Data compression with Deep Autoencoder

Initial Situation

 

  • Estimation of wooden log rotation angle by comparison with N reference images
  • Loading time of raw reference images too slow for real time system
  • Requirement: Decrease loading time, while keeping accuracy

 

 

Figure 1: Overall compression and reidentification process

Solution

 

  • Development of Deep Autoencoder for Image compression
  • Evaluation of different image compression algorithms for faster loading/storing times

 

 

 

Results

 

  • Faster loading times (x10) by compressing the reference images with the Deep Autoencoder
  • Similar accuracy for the rotation estimation
  • Concept for improved rotation matching strategy