检索结果-南通市图书馆

Livestock detection in aerial images using a fully convolutional network

在线全文

学校读者我要写书评

暂无评论

Computational Visual Media 2019年第2期5卷 221-228页

作者： Liang Han Pin Tao ralph r.martin Department of Computer Technology and Application Qinghai UniversityXiningChina Department of Computer Science and Technology Tsinghua UniversityBeijingChina School of Computer Science and Informatics Cardiff UniversityCardiffWalesUK

In order to accurately count the number of animals grazing on grassland, we present a livestock detection algorithm using modified versions of U-net and Google Inception-v4 net. This method works well to detect dense and touching instances. We also introduce a dataset for livestock detection in aerial images, consisting of 89 aerial images collected by quadcopter. Each image has resolution of about 3000 ×4000 pixels, and contains livestock with varying shapes,scales, and *** evaluate our method by comparison against Faster rCNN and Yolo-v3 algorithms using our aerial livestock dataset. The average precision of our method is better than Yolo-v3 and is comparable to Faster rCNN.

关键词： livestock detection segmentation classification

As-rigid-As-Possible Surface Morphing

在线全文

学校读者我要写书评

暂无评论

Journal of Computer Science & Technology 2011年第3期26卷 548-557页

作者：刘亚姝严寒冰 ralph r.martin Department of Computer Science Beijing University of Civil Engineering and Architecture National Computer Network Emergency response Technical Team/Coordination Center of China School of Computer Science Cardiff University

This paper presents a new morphing method based on the ＂as-rigid-as-possible＂ approach. Unlike the original as-rigid-as-possible method, we avoid the need to construct a consistent tetrahedral mesh, but instead require a consistent triangle surface mesh and from it create a tetrahedron for each surface triangle. Our new approach has several significant advantages. It is much easier to create a consistent triangle mesh than to create a consistent tetrahedral mesh. Secondly, the equations arising from our approach can be solved much more efficiently than the corresponding equations for a tetrahedral mesh. Finally, by incorporating the translation vector in the energy functional controlling interpolation, our new method does not need the user to arbitrarily fix any vertex to obtain a solution, allowing artists automatic control of interpolated mesh positions.

关键词： morphing simplex transformation interpolation

Panorama completion for street views

在线全文

学校读者我要写书评

暂无评论

Computational Visual Media 2015年第1期1卷 49-57页

作者： Zhe Zhu ralph r.martin Shi-Min Hu TNLIST Department of Computer Science and Technology Tsinghua University School of Computer Science & Informatics Cardiff University

This paper considers panorama images used for street views. Their viewing angle of 360° causes pixels at the top and bottom to appear stretched and warped. Although current image completion algorithms work well, they cannot be directly used in the presence of such distortions found in panoramas of street views. We thus propose a novel approach to complete such 360° panoramas using optimizationbased projection to deal with distortions. Experimental results show that our approach is efficient and provides an improvement over standard image completion algorithms.

关键词： image completion panorama street views structure-rectifying warp

robust tracking-by-detection using a selection and completion mechanism

在线全文

学校读者我要写书评

暂无评论

Computational Visual Media 2017年第3期3卷 285-294页

作者： ruochen Fan Fang-Lue Zhang Min Zhang ralph r.martin Tsinghua University School of Engineering and Computer Science Victoria University of Wellington Center of Mathematical Sciences and Applications Harvard University School of Computer Science and Informatics Cardiff University

It is challenging to track a target continuously in videos with long-term occlusion,or objects which leave then re-enter a *** tracking algorithms combined with onlinetrained object detectors perform unreliably in complex conditions, and can only provide discontinuous trajectories with jumps in position when the object is occluded. This paper proposes a novel framework of tracking-by-detection using selection and completion to solve the abovementioned problems. It has two components, tracking and trajectory completion. An offline-trained object detector can localize objects in the same category as the object being tracked. The object detector is based on a highly accurate deep learning model. The object selector determines which object should be used to re-initialize a traditional tracker. As the object selector is trained online,it allows the framework to be adaptable. During completion, a predictive non-linear autoregressive neural network completes any discontinuous *** tracking component is an online real-time algorithm, and the completion part is an after-theevent mechanism. Quantitative experiments show a significant improvement in robustness over prior stateof-the-art methods.

关键词： object tracking detection proposal selection trajectory completion

3D modeling and motion parallax for improved videoconferencing

在线全文

学校读者我要写书评

暂无评论

Computational Visual Media 2016年第2期2卷 131-142页

作者： Zhe Zhu ralph r.martin robert Pepperell Alistair Burleigh TNList Tsinghua University School of Computer Science & Informatics Cardiff University Cardiff School of Art & Design Cardiff Metropolitan University

We consider a face-to-face videoconferencing system that uses a Kinect camera at each end of the link for 3D modeling and an ordinary2 D display for output. The Kinect camera allows a 3D model of each participant to be transmitted;the(assumed static) background is sent ***, the Kinect tracks the receiver's head,allowing our system to render a view of the sender depending on the receiver's viewpoint. The resulting motion parallax gives the receivers a strong impression of 3D viewing as they move, yet the system only needs an ordinary 2D display. This is cheaper than a full3 D system, and avoids disadvantages such as the need to wear shutter glasses, Vr headsets, or to sit in a particular position required by an autostereo *** studies show that users experience a greater sensation of depth with our system compared to a typical 2D videoconferencing system.

关键词： naked-eye 3D motion parallax videoconferencing real-time 3D modeling

Skeleton-based canonical forms for non-rigid 3D shape retrieval

在线全文

学校读者我要写书评

暂无评论

Computational Visual Media 2016年第3期2卷 231-243页

作者： David Pickup Xianfang Sun Paul L.rosin ralph r.martin School of Computer Science and Informatics Cardiff University

The retrieval of non-rigid 3D shapes is an important task. A common technique is to simplify this problem to a rigid shape retrieval task by producing a bending-invariant canonical form for each shape in the dataset to be searched. It is common for these techniques to attempt to "unbend" a shape by applying multidimensional scaling(MDS) to the distances between points on the mesh, but this leads to unwanted local shape distortions. We instead perform the unbending on the skeleton of the mesh, and use this to drive the deformation of the mesh itself. This leads to computational speed-up, and reduced distortion of local shape detail. We compare our method against other canonical forms: our experiments show that our method achieves state-of-the-art retrieval accuracy in a recent canonical forms benchmark, and only a small drop in retrieval accuracy over the state-of-the-art in a second recent benchmark, while being significantly faster.

关键词： canonical forms shape retrieval skeletons pose invariance

Can attention enable MLPs to catch up with CNNs?

在线全文

学校读者我要写书评

暂无评论

Computational Visual Media 2021年第3期7卷 283-288页

作者： Meng-Hao Guo Zheng-Ning Liu Tai-Jiang Mu Dun Liang ralph r.martin Shi-Min Hu BNrist Department of Computer Science and TechnologyTsinghua UniversityBeijing 100084China Cardiff University Cardiff CF243AAUK.

In the first week of May 2021,researchers from four different institutions:Google,Tsinghua University,Oxford University,and Facebook shared their latest work[1–4]on ar *** at almost the same time,each proposing new learning architectures,consisting mainly of linear layers,claiming them to be comparable or superior to convolutional-based models.

关键词： enable Facebook Google

PCT:Point cloud transformer

在线全文

学校读者我要写书评

暂无评论

Computational Visual Media 2021年第2期7卷 187-199页

作者： Meng-Hao Guo Jun-Xiong Cai Zheng-Ning Liu Tai-Jiang Mu ralph r.martin Shi-Min Hu BNrist Department of Computer Science and TechnologyTsinghua UniversityBeiing 100084China Cardiff University Cardiff CF243

The irregular domain and lack of ordering make it challenging to design deep neural networks for point cloud *** paper presents a novel framework named Point Cloud Transformer(PCT)for point cloud *** is based on Transformer,which achieves huge success in natural language processing and displays great potential in image *** is inherently permutation invariant for processing a sequence of points,making it well-suited for point cloud *** better capture local context within the point cloud,we enhance input embedding with the support of farthest point sampling and nearest neighbor *** experiments demonstrate that the PCT achieves the state-of-the-art performance on shape classification,part segmentation,semantic segmentation,and normal estimation tasks.

关键词： 3D computer vision deep learning point cloud processing Transformer

Comfort-driven disparity adjustment for stereoscopic video

在线全文

学校读者我要写书评

暂无评论

Computational Visual Media 2016年第1期2卷 3-17页

作者： Miao Wang Xi-Jin Zhang Jun-Bang Liang Song-Hai Zhang ralph r.martin Department of Computer Science and Technology Tsinghua University Cardiff University

Pixel disparity—the offset of corresponding pixels between left and right views—is a crucial parameter in stereoscopic three-dimensional(S3D)video, as it determines the depth perceived by the human visual system(HVS). Unsuitable pixel disparity distribution throughout an S3 D video may lead to visual discomfort. We present a unified and extensible stereoscopic video disparity adjustment framework which improves the viewing experience for an S3 D video by keeping the perceived 3D appearance as unchanged as possible while minimizing discomfort. We first analyse disparity and motion attributes of S3 D video in general, then derive a wide-ranging visual discomfort metric from existing perceptual comfort models. An objective function based on this metric is used as the basis of a hierarchical optimisation method to find a disparity mapping function for each input video frame. Warping-based disparity manipulation is then applied to the input video to generate the output video, using the desired disparity mappings as constraints. Our comfort metric takes into account disparity range, motion, and stereoscopic window violation; the framework could easily be extended to use further visual comfort models. We demonstrate the power of our approach using both animated cartoons and real S3 D videos.

关键词： stereoscopic video editing video enhancement perceptual visual computing video manipulation