The main advantage of this approach over the traditional parametric active contours is that the contours represented by the level set function may break or merge naturally during the evolution, and the topological changes are thus automatically handled [10].
Therefore, the measurement depicting the difference of the contours representing the ground truth and the proposed method is given by: m_{1} = frac{1}{n_{g}} sum limits_{i = 1}^{n_{g}} left(sum limits_{p_{j} in C_{p}^{k_{i}}} dleft(p_{j}, C_{g}^{i}right) right) / left|C_{p}^{k_{i}}right| (27).
In contrast to Fst, the G'st contours are roughly isoclinal to the contours representing performance (Figure 5).
The 2D ellipses around the contour represent the errors in the - and -directions.
So, in the following steps, it is assumed that the contour representing the tomato in the i th image is available and reliable.
The neural network has 60 input neurons, two for each of the 30 points of the resampled snake, and only one output neuron that provides the probability that the contour represents a pedestrian; such probability will be, again, in the range [ ; 1].
