The objective of this work is to determine the location of temporal boundaries between signs in continuous sign language videos. Our approach employs 3D convolutional neural network representations with iterative temporal segment refinement to resolve ambiguities between sign boundary cues. We demonstrate the effectiveness of our approach on the BSLCORPUS, PHOENIX14 and BSL-1K datasets, showing considerable improvement over the state of the art and the ability to generalise to new signers, languages and domains.

No abstract

To improve the directivity of a receive beamformer, the scalar apodization weigths are replaced by filters. For a frequency dependent apodization without changing the delay scheme of the dynamic receive beamformer, symmetric FIR filters are used. Different image quality measures are investigated and discussed that allow to quantify the dynamic range (contrast) and detail resolution of an ultrasound system by evaluation of the 2D point spread function. For an automated optimization of the apodization filter transfer functions, the chosen image quality measures are continuous and sufficiently smooth so that a local search algorithm can find a global optimum. It is shown that apodization filters with a small number of taps are sufficient if an additional filter is added after the summation point. Compared to a conventional apodization, this approach offers a significant improvement in image quality and can be achieved with moderate hardware effort well suited for FPGAbased beamformer frontends.

No abstract

In precision engineering scanners are widely used for laser beam positioning. Equipped with cameras, scanners enable process monitoring or even position recognition of the parts to be welded. To allow precise welding or position recognition, it is essential to calibrate a welding system. Instead of calibrating the whole system, most approaches only help to adjust the laser beam position. Consequently, the varying lateral offset between the laser's focus point and the camera's field of view, due to chromatic aberration of the scanner optics. cannot be compensated. Furthermore, these approaches require manual microscopic measurement of weld seams. which comes along with several downsides. This paper proposes two techniques for automatic calibration without these downsides by use of the system-incorporated camera. The first technique is the calibration at laser wavelength. To this end, the system automatically creates laser spots, evaluates their positions and possible offsets, and finally fits an affine model for compensation. The second technique is based oil a specially coded test pattern, which is used for calibration at camera wavelengths. Experimental results confirm the accuracy of the calibration obtained