Camshift, namely "Continuously Adaptive Mean-Shift" algorithm, is an adaptive tracking algorithm. This algorithm is based on the color information to track the moving target in image sequence. In the simple background, this algorithm achieved a steady and current tracking effect. But in dynamic scene, the global motion caused by the camera, the background of the light and occlusion will affect the accuracy, or even lose the tracking of the target. In order to solve the above problem, this paper adjust the H component in HSV color space, as well use weighted color histogram to improve the Camshift algorithm, then combined with Kalman filter to track the target in the image sequence. The experimental result shows that this approach can track object stability and correctly in dynamic scene.
An object tracking framework based on adaboost and Mean-Shift for image sequence was proposed in the manuscript. The object rectangle and scene rectangle in the initial image of the sequence were drawn and then, labeled the pixel data in the two rectangles with 1 and 0. Trained the adaboost classifier by the pixel data and the corresponding labels. The obtained classifier was improved to be a 5 class classifier and employed to classify the data in the same scene region of next image. The confidence map including 5 values was got. The Mean-Shift algorithm is performed in the confidence map area to get the final object position. The rectangles of object and background were moved to the new position. The object rectangle was zoomed by 5 percent to adapt the object scale changing. The process including drawing rectangle, training, classification, orientation and zooming would be repeated until the end of the image sequence. The experiments result showed that the proposed algorithm is efficient for nonrigid object orientation in the dynamic scene.
Object tracking has been researched for many years as an important topic in machine learning, robot vision and many other fields. Over the years, various tracking methods are proposed and developed in order to gain a better tracking effect. Among them the mean-shift algorithm turns out to be robust and accurate compared other algorithms after different kinds of tests. But due to its limitations, the changes in scale and rotational motion of an object cannot be effectively processed. This problem occurs when the object of interest moves towards or away from the video camera. Improving over the previously proposed method such as scale and orientation adaptive mean shift tracking, which performs well with scaling change but not for the rotation, in this paper, the proposed method modifies the continuously adaptive mean shift tracking method so that it can handle effectively for changes in size and rotation in motion, simultaneously. The simulation results yield a successful tracking of moving objects even when the object undergoes scaling in size and rotation in motion in comparison to the conventional ones.
This paper proposes a block Mean-Shift algorithm based on target real-time update and LBP texture features, through the target update improves the accuracy of target tracking, enhances the local character of the target through the target block, so as to improve the robustness of algorithm based on skin color backgrounds. And then analyze the Mean-Shift algorithm cannot recover quickly lost target tracking defects, and its improvement by combining the frame difference method.
In order to improve the real-time character of missile radiator tracking and solve the predicting tracking problem when missile radiator shortly shelter or missing, it introduces moving target predicting and tracking technology. According to the predicting and tracking method, it proposes three predicting and tracking overall schemes of missile radiator based on Kalman filtering and improved Mean-Shift algorithm. Also it compares the real-time character of three kinds of schemes. According to the trajectory character of missile radiator, it constructs Kalman filter. The experiment results indicate that by using Kalman filtering technology, there are improvements in real-time character and shortly shelter or missing problem can be solved well. It plays a certain compensation function to the whole system.
Object Tracking Based on Multi-feature Mean-shift Algorithm