Image processing apparatus and method for real-time motion detection
View Patent ↗An image processing apparatus and method for real time motion detection is provided. In the apparatus, a sub-sampling module receives and sub-samples a current image and a plurality of previous images and a census transform module performs census transform on each of the sub-sampled images to obtain a census vector. A correlation calculation module calculates and compares correlation values between the current image and the plurality of previous images and detects a region having highest correlation. A motion detection module tracks positions of pixels corresponding to the region having the highest correlation to detect motion information in the images. The image processing apparatus and method can obtain, in real time, the direction and speed of an object that is in motion in each image.
1. An image processing apparatus for real time motion detection comprising:
a sub-sampling module that receives and sub-samples a current image and a plurality of previous images;
a census transform module that performs census transform on each of the sub-sampled images to obtain a census vector;
a correlation calculation module that calculates and compares correlation values between the current image and the plurality of previous images using the census vector and detects a region having highest correlation; and
a motion detection module that tracks positions of pixels corresponding to the region having the highest correlation to detect motion information in the images,
wherein the sub-sampling module performs sub-sampling using, as a sub-sampling interpolation method, at least one of bilinear interpolation, nearest-neighbor interpolation, and cubic convolution interpolation.
2. The image processing apparatus according to claim 1 , further comprising a buffer module including a plurality of readable and writable frame buffers and allowing simultaneous access to a currently input image and at least one previous image.
3. The image processing apparatus according to claim 1 , wherein the sub-sampling module reduces a size of an original image using at least one ratio and obtains at least one sub-sampled image having a different resolution from the original image.
4. The image processing apparatus according to claim 1 , wherein the correlation calculation module defines lower-level windows in each region to be compared and obtains a correlation value between the lower-level windows through an XOR operation between the lower-level windows.
5. The image processing apparatus according to claim 1 , wherein the motion detection module checks frequency components of an input image and selects sub-sampled images for comparison of correlation values according to the frequency components.
6. An image processing method for real time motion detection comprising:
receiving and sub-sampling a current image and a plurality of previous images;
performing census transform on each of the sub-sampled images to obtain a census vector;
calculating and comparing correlation values between the current image and the plurality of previous images based on the census vector and detecting a region having highest correlation; and
tracking positions of pixels corresponding to the region having the highest correlation to detect motion information in the images,
wherein the sub-sampling step includes performing sub-sampling using, as a sub-sampling interpolation method, at least one of bilinear interpolation, nearest-neighbor interpolation, and cubic convolution interpolation.
7. The image processing method according to claim 6 , wherein the sub-sampling step includes reducing a size of an original image using at least one ratio and obtaining at least one sub-sampled image having a different resolution from the original image.
8. The image processing method according to claim 6 , wherein the correlation calculation step includes defining lower-level windows in each region to be compared and obtaining a correlation value between the lower-level windows through an XOR operation between the lower-level windows.
9. The image processing method according to claim 6 , wherein the motion detection step includes checking frequency components of an input image and selecting sub-sampled images for comparison of correlation values according to the frequency components.