Face tracking method based on improved Camshift algorithm

Abstract

The invention discloses a face tracking method based on an improved Camshift algorithm, and the method comprises the following steps: 1) taking a face in an initial frame of a video image as an initial face window, and taking the face as a tracking target; 2) modeling an improved Camshift tracking algorithm according to the centroid position and the window size of a tracking target, and performingcalculating to obtain an optimal candidate window in the current frame image by using the tracking algorithm; 3) calculating whether the shielding interference of the current frame image exceeds a given threshold; 4) when the interference is less than a given threshold, using the candidate window obtained in the step 2) as a target window, and returning to the target window; 5) if the interference is not less than a given threshold value, introducing a Kalman filter, carrying out predicting by taking the obtained target mass center as an observation vector, and returning a prediction result as a target window, and 6) taking an output prediction vector obtained by the Kalman filter as a search window center, and continuing target tracking of the next frame.

Description

technical field [0001] The technology relates to the technical field of video target tracking, in particular to a face tracking method based on an improved Camshift algorithm. Background technique [0002] In modern transportation operations, due to the long transportation distance and high work intensity, drivers are prone to fatigue driving, which leads to various traffic accidents. After using the convolutional neural network to complete the separation of the background and the face, and frame the face window, it is necessary to track the face window for subsequent judgment of fatigue through facial features. The target tracking algorithm determines the real-time performance and accuracy of target tracking, and the existing Camshift tracking algorithm has a large amount of calculations, which ensures the real-time performance of face window tracking. Since the size of the search window is not fixed, the tracking window continues to expand, similar to Colors are easily di...

AI Technical Summary

Problems solved by technology

The target tracking algorithm determines the real-time performance and accuracy of target tracking, and the existing Camshift tracking algorithm has a large amount of calculations, which ensures the real-time performance of face window tracking. Since the size of the search window is not fixed, the tracking window continues to expand, similar to While the color is easily disturbed, updating the size parameter modulating the search box is computationally intensive

Images