Intruding object detection method and intruding object monitor apparatus which automatically set a threshold for object detection
First Claim
1. An object detection method for detecting an object present in an image obtained from an imaging device by comparing at least two images, comprising the steps of:
- generating a first comparison image representing a result of comparison made between a first input image from said imaging device and a reference image stored in a storage device;
threshold-processing said first comparison image using a predetermined threshold value, changing said threshold value until a noise level of said threshold-processed image becomes not greater than a predetermined value and setting the threshold value with which the noise level of said threshold-processed image becomes not greater than the predetermined value, as a first threshold value;
generating a second comparison image which represents a result of comparison made between a second input image including an object from said imaging device and said reference image stored in said storage device;
threshold-processing said second comparison image using a predetermined threshold, changing said threshold until the size of the object in the threshold-processed image becomes not greater than a predetermined value and setting the threshold value with which the size of said object in said threshold-processed image becomes not greater than the predetermined value, as a second threshold value;
setting a third threshold value within a range including said first and second threshold values anddetecting an object based on said third threshold value.
1 Assignment
0 Petitions
Accused Products
Abstract
A monitoring method and apparatus for detecting an intruding object within a monitoring field of view by applying a subtraction method to an image obtained from an imaging device. A differential image of luminance values between an input image from the imaging device and a reference background image stored in a storage device is generated. The differential image is binarized using a predetermined binarization threshold value and the bianrization threshold value is changed until a noise level of a bianrized image becomes not greater than a predetermined value and based on a binarization threshold value at which the noise level becomes not greater than the predetermined value, an intruding object is detected.
35 Citations
4 Claims
-
1. An object detection method for detecting an object present in an image obtained from an imaging device by comparing at least two images, comprising the steps of:
-
generating a first comparison image representing a result of comparison made between a first input image from said imaging device and a reference image stored in a storage device; threshold-processing said first comparison image using a predetermined threshold value, changing said threshold value until a noise level of said threshold-processed image becomes not greater than a predetermined value and setting the threshold value with which the noise level of said threshold-processed image becomes not greater than the predetermined value, as a first threshold value; generating a second comparison image which represents a result of comparison made between a second input image including an object from said imaging device and said reference image stored in said storage device; threshold-processing said second comparison image using a predetermined threshold, changing said threshold until the size of the object in the threshold-processed image becomes not greater than a predetermined value and setting the threshold value with which the size of said object in said threshold-processed image becomes not greater than the predetermined value, as a second threshold value; setting a third threshold value within a range including said first and second threshold values and detecting an object based on said third threshold value. - View Dependent Claims (2)
-
-
3. An object detection apparatus for detecting an object present in an image obtained from an imaging device by comparing at least two images, comprising:
-
an imaging device which outputs a first input image and a second input image; a first storage device which stores a reference image; a processing unit which generates a first comparison image representing a result of comparison made between said first input image and said reference image; a first threshold-processing unit which threshold-processes said first comparison image using a predetermined threshold value, wherein said first threshold-processing unit changes said threshold value until a noise component of the threshold-processed image becomes no greater than a predetermined value and outputs, as a first threshold value, the threshold value with which said noise component of said threshold-processed first comparison image becomes no greater than the predetermined value; another processing unit which generates a second comparison image representing a result of comparison between said second input image and said reference image stored in said first storage device; a second threshold-processing unit which threshold-processes said second comparison image using another predetermined threshold value, wherein said second threshold-processing unit changes said another threshold value until a size of an object in said threshold-processed image becomes no greater than a predetermined size and outputs, as a second threshold value, the threshold value with which the size of said object in said threshold-processed second comparison image becomes no greater than said predetermined size; a threshold setting unit which sets a third threshold value within a range including said first threshold value and second threshold value and a detection unit which detects an object based on said set third threshold value. - View Dependent Claims (4)
-
Specification