Image processing method
A method and apparatus for localizing an area in relative movement and for determining the speed and direction thereof in real time is disclosed. Each pixel of an image is smoothed using its own time constant. A binary value corresponding to the existence of a significant variation in the amplitude of the smoothed pixel from the prior frame, and the amplitude of the variation, are determined, and the time constant for the pixel is updated. For each particular pixel, two matrices are formed that include a subset of the pixels spatially related to the particular pixel. The first matrix contains the binary values of the subset of pixels. The second matrix contains the amplitude of the variation of the subset of pixels. In the first matrix, it is determined whether the pixels along an oriented direction relative to the particular pixel have binary values representative of significant variation, and, for such pixels, it is determined in the second matrix whether the amplitude of these pixels varies in a known manner indicating movement in the oriented direction. In each of several domains, histogram of the values in the first and second matrices falling in such domain is formed. Using the histograms, it is determined whether there is an area having the characteristics of the particular domain. The domains include luminance, hue, saturation, speed (V), oriented direction (D 1 ), time constant (CO), first axis (x(m)), and second axis (y(m)).
1. A process for tracking a target in an input signal implemented using a system comprising an image processing system, the input signal comprising a succession of frames, each frame comprising a succession of pixels, the target comprising pixels in one or more of a plurality of classes in one or more of a plurality of domains, the process performed by said system comprising:
selecting a pixel of the target as a starting pixel; on a frame-by-frame basis:
forming a tracking box around the starting pixel and for each pixel of the input signal in the tracking box forming a histogram of the pixels in the one or more of a plurality of classes in the one or more of a plurality of domains;
successively increasing the size of the tracking box and for each pixel of the input signal, in each successive tracking box forming a histogram of the pixels in the one or more of a plurality of classes in the one or more of a plurality of domains;
determining when the target is substantially within the tracking box;
stopping the size increasing of said tracking box; and
adjusting the center of the tracking box based upon the histograms.
2. The process according to claim 1 , comprising centering the tracking box relative to an optical axis of the frame.
3. The process according to claim 1 , comprising calculating a histogram according to a projection axis in a region delimited by an associated classifier, between two points on the projection axis, creating a histogram of the same points with orientation and intensity of motion as input parameters and modifying the values corresponding to said two points of the classifier and calculate an anticipated next frame.
4. The process according to claim 1 , wherein said image processing system comprises at least one component selected from a memory, a temporal processing unit, and a spatial processing unit.
5. The process according to claim 1 , wherein said image processing system comprises at least two components selected from a memory, a temporal processing unit, and a spatial processing unit.
6. A process of tracking a target in an input signal implemented using a system comprising an image processing system, the input signal comprising a succession of frames, each frame comprising a succession of pixels, the target comprising pixels in one or more of a plurality of classes in one or more of a plurality of domains, the process performed by said system comprising, on a frame-by-frame basis: forming at least one histogram of the pixels in the one or more of a plurality of classes in the one or more of a plurality of domains, said at least one histogram referring to classes defining said target, identifying the target from said at least one histogram, drawing a tracking box around the target, and centering the tracking box relative to an optical axis of the frame.
7. A process of tracking a target in an input signal implemented using a system comprising an image processing system, the input signal comprising a succession of frames, each frame comprising a succession of pixels, the target comprising pixels in one or more of a plurality of classes in one or more of a plurality of domains, the process performed by said system comprising, on a frame-by-frame basis: forming at least one histogram of the pixels in the one or more of a plurality of classes in the one or more of a plurality of domains, said at least one histogram referring to classes defining said target, and identifying the target from said at least one histogram, and
calculating a histogram according to a projection axis in a region delimited by an associated classifier, between two points on the projection axis, creating a histogram of the same points with orientation and intensity of motion as input parameters and modifying the values corresponding to said two points of the classifier and calculate an anticipated next frame.