Lingyan Ran | Stevens Institute of Technology (original) (raw)
Papers by Lingyan Ran
Proceedings of the 14th International Conference on Advances in Mobile Computing and Multi Media, 2016
This paper focuses on the use of spherical cameras for autonomous quadrone navigation tasks. Prev... more This paper focuses on the use of spherical cameras for autonomous quadrone navigation tasks. Previous works of literature for navigation mainly lie in two categories: scene-oriented simultaneous localization and mapping and robot-oriented heading fields lane detection and trajectory tracking. Those methods face the challenges of either high computation cost or heavy labelling and calibration requirements. In this paper, we propose to formulate the spherical image navigation as an image classification problem, which significantly simplifies the orientation estimation and path prediction procedure and accelerates the navigation process. More specifically, we train an end-to-end convolutional network on our spherical image dataset with novel orientation categories labels. This trained network can give precise predictions on potential path directions with single spherical images. Experimental results on our Spherical-Navi dataset demonstrate that the proposed approach outperforms the co...
This paper focuses on the use of spherical cameras for autonomous robot navigation tasks. Previou... more This paper focuses on the use of spherical cameras for autonomous robot navigation tasks. Previous works of literature mainly lie in two categories: scene oriented simultaneous localization and mapping and robot oriented heading fields lane detection and trajectory tracking. Those methods face the challenges of either high computation cost or heavy labelling and calibration requirements. In this paper, we propose to formulate the spherical image navigation as an image classification problem, which significantly simplifies the orientation estimation and path prediction procedure and accelerates the navigation process. More specifically, we train an end-to-end convolutional network on our spherical image dataset with novel orientation categories labels. This trained network can give precise predictions on potential path directions with single spherical images. Experimental results on our Spherical-Navi dataset demonstrate that the proposed approach outperforms the comparing methods in...
Breast histology images classification is a time- and labor-intensive task due to the complicated... more Breast histology images classification is a time- and labor-intensive task due to the complicated structural and textural information contained. Recent deep learning-based methods are less accurate due to the ignorance of the interfering multiscale contextual information in histology images. In this paper, we propose the multiscale spatial attention network (MSA-Net) to deal with these challenges. We first perform adaptive spatial transformation on histology microscopy images at multiple scales using a spatial attention (SA) module to make the model focus on discriminative content. Then we employ a classification network to categorize the transformed images and use the ensemble of the predictions obtained at multiple scales as the classification result. We evaluated our MSA-Net against four state-of-the-art methods on the BACH challenge dataset. Our results show that the proposed MSA-Net achieves a higher accuracy than the rest methods in the five-fold cross validation on training d...
Hyperspectral image (HSI) classification deals with the problem of pixel-wise spectrum labelling.... more Hyperspectral image (HSI) classification deals with the problem of pixel-wise spectrum labelling. Traditional HSI classification algorithms focus on two major stages: feature extraction and classifier design. Though studied for decades, HSI classification hasn't been perfectly solved. One of the main reasons relies on the fact that features extracted by embedding methods can hardly match an ad hoc classifier. Recently, deep learning methods achieve an end-to-end mechanism and can learn features suitable for classification from the raw data. Inspired by the newly proposed work on deep learning for HSI classification, in this paper, we propose to build a deep convolutional network based on the analysis of spectral band discriminative characteristics. More specifically, we first split the spectrum bands into groups based on their correlation relationships. Then we build a band variant CNN submodel, where each group is modelled by one of those submodels. Meanwhile, a conventional CN...
Pattern Recognition Letters
IEEE Access
Human pose estimation from a monocular image has attracted lots of interest due to its huge poten... more Human pose estimation from a monocular image has attracted lots of interest due to its huge potential application in many areas. The performance of 2D human pose estimation has been improved a lot with the emergence of deep convolutional neural network. In contrast, the recovery of 3D human pose from an 2D pose is still a challenging problem. Currently, most of the methods try to learn a universal map, which can be applied for all human poses in any viewpoints. However, due to the large variety of human poses and camera viewpoints, it is very difficult to learn a such universal mapping from current datasets for 3D pose estimation. Instead of learning a universal map, we propose to learn an adaptive viewpoint transformation module, which transforms the 2D human pose to a more suitable viewpoint for recovering the 3D human pose. Specifically, our transformation module takes a 2D pose as input and predicts the transformation parameters. Rather than some hand-crafted criteria, this module is directly learned from the datasets and depends on the input 2D pose in testing phrase. Then the 3D pose is recovered from this transformed 2D pose. Since the difficulty of 3D pose recovery becomes smaller, we can obtain more accurate estimation results. Experiments on Human3.6M and MPII datasets show that the proposed adaptive viewpoint transformation can improve the performance of 3D human pose estimation. INDEX TERMS 3D human pose estimation, adaptive viewpoint transformation, deep convolutional neural network.
Sensors (Basel, Switzerland), Jan 23, 2017
During recent years, convolutional neural network (CNN)-based methods have been widely applied to... more During recent years, convolutional neural network (CNN)-based methods have been widely applied to hyperspectral image (HSI) classification by mostly mining the spectral variabilities. However, the spatial consistency in HSI is rarely discussed except as an extra convolutional channel. Very recently, the development of pixel pair features (PPF) for HSI classification offers a new way of incorporating spatial information. In this paper, we first propose an improved PPF-style feature, the spatial pixel pair feature (SPPF), that better exploits both the spatial/contextual information and spectral information. On top of the new SPPF, we further propose a flexible multi-stream CNN-based classification framework that is compatible with multiple in-stream sub-network designs. The proposed SPPF is different from the original PPF in its paring pixel selection strategy: only pixels immediately adjacent to the central one are eligible, therefore imposing stronger spatial regularization. Additio...
Sensors (Basel, Switzerland), Jan 23, 2017
During recent years, convolutional neural network (CNN)-based methods have been widely applied to... more During recent years, convolutional neural network (CNN)-based methods have been widely applied to hyperspectral image (HSI) classification by mostly mining the spectral variabilities. However, the spatial consistency in HSI is rarely discussed except as an extra convolutional channel. Very recently, the development of pixel pair features (PPF) for HSI classification offers a new way of incorporating spatial information. In this paper, we first propose an improved PPF-style feature, the spatial pixel pair feature (SPPF), that better exploits both the spatial/contextual information and spectral information. On top of the new SPPF, we further propose a flexible multi-stream CNN-based classification framework that is compatible with multiple in-stream sub-network designs. The proposed SPPF is different from the original PPF in its paring pixel selection strategy: only pixels immediately adjacent to the central one are eligible, therefore imposing stronger spatial regularization. Additio...
Lecture Notes in Computer Science, 2014
Proceedings of the 14th International Conference on Advances in Mobile Computing and Multi Media, 2016
This paper focuses on the use of spherical cameras for autonomous quadrone navigation tasks. Prev... more This paper focuses on the use of spherical cameras for autonomous quadrone navigation tasks. Previous works of literature for navigation mainly lie in two categories: scene-oriented simultaneous localization and mapping and robot-oriented heading fields lane detection and trajectory tracking. Those methods face the challenges of either high computation cost or heavy labelling and calibration requirements. In this paper, we propose to formulate the spherical image navigation as an image classification problem, which significantly simplifies the orientation estimation and path prediction procedure and accelerates the navigation process. More specifically, we train an end-to-end convolutional network on our spherical image dataset with novel orientation categories labels. This trained network can give precise predictions on potential path directions with single spherical images. Experimental results on our Spherical-Navi dataset demonstrate that the proposed approach outperforms the co...
This paper focuses on the use of spherical cameras for autonomous robot navigation tasks. Previou... more This paper focuses on the use of spherical cameras for autonomous robot navigation tasks. Previous works of literature mainly lie in two categories: scene oriented simultaneous localization and mapping and robot oriented heading fields lane detection and trajectory tracking. Those methods face the challenges of either high computation cost or heavy labelling and calibration requirements. In this paper, we propose to formulate the spherical image navigation as an image classification problem, which significantly simplifies the orientation estimation and path prediction procedure and accelerates the navigation process. More specifically, we train an end-to-end convolutional network on our spherical image dataset with novel orientation categories labels. This trained network can give precise predictions on potential path directions with single spherical images. Experimental results on our Spherical-Navi dataset demonstrate that the proposed approach outperforms the comparing methods in...
Breast histology images classification is a time- and labor-intensive task due to the complicated... more Breast histology images classification is a time- and labor-intensive task due to the complicated structural and textural information contained. Recent deep learning-based methods are less accurate due to the ignorance of the interfering multiscale contextual information in histology images. In this paper, we propose the multiscale spatial attention network (MSA-Net) to deal with these challenges. We first perform adaptive spatial transformation on histology microscopy images at multiple scales using a spatial attention (SA) module to make the model focus on discriminative content. Then we employ a classification network to categorize the transformed images and use the ensemble of the predictions obtained at multiple scales as the classification result. We evaluated our MSA-Net against four state-of-the-art methods on the BACH challenge dataset. Our results show that the proposed MSA-Net achieves a higher accuracy than the rest methods in the five-fold cross validation on training d...
Hyperspectral image (HSI) classification deals with the problem of pixel-wise spectrum labelling.... more Hyperspectral image (HSI) classification deals with the problem of pixel-wise spectrum labelling. Traditional HSI classification algorithms focus on two major stages: feature extraction and classifier design. Though studied for decades, HSI classification hasn't been perfectly solved. One of the main reasons relies on the fact that features extracted by embedding methods can hardly match an ad hoc classifier. Recently, deep learning methods achieve an end-to-end mechanism and can learn features suitable for classification from the raw data. Inspired by the newly proposed work on deep learning for HSI classification, in this paper, we propose to build a deep convolutional network based on the analysis of spectral band discriminative characteristics. More specifically, we first split the spectrum bands into groups based on their correlation relationships. Then we build a band variant CNN submodel, where each group is modelled by one of those submodels. Meanwhile, a conventional CN...
Pattern Recognition Letters
IEEE Access
Human pose estimation from a monocular image has attracted lots of interest due to its huge poten... more Human pose estimation from a monocular image has attracted lots of interest due to its huge potential application in many areas. The performance of 2D human pose estimation has been improved a lot with the emergence of deep convolutional neural network. In contrast, the recovery of 3D human pose from an 2D pose is still a challenging problem. Currently, most of the methods try to learn a universal map, which can be applied for all human poses in any viewpoints. However, due to the large variety of human poses and camera viewpoints, it is very difficult to learn a such universal mapping from current datasets for 3D pose estimation. Instead of learning a universal map, we propose to learn an adaptive viewpoint transformation module, which transforms the 2D human pose to a more suitable viewpoint for recovering the 3D human pose. Specifically, our transformation module takes a 2D pose as input and predicts the transformation parameters. Rather than some hand-crafted criteria, this module is directly learned from the datasets and depends on the input 2D pose in testing phrase. Then the 3D pose is recovered from this transformed 2D pose. Since the difficulty of 3D pose recovery becomes smaller, we can obtain more accurate estimation results. Experiments on Human3.6M and MPII datasets show that the proposed adaptive viewpoint transformation can improve the performance of 3D human pose estimation. INDEX TERMS 3D human pose estimation, adaptive viewpoint transformation, deep convolutional neural network.
Sensors (Basel, Switzerland), Jan 23, 2017
During recent years, convolutional neural network (CNN)-based methods have been widely applied to... more During recent years, convolutional neural network (CNN)-based methods have been widely applied to hyperspectral image (HSI) classification by mostly mining the spectral variabilities. However, the spatial consistency in HSI is rarely discussed except as an extra convolutional channel. Very recently, the development of pixel pair features (PPF) for HSI classification offers a new way of incorporating spatial information. In this paper, we first propose an improved PPF-style feature, the spatial pixel pair feature (SPPF), that better exploits both the spatial/contextual information and spectral information. On top of the new SPPF, we further propose a flexible multi-stream CNN-based classification framework that is compatible with multiple in-stream sub-network designs. The proposed SPPF is different from the original PPF in its paring pixel selection strategy: only pixels immediately adjacent to the central one are eligible, therefore imposing stronger spatial regularization. Additio...
Sensors (Basel, Switzerland), Jan 23, 2017
During recent years, convolutional neural network (CNN)-based methods have been widely applied to... more During recent years, convolutional neural network (CNN)-based methods have been widely applied to hyperspectral image (HSI) classification by mostly mining the spectral variabilities. However, the spatial consistency in HSI is rarely discussed except as an extra convolutional channel. Very recently, the development of pixel pair features (PPF) for HSI classification offers a new way of incorporating spatial information. In this paper, we first propose an improved PPF-style feature, the spatial pixel pair feature (SPPF), that better exploits both the spatial/contextual information and spectral information. On top of the new SPPF, we further propose a flexible multi-stream CNN-based classification framework that is compatible with multiple in-stream sub-network designs. The proposed SPPF is different from the original PPF in its paring pixel selection strategy: only pixels immediately adjacent to the central one are eligible, therefore imposing stronger spatial regularization. Additio...
Lecture Notes in Computer Science, 2014