Abstract: An image calibration method of the present invention is configured to calibrate the position of observation area in motion image which includes image frames. The step of the image calibration method includes: determining the observation area and acquires central position of the observation area in first image frame of the motion image; determining first unique area, which complies with gradient characteristic, in the first image frame; acquiring first vector value from the central positions of the observation area to the first unique area in the first image frame; finding second unique area in the second image frame of the motion image according to the gradient characteristic; acquiring second vector value from the central position of the observation area to the central position of the second unique area in the second image frame; and calibrating position of the observation area in a third image frame according to the difference between the first vector and the second vector.

Abstract: An image calibration method of the present invention is configured to calibrate the position of observation area in motion image which includes image frames. The step of the image calibration method includes: determining the observation area and acquires central position of the observation area in first image frame of the motion image; determining first unique area, which complies with gradient characteristic, in the first image frame; acquiring first vector value from the central positions of the observation area to the first unique area in the first image frame; finding second unique area in the second image frame of the motion image according to the gradient characteristic; acquiring second vector value from the central position of the observation area to the central position of the second unique area in the second image frame; and calibrating position of the observation area in a third image frame according to the difference between the first vector and the second vector.

Abstract: Disclosed herein is a method for auto-depicting trends in object contours (referred to as ADTOC). At the heart of ADTOC is a sifting process to determine a significant angular value via evaluating a plurality of angular values in a predefined range. ADTOC is characterized in that a probe-ahead concept is applied to obtain a reference angular value along the current route, and then the probed angular value is used to modify the significant angular value in order to timely correct the subsequent trace direction, thus achieving more accurate trace result. Contours with discontinuous segments caused by noise, obstacles, illumination, shading variations, etc. can also be auto-depicted without requiring a predefined auxiliary route.

Abstract: Disclosed herein is a method for auto-depicting trends in object contours (referred to as ADTOC). At the heart of ADTOC is a sifting process to determine a significant angular value via evaluating a plurality of angular values in a predefined range. ADTOC is characterized in that a probe-ahead concept is applied to obtain a reference angular value along the current route, and then the probed angular value is used to modify the significant angular value in order to timely correct the subsequent trace direction, thus achieving more accurate trace result. Contours with discontinuous segments caused by noise, obstacles, illumination, shading variations, etc. can also be auto-depicted without requiring a predefined auxiliary route.