple pixel width pixel group image signals; and f) processing said multiple pixel width pixel group image signals to monitor image contrast to distinguish between object edges and mach edges to identify shadows in said video image.
Claim 65
Independent Claim
128 words
A device-implemented method of detecting edges in a video image comprising: a) providing a video sensor; b) producing an image signal defining a video image containing shadows formed of a plurality of image pixels arranged in a two dimensional array using said video sensor; c) assembling adjacent pixels in said image to form pixel groups of pixel width Δ; d) determining the image intensity of each image pixel group of said image to produce pixel group image signals; e) repeating steps c) and d) for varying values of Δ to form multiple pixel width pixel group image signals; and f) processing said multiple pixel width pixel group image signals to monitor image contrast to distinguish between object edges and mach edges to identify shadows in said video image.
Claim 66
Dependent Claim
88 words
The method of claim 58 wherein said step e) of processing includes, i) taking at least an approximation of the first derivative of intensity of each of said pixel group signals to produce edge detection signals; and ii) screening said edge detection signals using at least an approximation of the second derivative of intensity of the monitored scene to suppress high frequency aliasing; iii) repeating said steps i) and ii) of monitoring and screening for each of said varying values of Δ in order to detect Mach edges.
Claim 67
Dependent Claim
41 words
The method of claim 59 wherein said step d) of determining image intensity comprises: i) configuring the video sensor to multiple pixel sizes Δ, and ii) monitoring the intensity of the monitored scene for each of said multiple pixel sizes Δ.
Claim 68
Dependent Claim
141 words
An image processing system which distinguishes object edges from shadows in a monitored scene comprising: a video sensor producing a video image of the monitored scene, formed of a plurality of image pixels arranged in a two dimensional array; means, operatively connected to said video sensor, for assembling adjacent pixels in said video image to form pixel groups of pixel width Δ, said assembly means assembling said adjacent pixels to varying values of pixel width Δ; pixel image signal production means for determining the image intensity of each image pixel group of said image to produce pixel group image signals for each pixel width Δ assembled by said assembly means; and processing means for processing said pixel group image signals for each pixel width Δ to monitor image contrast to distinguish between object edges and mach edges in said video image.
Claim 69
Dependent Claim
141 words
An image processing system which distinguishes object edges from shadows in a monitored scene comprising: a video sensor producing a video image of the monitored scene, formed of a plurality of image pixels arranged in a two dimensional array; means, operatively connected to said video sensor, for assembling adjacent pixels in said video image to form pixel groups of pixel width Δ, said assembly means assembling said adjacent pixels to varying values of pixel width Δ; pixel image signal production means for determining the image intensity of each image pixel group of said image to produce pixel group image signals for each pixel width Δ assembled by said assembly means; and processing means for processing said pixel group image signals for each pixel width Δ to monitor image contrast to distinguish between object edges and mach edges in said video image.
Claim 70
Dependent Claim
82 words
An image processing system which distinguishes object edges from shadows in a monitored scene having a plurality of image pixels arranged in a two dimensional array, comprising: means for assembling the pixels of the monitored scene into multiple pixel assemblies of varying widths to simulate the shadow contrast sensitivity of the human vision system; and processor means, responsive to said means for assembling, for monitoring image contrast and distinguishing between object edges and mach edges produced by shadows in said monitored scene.
Claim 71
Dependent Claim
82 words
An image processing system which distinguishes object edges from shadows in a monitored scene having a plurality of image pixels arranged in a two dimensional array, comprising: means for assembling the pixels of the monitored scene into multiple pixel assemblies of varying widths to simulate the shadow contrast sensitivity of the human vision system; and processor means, responsive to said means for assembling, for monitoring image contrast and distinguishing between object edges and mach edges produced by shadows in said monitored scene.
References Cited (Backward Citations)
US3701095A
Cited
US4804842A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 1999-02-26 | 1999-08-28 | 2000-02-27 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2003-02-26 | 2003-08-28 | 2004-02-27 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2007-02-26 | 2007-08-28 | 2008-02-27 | $7700.00 | Window Closed / Lapsed |