Error in calculation of threshold of frustum.

[johanneskbl]

There were parantheses missing to calculate the mean of min and max. Therefore the frustum was always too large. The expansion factor delta, which in the paper was argued to need to be greater than zero, is set to zero by default. The error in the frustum threshold calculation leads to this choice of delta making more sense.

Although this seems to be a straight hickup, we found that calculating it correctly worsens the performance even if we set the expansion factor to a value such that the frustum is approximately as big as before. The relationship of the frustum size and the network's performance needs to be investigated more. For now, this calculation is in our view an error and the frustum size should be controlled by the expansion factor instead.