|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | Progressive LiDAR Adaptation for Road Detection显示文摘Despite rapid developments in visual image-based road detection, robustly identifying road areas in visual images remains challenging due to issues like illumination changes and blurry images. To this end, LiDAR sensor data can be incorporated to improve the visual image-based road detection,because LiDAR data is less susceptible to visual noises. However,the main difficulty in introducing LiDAR information into visual image-based road detection is that LiDAR data and its extracted features do not share the same space with the visual data and visual features. Such gaps in spaces may limit the benefits of LiDAR information for road detection. To overcome this issue, we introduce a novel Progressive LiDAR adaptation-aided road detection(PLARD) approach to adapt LiDAR information into visual image-based road detection and improve detection performance. In PLARD, progressive LiDAR adaptation consists of two subsequent modules: 1) data space adaptation, which transforms the LiDAR data to the visual data space to align with the perspective view by applying altitude difference-based transformation; and 2) feature space adaptation, which adapts LiDAR features to visual features through a cascaded fusion structure. Comprehensive empirical studies on the well-known KITTI road detection benchmark demonstrate that PLARD takes advantage of both the visual and LiDAR information, achieving much more robust road detection even in challenging urban scenes. In particular, PLARD outperforms other state-of-theart road detection models and is currently top of the publicly accessible benchmark leader-board. | Zhe Chen Jing Zhang Dacheng Tao | 2019 | IEEE/CAA Journal of Automatica Sinica2019，6，3： | 8 |
| 2 | Balance Control of a Biped Robot on a Rotating Platform Based on Efficient Reinforcement Learning显示文摘In this work,we combined the model based reinforcement learning(MBRL)and model free reinforcement learning(MFRL)to stabilize a biped robot(NAO robot)on a rotating platform,where the angular velocity of the platform is unknown for the proposed learning algorithm and treated as the external disturbance.Nonparametric Gaussian processes normally require a large number of training data points to deal with the discontinuity of the estimated model.Although some improved method such as probabilistic inference for learning control(PILCO)does not require an explicit global model as the actions are obtained by directly searching the policy space,the overfitting and lack of model complexity may still result in a large deviation between the prediction and the real system.Besides,none of these approaches consider the data error and measurement noise during the training process and test process,respectively.We propose a hierarchical Gaussian processes(GP)models,containing two layers of independent GPs,where the physically continuous probability transition model of the robot is obtained.Due to the physically continuous estimation,the algorithm overcomes the overfitting problem with a guaranteed model complexity,and the number of training data is also reduced.The policy for any given initial state is generated automatically by minimizing the expected cost according to the predefined cost function and the obtained probability distribution of the state.Furthermore,a novel Q(λ)based MFRL method scheme is employed to improve the policy.Simulation results show that the proposed RL algorithm is able to balance NAO robot on a rotating platform,and it is capable of adapting to the platform with varying angular velocity. | Ao Xi Thushal Wijekoon Mudiyanselage Dacheng Tao Chao Chen | 2019 | IEEE/CAA Journal of Automatica Sinica2019，6，4： | 5 |
| 3 | Guest Editorial for Special Issue on Cognitive Computing for Collaborative Robotics显示文摘Cognitive Computing breaks the boundary between two separate fields,neuroscience and computer science.It paves the way for machines to have reasoning abilities which is analogous to human.The research field of cognitive computing is interdisciplinary,and uses knowledge and methods from many areas such as psychology,biology,signal processing,physics,information theory,mathematics,and statistics.The development of cognitive computing will keep cross-fertilizing these research areas.However,in collaborative robotics applications there still remain many open problems for using cognitive computing theories.Technologies like computational cognition and perception(CCP)and computational neuroscience(CN)are driving as the best tools for upgrading the robots with near human intelligence,which can be intended to physically interact with humans in a shared workspace. | Huimin Lu Dongpu Cao Dacheng Tao Schahram Dustdar Pinhan Ho | 2021 | IEEE/CAA Journal of Automatica Sinica2021，8，7： | 2 |
| 4 | Image Quality Assessment Based on Multiscale Geometric Analysis 显示文摘 | GAO Xinbo LU Wen TAO Dacheng | 2009 | IEEE Transactions on Image Processing2009，18，7： | 1 |
| 5 | Robust face recognition via occlusion dictionary learning显示文摘 | Ou Weihua You Xinge Tao Dacheng | 2014 | Pattern Recognition2014，47，4： | 1 |
| 6 | Viewindependent human behavior analysis 显示文摘 | Huang Kaiqi Tao Dacheng Yuan Yuan* | 2009 | IEEE Trans onSystems Man and Cybernetics Part B: Cybernetics2009，39，4： | 1 |
| 7 | Direct Kernel Biased Discriminant Analysis: A New Content-based Image Retrieval Relevance Feedback Algorithm显示文摘 | Tao Dacheng Tang Xiaoou Li Xuelong | 2006 | IEEE Transactions on Multimedia2006，8，4： | 1 |
| 8 | Joint learning for single-image super-resolution via a coupled constraint显示文摘 | Gao Xinbo Zhang Kaibing Tao Dacheng | 2012 | IEEE Transactions on Image Processing2012，21，2： | 1 |
| 9 | Multimodal Graph-Based Reranking for Web Image Search显示文摘 | WANG Meng LI Hao TAO Dacheng | 2012 | IEEE Transactions on Image Processing(S1057-7149)2012，21，11： | 1 |
| 10 | Single image super-resolution with multiscale similarity learning显示文摘 | Zhang Kaibing Gao Xinbo Tao Dacheng | 2013 | IEEE Transactions on Neural Networks and Leaning Systems2013，24，10： | 1 |
| 11 | General Tensor Discriminant Analysis and Gabor Features for Gait Recognition显示文摘 | Tao Dacheng Li Xuelong Wu Xindong | 2007 | IEEE Trans on Pattern Analysis and Machine Intelligence2007，29，10： | 1 |
| 12 | Patch alignment for dimensionality reduction 显示文摘 | Zhang Tianhao Tao Dacheng Li Xuelong | 2009 | IEEE Transactions on Knowledge and Data Engineer-ing2009，21，9： | 1 |
| 13 | Multiview Hessian regularization for image annotation显示文摘 | Liu Weifeng Tao Dacheng | 2013 | Image Processing2013，22，7： | 1 |
| 14 | Color to gray: visual cue preservation显示文摘 | Song Mingli Tao Dacheng Chen Chun | 2010 | IEEE Transactions on Pattern Analysis and Machine Intelligence2010，32，9： | 1 |
| 15 | Multiview Hessian discriminative sparse coding for image annotation显示文摘 | Liu Weifeng Tao Dacheng Jun Cheng | 2014 | Computer Vision and Image Understanding2014，118，1： | 1 |
| 16 | Joint learning for single-image super-resolution via a coupled constraint 显示文摘 | Gao Xinbo Zhang Kaibing Tao Dacheng | 2012 | IEEE Trans on Image Processing2012，21，2： | 1 |
| 17 | Multiview vectorvalued manifold regularization for multilabel image classification显示文摘 | Luo Yong Tao Dacheng Xu Chang | 2013 | Neural Networks and Learning Systems2013，24，5： | 1 |
| 18 | Manifold regularized discriminative nonnegative matrix factorization with fast gradient descent显示文摘 | GUAN Naiyang TAO Dacheng LU Zhigang | 2011 | IEEE Transactions on Image Processing2011，20，7： | 1 |
| 19 | Image Categorization: Graph Edit Distance+Edge Direction Histogram显示文摘 | Gao Xinbo Xiao Bing Tao Dacheng | 2008 | Pattern Recognition2008，41，10： | 1 |
| 20 | Patch alignment for dimensionality reduction显示文摘 | Zhang Tianhao Tao Dacheng Zhao Deli | 2009 | IEEE Transactions on Knowledge and Data Engineering2009，21，9： | 1 |
您所在的机构暂未开通此部分的功能，请联系管理员