- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
[IEEE 2018 15th Conference on Computer and Robot Vision (CRV) - Toronto, ON, Canada (2018.5.8-2018.5.10)] 2018 15th Conference on Computer and Robot Vision (CRV) - Learning a Bias Correction for Lidar-Only Motion Estimation
摘要： This paper presents a novel technique to correct for bias in a classical estimator using a learning approach. We apply a learned bias correction to a lidar-only motion estimation pipeline. Our technique trains a Gaussian process (GP) regression model using data with ground truth. The inputs to the model are high-level features derived from the geometry of the point-clouds, and the outputs are the predicted biases between poses computed by the estimator and the ground truth. The predicted biases are applied as a correction to the poses computed by the estimator. Our technique is evaluated on over 50 km of lidar data, which includes the KITTI odometry benchmark and lidar datasets collected around the University of Toronto campus. After applying the learned bias correction, we obtained significant improvements to lidar odometry in all datasets tested. We achieved around 10% reduction in errors on all datasets from an already accurate lidar odometry algorithm, at the expense of only less than 1% increase in computational cost at run-time.
关键词： Lidar Odometry,Gaussian Process,Motion Estimation,Bias Correction
更新于2025-09-23 15:23:52
-
Maintaining the predictive abilities of egg freshness models on new variety based on VIS-NIR spectroscopy technique
摘要： This research was performed to study calibration model transfer between White Leghorns eggs and Bantam eggs for prediction of egg freshness by visible near infrared (VIS-NIR) spectroscopy. Transmission spectra of the two varieties were acquired in the equatorial region of the eggs. And albumen pH as the freshness evaluating parameter was measured using traditional destructive methods. After outliers were eliminated by Mahalanobis distance combined with principal component analysis (PCA), partial least squares regression (PLSR) with different preprocessing methods was used to develop prediction models. Global updating, direct standardization (DS) and slope/bias correction (SBC) were evaluated to transfer calibration models from one variety to another. The Kennard-Stone (KS) algorithm was used to select standardization samples. White Leghorns eggs and Bantam eggs as the master variety in turn were compared to find superior master variety. Application of the slope/bias correction (SBC) algorithm obtained the best prediction results of albumen pH. And the better slope/bias correction (SBC) transfer performance with a rp of 0.908 and a RMSEP of 0.133 was found when Bantam eggs were as the superior master variety.
关键词： Slope/bias correction,Visible near infrared spectroscopy,Direct standardization,Global updating,Egg
更新于2025-09-19 17:15:36