Sentence examples for mean shift tracker from inspiring English sources

In Figure 13 the tracking results of Auto GMM-SAMT (green solid contour) are compared to the results of the standard mean shift tracker combined with the ±10% method (red dotted ellipse).

Figure 13 Tracking results using the standard mean shift tracker combined with the ±10% method (The result of the standard mean shift tracker indicated by the red dotted ellipses is hard to see. Can you please enhance the visibility of the red dotted ellipses?) and Auto GMM-SAMT (green solid contour) for tracking an airplane and a car in sequences Airplane (a) and Follow_me (b), respectively.

To further evaluate the tracking result the tracking error in pixels is estimated by computing the averaged euclidean distance of the tracked centroids to the ground truth centroids, see Tables 3 and 4. Since the standard method failes to track the follow-me car, the tracking error is extremly high in that case and does not represent the general performance of the standard mean shift tracker.

Its performance is investigated and evaluated with synthetic and natural sequences and compared with the mean-shift tracker.

The working of the framework is demonstrated by combining a SURF-based mean-shift tracker, an optical-flow tracker and a Kalman filter to provide robust tracking over a long time.

Throughout this work we use the mean-shift tracker.

We quantitatively compare two template-based tracking algorithms, Hager's method and the hyperplane tracker, and three histogram-based methods, the mean-shift tracker, two trust-region trackers, and the CONDENSATION tracker.

Quast and A. Kaup, "Auto GMM-SAMT: an automatic object tracking system for video surveillance in traffic scenarios"), which describes a shape adaptive mean-shift tracker relying on Gaussian mixture models to adapt the kernel to the object shape.

To verify the tracking ability of the proposed tracker, comparative studies of tracking accuracy and speed of the proposed tracker with particle filter, mean shift and PSO are presented.

The mean-shift based tracker iteratively shifts a data point to the average of data points in its neighborhood, which minimizes the distance between a model histogram representing the target and candidate histograms computed on the current frame.

Secondly two different depth trackers are proposed to handle different scenarios: one is based on depth frame differencing, and the other one is based on the mean shift algorithm which is modified to utilize depth information.