Adaptive LiDAR Sampling and Depth Completion Using Ensemble Variance

Eyal Gofer, Shachar Praisler, Guy Gilboa

Research output: Contribution to journalArticlepeer-review

Abstract

This work considers the problem of depth completion, with or without image data, where an algorithm may measure the depth of a prescribed limited number of pixels. The algorithmic challenge is to choose pixel positions strategically and dynamically to maximally reduce overall depth estimation error. This setting is realized in daytime or nighttime depth completion for autonomous vehicles with a programmable LiDAR. Our method uses an ensemble of predictors to define a sampling probability over pixels. This probability is proportional to the variance of the predictions of ensemble members, thus highlighting pixels that are difficult to predict. By additionally proceeding in several prediction phases, we effectively reduce redundant sampling of similar pixels. Our ensemble-based method may be implemented using any depth-completion learning algorithm, such as a state-of-the-art neural network, treated as a black box. In particular, we also present a simple and effective Random Forest-based algorithm, and similarly use its internal ensemble in our design. We conduct experiments on the KITTI dataset, using the neural network algorithm of Ma et al. and our Random Forest-based learner for implementing our method. The accuracy of both implementations exceeds the state of the art. Compared with a random or grid sampling pattern, our method allows a reduction by a factor of 4–10 in the number of measurements required to attain the same accuracy.

Original languageEnglish
Pages (from-to)8900-8912
Number of pages13
JournalIEEE Transactions on Image Processing
Volume30
DOIs
StatePublished - 2021

Keywords

  • Adaptive sampling
  • Estimation
  • Heuristic algorithms
  • Image reconstruction
  • Laser radar
  • LiDAR
  • Measurement uncertainty
  • Noise measurement
  • Prediction algorithms
  • Random Forest
  • active learning
  • depth completion
  • ensemble methods
  • probability matching

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Graphics and Computer-Aided Design

Fingerprint

Dive into the research topics of 'Adaptive LiDAR Sampling and Depth Completion Using Ensemble Variance'. Together they form a unique fingerprint.

Cite this