Image processing apparatus and method
First Claim
1. A process of tracking a target provided in an input signal received by an image processing system, the image processing system being configured for receiving the input signal, which input signal includes data regarding a succession of frames, and each frame including a plurality of pixels, a portion of the plurality of pixels including the target, the process comprising:
- calculating a histogram boundary for an area defined within the portion of the plurality of pixels containing the target;
analyzing the calculated histogram boundary to determine whether the area contains the target in its entirety;
adjusting the histogram boundary for the area defined within the portion of the plurality of pixels containing the target until the adjusted histogram boundary contains the target in its entirety; and
setting the calculated histogram boundary based on predefined criteria,wherein the predefined criteria includes coordinates (Xmin, Ymin) and (Xmax, Ymax), and wherein calculating the histogram boundary comprises;
calculating an x histogram dimension for pixels from Xmin to Xmax;
calculating a y histogram dimension for pixels from Ymin to Ymax; and
analyzing the calculated x and y histograms dimension to determine whether the x and y histogram dimensions contain target information,wherein analyzing the x and y histogram dimensions comprises performing a thresholding operation,wherein the area defined by the histogram boundary is defined by coordinates (Xmin, Ymin) and (Xmax, Ymax), and wherein adjusting the location of the center comprises defining a new center of the histogram boundary at coordinate ((Xmin+Xmax)/2, (Ymin+Ymax)/2).
4 Assignments
0 Petitions
Accused Products
Abstract
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 (D1), time constant (CO), first axis (x(m)), and second axis (y(m)).
103 Citations
14 Claims
-
1. A process of tracking a target provided in an input signal received by an image processing system, the image processing system being configured for receiving the input signal, which input signal includes data regarding a succession of frames, and each frame including a plurality of pixels, a portion of the plurality of pixels including the target, the process comprising:
-
calculating a histogram boundary for an area defined within the portion of the plurality of pixels containing the target; analyzing the calculated histogram boundary to determine whether the area contains the target in its entirety; adjusting the histogram boundary for the area defined within the portion of the plurality of pixels containing the target until the adjusted histogram boundary contains the target in its entirety; and setting the calculated histogram boundary based on predefined criteria, wherein the predefined criteria includes coordinates (Xmin, Ymin) and (Xmax, Ymax), and wherein calculating the histogram boundary comprises; calculating an x histogram dimension for pixels from Xmin to Xmax; calculating a y histogram dimension for pixels from Ymin to Ymax; and analyzing the calculated x and y histograms dimension to determine whether the x and y histogram dimensions contain target information, wherein analyzing the x and y histogram dimensions comprises performing a thresholding operation, wherein the area defined by the histogram boundary is defined by coordinates (Xmin, Ymin) and (Xmax, Ymax), and wherein adjusting the location of the center comprises defining a new center of the histogram boundary at coordinate ((Xmin+Xmax)/2, (Ymin+Ymax)/2). - View Dependent Claims (2, 3, 4, 5, 6, 7)
-
-
8. A target tracking system for determining, according to an initial area including a target to be tracked in an image captured by a camera, a targeting box surrounding a starting position of a frame, the target tracking system comprising:
-
an x histogram unit for forming a histogram based on predetermined x pixels of the targeting box; a y histogram unit for forming a histogram based on predetermined y pixels of the targeting box; and a controller for specifying dimensions of the targeting box bounded by the predetermined x pixels and y pixels, the controller adjusting the dimensions of the targeting box starting with the initial area and, in accordance with the histogram formed by the x and y histogram units, adjusting the dimensions until the target tracking system detects at least one edge of the target, wherein the targeting box is defined by coordinates (Xmin, Ymin) and (Xmax, Ymax), such that the x histogram unit calculates an x histogram dimension based on pixels from Xmin to Xmax, and the y histogram unit calculates a y histogram dimension based on pixels from Ymin to Ymax, and wherein the controller is configured to analyze the calculated x and y histogram dimensions to determine whether the x and y histogram dimensions contain target information, wherein the controller is configured to analyze the calculated x and y histogram dimensions by performing a thresholding operation. - View Dependent Claims (9, 10, 11, 12, 13, 14)
-
Specification