Search Results for author: Yang Tang

Found 15 papers, 1 papers with code

Sat2lod2: A Software For Automated Lod-2 Modeling From Satellite-Derived Orthophoto And Digital Surface Model

1 code implementation8 Apr 2022 Shengxi Gui, Rongjun Qin, Yang Tang

We further improve the robustness of the method by 1) intergrading building segmentation based on HRNetV2 into our software; and 2) having implemented a decision strategy to identify complex buildings and directly generate mesh to avoid erroneous LoD2 reconstruction from a system point of view.

Semantic Segmentation

Learn to Adapt for Monocular Depth Estimation

no code implementations26 Mar 2022 Qiyu Sun, Gary G. Yen, Yang Tang, Chaoqiang Zhao

To boost the transferability of depth estimation models, we propose an adversarial depth estimation task and train the model in the pipeline of meta-learning.

Domain Adaptation Meta-Learning +1

Unsupervised Monocular Depth Estimation in Highly Complex Environments

no code implementations28 Jul 2021 Chaoqiang Zhao, Yang Tang, Qiyu Sun

While in some challenging environments, like night, rainy night or snowy winter, the photometry of the same pixel on different frames is inconsistent because of the complex lighting and reflection, so that the day-time unsupervised frameworks cannot be directly applied to these complex scenarios.

Domain Adaptation Monocular Depth Estimation

Multi-task GANs for Semantic Segmentation and Depth Completion with Cycle Consistency

no code implementations29 Nov 2020 Chongzhen Zhang, Yang Tang, Chaoqiang Zhao, Qiyu Sun, Zhencheng Ye, Jürgen Kurths

Semantic segmentation and depth completion are two challenging tasks in scene understanding, and they are widely used in robotics and autonomous driving.

Autonomous Driving Depth Completion +2

Masked GANs for Unsupervised Depth and Pose Prediction with Scale Consistency

no code implementations9 Apr 2020 Chaoqiang Zhao, Gary G. Yen, Qiyu Sun, Chongzhen Zhang, Yang Tang

This paper proposes a masked generative adversarial network (GAN) for unsupervised monocular depth and ego-motion estimation. The MaskNet and Boolean mask scheme are designed in this framework to eliminate the effects of occlusions and impacts of visual field changes on the reconstruction loss and adversarial loss, respectively.

Image Reconstruction Pose Prediction +2

When Autonomous Systems Meet Accuracy and Transferability through AI: A Survey

no code implementations29 Mar 2020 Chongzhen Zhang, Jianrui Wang, Gary G. Yen, Chaoqiang Zhao, Qiyu Sun, Yang Tang, Feng Qian, Jürgen Kurths

Then, we further review the performance of RL and meta-learning from the aspects of accuracy or transferability or both of them in autonomous systems, involving pedestrian tracking, robot navigation and robotic manipulation.

Deblurring Decision Making +11

Monocular Depth Estimation Based On Deep Learning: An Overview

no code implementations14 Mar 2020 Chaoqiang Zhao, Qiyu Sun, Chongzhen Zhang, Yang Tang, Feng Qian

With the rapid development of deep neural networks, monocular depth estimation based on deep learning has been widely studied recently and achieved promising performance in accuracy.

Monocular Depth Estimation

Perception and Navigation in Autonomous Systems in the Era of Learning: A Survey

no code implementations8 Jan 2020 Yang Tang, Chaoqiang Zhao, Jianrui Wang, Chongzhen Zhang, Qiyu Sun, Weixing Zheng, Wenli Du, Feng Qian, Juergen Kurths

Second, we review the visual-based environmental perception and understanding methods based on deep learning, including deep learning-based monocular depth estimation, monocular ego-motion prediction, image enhancement, object detection, semantic segmentation, and their combinations with traditional vSLAM frameworks.

Autonomous Navigation Decision Making +10

Deep Direct Visual Odometry

no code implementations11 Dec 2019 Chaoqiang Zhao, Yang Tang, Qiyu Sun, Athanasios V. Vasilakos

Extensive experiments on the KITTI dataset show that the proposed constraints can effectively improve the scale-consistency of TrajNet when compared with previous unsupervised monocular methods, and integration with TrajNet makes the initialization and tracking of DSO more robust and accurate.

Pose Estimation Pose Prediction +2

Flexible Clustering with a Sparse Mixture of Generalized Hyperbolic Distributions

no code implementations12 Mar 2019 Michael P. B. Gallaugher, Yang Tang, Paul D. McNicholas

A parametrization of the component scale matrices for the mixture of generalized hyperbolic distributions is proposed by including a penalty term in the likelihood constraining the parameters resulting in a flexible model for high dimensional data and a meaningful interpretation.

Text Assisted Insight Ranking Using Context-Aware Memory Network

no code implementations13 Nov 2018 Qi Zeng, Liangchen Luo, Wenhao Huang, Yang Tang

Extracting valuable facts or informative summaries from multi-dimensional tables, i. e. insight mining, is an important task in data analysis and business intelligence.

Robust Order Scheduling in the Fashion Industry: A Multi-Objective Optimization Approach

no code implementations1 Feb 2017 Wei Du, Yang Tang, Sunney Yung Sun Leung, Le Tong, Athanasios V. Vasilakos, Feng Qian

In the fashion industry, order scheduling focuses on the assignment of production orders to appropriate production lines.

Differential Evolution with Event-Triggered Impulsive Control

no code implementations17 Dec 2015 Wei Du, Sunney Yung Sun Leung, Yang Tang, Athanasios V. Vasilakos

In this paper, an event-triggered impulsive control scheme (ETI) is introduced to improve the performance of DE.

Model Based Clustering of High-Dimensional Binary Data

no code implementations11 Apr 2014 Yang Tang, Ryan P. Browne, Paul D. McNicholas

Recent work on clustering of binary data, based on a $d$-dimensional Gaussian latent variable, is extended by incorporating common factor analyzers.

Cannot find the paper you are looking for? You can Submit a new open access paper.