Related papers: A Thru-free Multiline Calibration
Most intelligent transportation systems use a combination of radar sensors and cameras for robust vehicle perception. The calibration of these heterogeneous sensor types in an automatic fashion during system operation is challenging due to…
In many cases beam coupling impedances or wake fields are calculated with computer simulator such as CST Studio Suite, GdfidL Electromagnetic Field Simulator and so on. But evaluation with the stretched-wire method is still very useful by…
Model regularization requires extensive manual tuning to balance complexity against overfitting. Cross-regularization resolves this tradeoff by directly adapting regularization parameters through validation gradients during training. The…
A non-invasive, in-situ calibration method for Total Internal Reflection Microscopy (TIRM) based on optical tweezing is presented which greatly expands the capabilities of this technique. We show that by making only simple modifications to…
In the context of robotics, accurate ground-truth positioning is the cornerstone for the development of mapping and localization algorithms. In outdoor environments and over long distances, total stations provide accurate and precise…
This paper is about regularizing deep convolutional networks (CNNs) based on an adaptive framework for transfer learning with limited training data in the target domain. Recent advances of CNN regularization in this context are commonly due…
Multi-task learning (MTL) seeks to improve the generalized performance of learning specific tasks, exploiting useful information incorporated in related tasks. As a promising area, this paper studies an MTL-based control approach…
Transmission interface power flow adjustment is a critical measure to ensure the security and economy operation of power systems. However, conventional model-based adjustment schemes are limited by the increasing variations and…
We propose a novel distance-based regularization method for deep metric learning called Multi-level Distance Regularization (MDR). MDR explicitly disturbs a learning procedure by regularizing pairwise distances between embedding vectors…
Albeit achieving high predictive accuracy across many challenging computer vision problems, recent studies suggest that deep neural networks (DNNs) tend to make overconfident predictions, rendering them poorly calibrated. Most of the…
This paper presents a novel deep reinforcement learning (DRL)-based control strategy for achieving precise and robust output voltage regulation in LCC-S resonant converters, specifically designed for wireless power transfer applications.…
Calibration of fixtures in robotic work cells is essential but also time consuming and error-prone, and poor calibration can easily lead to wasted debugging time in downstream tasks. Contact-based calibration methods let the user measure…
Deep neural networks (DNNs) are poorly calibrated when trained in conventional ways. To improve confidence calibration of DNNs, we propose a novel training method, distance-based learning from errors (DBLE). DBLE bases its confidence…
Accurately calibrating light field camera is essential to its applications. Rapid progress has been made in this area in the past decades. In this paper, detailed analysis was first performed towards the state of the art projection models…
Camera calibration is a necessity in various tasks including 3D reconstruction, hand-eye coordination for a robotic interaction, autonomous driving, etc. In this work we propose a novel method to predict extrinsic (baseline, pitch, and…
Non-intrusive displacement measurement technique has a distinct edge over displacement sensors working in contact mode. Laser Doppler Vibrometry based schemes (LDV) offer such an advantage. However, the measurements are limited up to…
This paper focuses on a novel and challenging detection scenario: A majority of true objects/instances is unlabeled in the datasets, so these missing-labeled areas will be regarded as the background during training. Previous art on this…
Scanning Thermal Microscopy (SThM) is a scanning probe technique aimed at quantitative characterization of local thermal properties at the length scale down to tens of nanometers. With many probe designs and approaches to interpretation of…
In this work, we propose BP-MVSNet, a convolutional neural network (CNN)-based Multi-View-Stereo (MVS) method that uses a differentiable Conditional Random Field (CRF) layer for regularization. To this end, we propose to extend the BP layer…
The paper presents a reflectionless stripline filter with reduced dimensions having a single bandwidth over a wide frequency range. The filter consists of coupled strip lines and RLC circuits included in the diagonal ports of the coupled…