Image processing apparatus and method thereof
View Patent ↗An image processing apparatus such as a surveillance apparatus and method thereof are provided. The image processing apparatus includes: an object detecting unit which detects a plurality of moving objects from at least one of two or more images obtained by photographing a surveillance area from two or more view points, respectively; a depth determination unit which determines depths of the moving objects based on the two or more images, wherein the depth determination unit determines the moving objects as different objects if the moving objects have different depths.
1. An image processing apparatus comprising:
an object detector which detects a plurality of objects from at least one of two or more images captured by two or more image capture devices which photograph a surveillance area from two or more view points, respectively;
a depth determiner which determines depths of the plurality of objects based on the two or more images, the depths being respective distances between the plurality of objects and at least one of the image capture devices; and
an object combiner which determines two objects, which have been detected as two objects by the object detector, among the plurality of objects as different objects if a difference between depths of the two objects is determined to be equal to or greater than a first threshold value, and determines the two objects as one object if the difference is determined to be less than the first threshold value,
wherein the first threshold value is greater than zero (0),
wherein the image processing apparatus further comprises a texture determiner which determines texture similarity between the two objects by detecting texture information thereof, and
wherein the object combiner determines the two objects, determined as one object based on the depth difference, as different objects, if a difference between texture information of the two objects is determined to be equal to or greater than a second threshold value, and confirms that the two objects, determined as one object based on the depth difference, as one object if the difference between the texture information of the two objects is determined to be less than the second threshold value.
2. The image processing apparatus of claim 1 , wherein when the object detector detects the plurality of objects, the object detector generates outlines of the two objects in at least one of the two or more images and labels the two objects differently, and
wherein the object combiner determines the two differently labeled objects as one object if the difference between the depths of the two differently labeled objects is determined to be less than the first threshold value and the difference between the texture information of the two differently labeled objects is determined to be less than the second threshold value.
3. The image processing apparatus of claim 2 , further comprising an event detector which indicates that an event has occurred if at least one of the plurality of objects is determined to be a moving object and have a depth satisfying a specific condition.
4. The image processing apparatus of claim 2 , wherein the object combiner determines the two differently labeled objects as two different objects if the difference between the texture information of the two differently labeled objects is determined to be equal to or greater than the second threshold value even though the difference between the depths of the two differently labeled objects is determined to be less than the first threshold value.
5. The image processing apparatus of claim 2 , wherein the object combiner relabels the two differently labeled objects as one object using one outline if the difference between the depths of the two differently labeled objects is determined to be less than the first threshold value and the difference between the texture information of the two differently labeled objects is determined to be less than the second threshold value.
6. The image processing apparatus of claim 5 , further comprising an event detector which indicates that an event has occurred if at least one of the plurality of objects is determined to be a moving object and have a depth satisfying a specific condition.
7. The image processing apparatus of claim 1 , wherein the two objects are adjacent to each other.
8. An image processing method comprising:
detecting a plurality of objects from at least one of two or more images captured by two or more image capture devices which photograph a surveillance area from two or more view points, respectively;
determining depths of the plurality of objects based on the two or more images, the depths being respective distances between the plurality of objects and at least one of the image capture devices; and
determining two objects, which have been detected as two objects in the detecting, among the plurality of objects as different objects if a difference between depths of the two objects is determined to be equal to or greater than a first threshold value, and determining the two objects as one object if the difference is determined to be less than the first threshold value,
wherein the first threshold value is greater than zero (0),
wherein the image processing method further comprises:
determining texture similarity between the two objects by detecting texture information thereof;
determining the two objects, determined as one object based on the depth difference, as different objects, if a difference between texture information of the two objects is determined to be equal to or greater than a second threshold value; and
confirming that the two objects, determined as one object based on the depth difference, as one object if the difference between the texture information of the two objects is determined to be less than the second threshold value.