Abstract: The present invention discloses a method which comprises the following steps: inputting the image waiting for test and the template; log-polar transforming the image waiting for test; performing feature extraction on transformed image object; capturing an image feature; achieving a response map of scale and rotation of the image object corresponding to a template through a phase correlation by using features extracted from the image features; calculating a relative displacement by using a response value and coordinates of the response value in a surround area of a maximum value of the response pattern; calculating the scale and the rotation of an object in the image waiting for test corresponding to the template through the relative displacement. The present invention adopts the log-polar space as the image operating space to estimate the change in size and rotation of the object and provide a fast and robust select for upper applications.

Abstract: A stereo visual odometry method based on image gradient joint optimization includes steps of: pre-processing each frame of images of a stereo video input; calculating a stereo image disparity map of a stereo video frame, and obtaining a metric distance; scaling to form scale images with different scales for forming a pyramid model, and calculating features to obtain a series of feature images; processing the images with a Kalman filter according to the metric distance, so to predict and estimate a motion process of a camera pose, wherein camera motion models is built in the Kalman filter; accurately calculating a camera pose of a current frame by using a gradient-based stereo visual navigation method; and updating the camera motion models in the Kalman filter with the camera pose of the current frame.

Abstract: A stereo visual odometry method based on image gradient joint optimization includes steps of: pre-processing each frame of images of a stereo video input; calculating a stereo image disparity map of a stereo video frame, and obtaining a metric distance; scaling to form scale images with different scales for forming a pyramid model, and calculating features to obtain a series of feature images; processing the images with a Kalman filter according to the metric distance, so to predict and estimate a motion process of a camera pose, wherein camera motion models is built in the Kalman filter; accurately calculating a camera pose of a current frame by using a gradient-based stereo visual navigation method; and updating the camera motion models in the Kalman filter with the camera pose of the current frame.

Abstract: The present invention discloses a method which comprises the following steps: inputting the image waiting for test and the template; log-polar transforming the image waiting for test; performing feature extraction on transformed image object; capturing an image feature; achieving a response map of scale and rotation of the image object corresponding to a template through a phase correlation by using features extracted from the image features; calculating a relative displacement by using a response value and coordinates of the response value in a surround area of a maximum value of the response pattern; calculating the scale and the rotation of an object in the image waiting for test corresponding to the template through the relative displacement. The present invention adopts the log-polar space as the image operating space to estimate the change in size and rotation of the object and provide a fast and robust select for upper applications.