Weimin Wang

The National Institute of Advanced Industrial Science and Technology (AIST)

Collapsed buildings should be detected immediately after earthquakes for humanitarian assistance and post-disaster recovery. Automatic collapsed building detection using deep learning has recently become increasingly popular because of its superior ability to obtain discriminative feature representations. Among various types of data, airborne 3D po...

We present a lightweight post-processing method to refine the semantic segmentation results of point cloud sequences. Most existing methods usually segment frame by frame and encounter the inherent ambiguity of the problem: based on a measurement in a single frame, labels are sometimes difficult to predict even for humans. To remedy this problem, w...

Mobile stereo-matching systems have become an important part of many applications, such as automated-driving vehicles and autonomous robots. Accurate stereo-matching methods usually lead to high computational complexity; however, mobile platforms have only limited hardware resources to keep their power consumption low; this makes it difficult to ma...

3D point clouds can flexibly represent continuous surfaces and can be used for various applications; however, the lack of structural information makes point cloud recognition challenging. Recent edge-aware methods mainly use edge information as an extra feature that describes local structures to facilitate learning. Although these methods show that...

Automated video-based assessment of surgical skills is a promising task in assisting young surgical trainees, especially in poor-resource areas. Existing works often resort to a CNN-LSTM joint framework that models long-term relationships by LSTMs on spatially pooled short-term CNN features. However, this practice would inevitably neglect the diffe...

Automated video-based assessment of surgical skills is a promising task in assisting young surgical trainees, especially in poor-resource areas. Existing works often resort to a CNN-LSTM joint framework that models long-term relationships by LSTMs on spatially pooled short-term CNN features. However, this practice would inevitably neglect the diffe...

Modeling the local surface geometry is challenging in 3D point cloud understanding due to the lack of connectivity information. Most prior works model local geometry using various convolution operations. We observe that the convolution can be equivalently decomposed as a weighted combination of a local and a global component. With this observation,...

Learning point clouds is challenging due to the lack of connectivity information, i.e., edges. Although existing edge-aware methods can improve the performance by modeling edges, how edges contribute to the improvement is unclear. In this study, we propose a method that automatically learns to enhance/suppress edges while keeping the its working me...

Deep learning models as an emerging topic have shown great progress in various fields. Especially, visualization tools such as class activation mapping methods provided visual explanation on the reasoning of convolutional neural networks (CNNs). By using the gradients of the network layers, it is possible to demonstrate where the networks pay atten...

Mobile stereo-matching systems have become an important part of many applications, such as automated-driving vehicles and autonomous robots. Accurate stereo-matching methods usually lead to high computational complexity; however, mobile platforms have only limited hardware resources to keep their power consumption low; this makes it difficult to ma...

The attribution method provides a direction for interpreting opaque neural networks in a visual way by identifying and visualizing the input regions/pixels that dominate the output of a network. Regarding the attribution method for visually explaining video understanding networks, it is challenging because of the unique spatiotemporal dependencies...

The attribution method provides a direction for interpreting opaque neural networks in a visual way by identifying and visualizing the input regions/pixels that dominate the output of a network. Regarding the attribution method for visually explaining video understanding networks, it is challenging because of the unique spatiotemporal dependencies...

In this work, we propose and investigate a user-centric framework for the delivery of omnidirectional video (ODV) on VR systems by taking advantage of visual attention (saliency) models for bitrate allocation module. For this purpose, we formulate a new bitrate allocation algorithm that takes saliency map and nonlinear sphere-to-plane mapping into...

Identifying and visualizing regions that are significant for a given deep neural network model, i.e., attribution methods, is still a vital but challenging task, especially for spatio-temporal networks that process videos as input. Albeit some methods that have been proposed for video attribution, it is yet to be studied what types of network struc...

This paper presents a novel semantic-based online extrinsic calibration approach, SOIC (so, I see), for Light Detection and Ranging (LiDAR) and camera sensors. Previous online calibration methods usually need prior knowledge of rough initial values for optimization. The proposed approach removes this limitation by converting the initialization prob...

3D semantic segmentation of point cloud aims at assigning semantic labels to each point by utilizing and respecting the 3D representation of the data. Detailed 3D semantic segmentation of urban areas can assist policymakers, insurance companies, governmental agencies for applications such as urban growth assessment, disaster management, and traffic...

We address automatic matching of street images with relevant web resources to enable identification of store signage in street images. Identification methods for signage usually involve image matching, which attempts to match query images to other similar viewings using pre-labeled copies from a target dataset. Manual target dataset such as a finge...

This paper presents a novel method for detecting scene changes from a pair of images with a difference of camera viewpoints using a dense optical flow based change detection network. In the case that camera poses of input images are fixed or known, such as with surveillance and satellite cameras, the pixel correspondence between the images captured...

This paper presents a novel method for fully automatic and convenient extrinsic calibration of a 3D LiDAR and a panoramic camera with a normally printed chessboard. The proposed method is based on the 3D corner estimation of the chessboard from the sparse point cloud generated by one frame scan of the LiDAR. To estimate the corners, we formulate a...

In this paper, we propose a method for cloud removal from visible light RGB satellite images by extending the conditional Generative Adversarial Networks (cGANs) from RGB images to multispectral images. Satellite images have been widely utilized for various purposes, such as natural environment monitoring (pollution, forest or rivers), transportati...

The segmentation of point clouds is an important aspect of automated processing tasks such as semantic extraction. However, the sparsity and non-uniformity of the point clouds gathered by the popular 3D mobile LiDAR devices pose many challenges for existing segmentation methods. To improve the segmentation results of point clouds from mobile LiDAR...

PDR (Pedestrian Dead Reckoning) is a very promising technology for indoor positioning. We held a technical challenge, entitled the UbiComp/ISWC 2015 PDR Challenge, consisting of the following three categories: Algorithm, Evaluation, and Exhibition. In this paper, we specially focus on collected data for PDR algorithm category. UbiComp/ISWC particip...

A low-voltage controller-based all-digital phase-locked loop (ADPLL) utilized in the medical implant communication service (MICS) frequency band was designed in this study. In the proposed design, controller-based loop topology is used to control the phase and frequency to ensure the reliable handling of the ADPLL output signal. A digitally-control...

In this work, we implement a mobile system called Velobug to measures 3D data of the environment. Velobug could generate dense and colored point cloud to reconstruct the environment for 3D mapping with long effective range. Velobug is mainly consisted of a Velodyne HDL-32e LiDAR senor and a Point Grey Research Ladybug3 panoramic camera. The LiDAR s...

A design procedure of an all-digital phase-locked loop (ADPLL) based on phase selection mechanism with loop stability independent of process, supply voltage and temperature is presented. A poly-phase filter and a phase interpolator are used to generate multiple phases to reduce the phase error. The modeling of proposed ADPLL structure is extensivel...