Video safety detector with shadow elimination

Claim 3

The method according to claim 1 wherein said steps of generating and comparing comprise a high pass filter process.

Claim 4

The method according to claim 2 wherein said mask image comprises indications defining pass areas as blobs from said high pass filter and defining clear areas as non-blob areas from said high pass filter.

Claim 5

The method according to claim 1 further comprising the step of taking an absolute value of said difference image to form an absolute difference image, wherein said step of segmenting is performed on said absolute difference image rather than on said difference image.

Claim 6

The method according to claim 1 wherein said step of segmenting further comprises the steps of: characterizing contiguous related pixels; determining areas of contiguous related pixels; and comparing said areas with threshold limits.

Claim 7

The method according to claim 1 further comprising the step of providing notification output if said texture comparison procedure finds a discrepancy between said edge data and said gradient images which discrepancy exceeds a predetermined threshold.

Claim 8

The method according to claim 1 wherein said step of segmenting is performed using a watershed process.

Claim 9

The method according to claim 1 further comprising the step of illuminating said space with diffuse light.

Claim 10

The method according to claim 2 wherein said diffuse light is provided by a light source mounted proximate to said camera.

Claim 11

The method according to claim 1 wherein said source image comprises a set of time sequenced images.

Claim 12

The method according to claim 1 further comprising a step of illuminating said space with near IR light.

Claim 13

The method according to claim 11 wherein said step of acquiring a digital source image further comprising a step of filtering light reflected from said space using an IR bandpass filter.

Claim 14

The method according to claim 11 wherein said textured background comprises texture having pre-selected IR reflectivity.

Claim 15

The method according to claim 1 wherein said textured background comprises a high spatial frequency texture.

Claim 16

The method according to claim 1 wherein said textured background comprises a perimeter of said space.

Claim 17

The method according to claim 1 wherein said step of performing a gradient computation procedure comprises computing a magnitude and direction of a first derivative at each point in said source image.

Claim 18

The method according to claim 1 wherein said step of performing a gradient computation procedure comprises convolving said source image with standard Sobel kernels.

Claim 19

A machine vision intrusion detection apparatus comprising: at least one image acquisition device arranged to acquire an image of a space; at least one light source arranged to illuminate at least part of said space; at least one video processor in communication with said at least one image acquisition device; wherein said at least one video processor further comprises: an image processor component in communication with said image acquisition device; wherein said image processor component further comprises a low pass filter component in communication with said image acquisition device and receiving a source image therefrom; a comparison component in communication with said image acquisition device and receiving said source image therefrom, said comparison component also in communication with said low pass filter component and receiving a background image therefrom; a segmentation component in communication with said comparison component and receiving a difference image therefrom; an edge detection component in communication with said segmentation component and receiving a mask image therefrom, said edge detection component also in communication with said low pass filter and receiving a background image therefrom; a gradient computation component in communication with said image acquisition device and receiving a source image therefrom; and a texture comparison component in communication with said edge detection component and receiving edge data therefrom, said texture comparison component also in communication with said gradient computation component and receiving gradient images therefrom.

Claim 20

A machine vision intrusion detection apparatus comprising: at least one image acquisition device arranged to acquire an image of a space; at least one light source arranged to illuminate at least part of said space; at least one video processor in communication with said at least one image acquisition device; wherein said at least one video processor further comprises: an image processor component in communication with said image acquisition device; wherein said image processor component further comprises a low pass filter component in communication with said image acquisition device and receiving a source image therefrom; a comparison component in communication with said image acquisition device and receiving said source image therefrom, said comparison component also in communication with said low pass filter component and receiving a background image therefrom; a segmentation component in communication with said comparison component and receiving a difference image therefrom; an edge detection component in communication with said segmentation component and receiving a mask image therefrom, said edge detection component also in communication with said low pass filter and receiving a background image therefrom; a gradient computation component in communication with said image acquisition device and receiving a source image therefrom; and a texture comparison component in communication with said edge detection component and receiving edge data therefrom, said texture comparison component also in communication with said gradient computation component and receiving gradient images therefrom.

Claim 21

The apparatus according to claim 18 : wherein said light source comprises a near IR light source; and wherein said image acquisition device is configured with an IR band-pass filter to acquire reflected near IR light and reject light outside of the near IR frequency band.