A Clustering Based Denoising Technique for Range Images of Time of Flight Cameras

Abstract

A relatively new technique for measuring the 3D structure of visual scenes is provided by time of flight (TOF) cameras. Reflections of modulated light waves are recorded by a parallel pixel array structure. The time series at each pixel of the resulting image stream is used to estimate travelling time and thus range information. This measuring technique results in pixel dependent noise levels with variances changing over several orders of magnitude dependent on the illumination and material parameters.This makes application of traditional (global) denoising techniques suboptimal. Using free aditional information from the camera and a clustering procedure we can get information about which pixels belong to the same object, and what their noise level is, which allows for locally adapted smoothing. To illustrate the success of this method, we compare it with raw camera output and a traditional method for edge preserving smoothing, anisotropic diffusion [10,12].We show that this mathematical technique works without individual adaptations on two camera systems with highly different noise characteristics.

Optimizing pyramid visibiliy coverage for autonomous robots in 3D environment

“…By adjusting e, the system can tolerate small deviations due to certain acquisition noise. On the other hand, a local errcie nt data preprocessing step in topological denoise or geometric completion/fairing [ 18] [19] could also be helpful in cleaning environment noise.…”

On Optimizing Autonomous Pipeline Inspection

“…By adjusting ε, the system can tolerate small deviations because of certain acquisition noise. On the other hand, a local efficient data preprocessing step in topological denoise or geometric completion/fairing [44], [45] could also be helpful in cleaning environment noise.…”

Denoising Time-Of-Flight Data with Adaptive Total Variation

“…Denoising approaches for ToF data are e.g. presented in [15,10,7,6,11,1]. These approaches are mainly based on bilateral filtering or wavelet techniques, combined with appropriate noise models.…”