Filters








936 Hits in 8.6 sec

AIRBORNE LIDAR POINT CLOUD CLASSIFICATION BASED ON MULTILEVEL POINT CLUSTER FEATURES

Y. Gao, M. C. Li
2020 The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences  
The method uses the tag information of the training data and the tag source of each dictionary item to construct a significant dictionary learning model in sparse coding to expresses the feature of the  ...  The classification and identification of point cloud is the basis of its application, and it is also a hot and difficult problem in the field of geographic information science.The difficulty of LiDAR point  ...  mutual occlusion, and like cars, pedestrians, etc. are in motion during scanning.  ... 
doi:10.5194/isprs-archives-xlii-3-w10-1231-2020 fatcat:lolre7ycabfdleexjm45oaosmy

Multiple object tracking with context awareness [article]

Laura Leal-Taixé
2016 arXiv   pre-print
., locating the pedestrians in the image, and data association, i.e., linking detections across frames to form complete trajectories.  ...  In crowded environments occlusions and false detections are common, and although there have been substantial advances in recent years, tracking is still a challenging task.  ...  Trajectory 1 in Figure A.4.3 Features used for classification An analysis of the features used for classification is presented in this section.  ... 
arXiv:1411.7935v2 fatcat:hv4ge7lgubhnvcbuwibg3kmhia

2019 6th International Conference on Systems and Informatics

2019 2019 6th International Conference on Systems and Informatics (ICSAI)  
Great efforts have been made to improve the state of the art in the technologies for computer-based applications.  ...  ICSAI 2019 aims to advance these technologies to a new level and to make development of computer-based application more reliable and efficient.  ...  Design and Operation of Low Speed and Direct Drive of Single-Phase Generator Fault Analysis of Wind Turbine Gearbox Based on Vague Set and Fault Tree Low-Frequency Oscillation Mode Identification with  ... 
doi:10.1109/icsai48974.2019.9010230 fatcat:eovojg6yirhfhnmxzugrvzzc5a

Natural Graph Wavelet Packet Dictionaries

Alexander Cloninger, Haotian Li, Naoki Saito
2021 Journal of Fourier Analysis and Applications  
, and demonstrate the strengths of these basis dictionaries for graph signals measured on sunflower graphs and street networks.  ...  These basis dictionaries can be seen as generalizations of the classical Shannon wavelet packet dictionary to arbitrary graphs, and do not rely on the frequency interpretation of Laplacian eigenvalues.  ...  We also thank the three anonymous reviewers for their insightful comments and suggestions, which helped us to improve the presentation and quality of this article.  ... 
doi:10.1007/s00041-021-09832-3 fatcat:flcmdwvbjng2hb35s3s7yvy2ty

Natural Graph Wavelet Packet Dictionaries [article]

Alexander Cloninger, Haotian Li, Naoki Saito
2021 arXiv   pre-print
, and demonstrate the strengths of these basis dictionaries for graph signals measured on sunflower graphs and street networks.  ...  These basis dictionaries can be seen as generalizations of the classical Shannon wavelet packet dictionary to arbitrary graphs, and do not rely on the frequency interpretation of Laplacian eigenvalues.  ...  We also thank the three anonymous reviewers for their insightful comments and suggestions, which helped us to improve the presentation and quality of this article.  ... 
arXiv:2009.09020v4 fatcat:ssy4p2xuujh2za7tviuvwi5wxu

Person reidentification by semisupervised dictionary rectification learning with retraining module

Hongyuan Wang, Zongyuan Ding, Ji Zhang, Suolan Liu, Tongguang Ni, Fuhua Chen
2018 Journal of Electronic Imaging (JEI)  
It thus integrates the advantages of the two methods through combining dictionary learning and metric learning.  ...  To address these issues, we make use of a small amount of labeled samples to add discriminant information in the basic dictionary learning.  ...  PRID 31 is different from other existing datasets in that the gallery and probe sets have different numbers of people. In our experiments, we use the single-shot version of the dataset.  ... 
doi:10.1117/1.jei.27.4.043043 fatcat:ofhwna464zfp7kd474si5moczi

Global optimization for coupled detection and data association in multiple object tracking

Zheng Wu, Margrit Betke
2016 Computer Vision and Image Understanding  
The framework follows the Lagrange dual decomposition strategy, taking advantage of the often complementary nature of the two subproblems.  ...  We present a novel framework for tracking multiple objects imaged from one or more static cameras, where the problems of object detection and data association are expressed by a single objective function  ...  The Simultaneous Detection-tracklet Classification and Clustering (CL 2 ) method [31] associates objects in the joint space of tracklets and motion trajectories.  ... 
doi:10.1016/j.cviu.2015.10.006 fatcat:fpdu5ano4nbjpflbp56tgo6jty

Receptive Multi-granularity Representation for Person Re-Identification [article]

Guanshuo Wang, Yufeng Yuan, Jiwei Li, Shiming Ge, Xi Zhou
2020 arXiv   pre-print
In this way, our model can provide a more comprehensive and efficient feature representation without larger model storage costs.  ...  Extensive experiments on intra-dataset and cross-dataset evaluations demonstrate the effectiveness of the proposed approach.  ...  Fig. 8 . 8 Relationship between Rank-1 accuracy/mAP and partition numbers, evaluated on Market-1501, DukeMTMC-reID, CUHK03, and MSMT17 datasets, evaluated by single-branch dual-path networks with RP and  ... 
arXiv:2008.13450v1 fatcat:bi7lgqfp4vfnrn5aiz4kgmiumi

Pedestrian Detection with Spatially Pooled Features and Structured Ensemble Learning [article]

Sakrapee Paisitkriangkrai, Chunhua Shen, Anton van den Hengel
2015 arXiv   pre-print
Experimental results on both synthetic and real-world data sets demonstrate the effectiveness of our approach, and we show that it is possible to train state-of-the-art pedestrian detectors using the proposed  ...  In this situation the performance of a detector should be assessed on the basis of the area under the ROC curve over that range, rather than over the full curve, as the performance outside the range is  ...  ACKNOWLEDGEMENTS This work was in part supported by the Data to Decisions Cooperative Research Centre. C.  ... 
arXiv:1409.5209v3 fatcat:n6f3s3x4gbf65fotwbx6rnnfoa

Dual-path CNN with Max Gated block for Text-Based Person Re-identification [article]

Tinghuai Ma, Mingming Yang, Huan Rong, Yurong Qian, Yurong Qian, Yuan Tian, NajlaAl-Nabhan
2020 arXiv   pre-print
With that in mind, a novel Dual-path CNN with Max Gated block (DCMG) is proposed to extract discriminative word embeddings and make visual-textual association concern more on remarkable features of both  ...  Finally, extensive experiments are conducted on the benchmark dataset, CUHK-PEDES, in which our approach achieves the rank-1 score of 55.81% and outperforms the state-of-the-art method by 1.3%.  ...  Note that we remove the words, which have not appeared in the training set as well as dictionary. For CUHK-PEDES, the dictionary size is 7012.  ... 
arXiv:2009.09343v1 fatcat:bbh7dk6slncmhf5eoydek2tatq

A shadow elimination approach in video-surveillance context

Alessandro Leone, Cosimo Distante, Francesco Buccolieri
2006 Pattern Recognition Letters  
errors in localization, segmentation, measurements, tracking and classification of moving objects.  ...  Particularly, MP selects the best little set of atoms of 2D Gabor dictionary for features selection representative of properties of the texture in the image.  ...  Acknowledgement This work is supported in part by FIRB-MIUR: ''Microtechnologies for virtual immersive telepresence''.  ... 
doi:10.1016/j.patrec.2005.08.020 fatcat:kro4syzpdbe7bnz6w4nruh5nbu

Adaptive Sparse Representations for Video Anomaly Detection

Xuan Mo, Vishal Monga, Raja Bala, Zhigang Fan
2014 IEEE transactions on circuits and systems for video technology (Print)  
As the volume of video data increases, most video analysis requires significant human supervision.  ...  Second, we introduce non-linearity into the linear sparsity model and dictionary design and optimization technique to enable superior class separability and dictionary compactness.  ...  Since manual analysis of such large volumes of data is prohibitively costly, there is a desire to develop effective algorithms that can aid in the automatic or semi-automatic interpretation and analysis  ... 
doi:10.1109/tcsvt.2013.2280061 fatcat:njjuwnbe7fa7toikvl7lsdguhi

Fully Unsupervised Person Re-identification viaSelective Contrastive Learning [article]

Bo Pang, Deming Zhai, Junjun Jiang, Xianming Liu
2021 arXiv   pre-print
Experimental results demonstrate the superiority of our method in unsupervised person ReID compared with the state-of-the-arts.  ...  Moreover, we propose to jointly leverage global and local features to construct three dynamic dictionaries, among which the global and local memory banks are used for pairwise similarity computation and  ...  The similarity between x i and another image x j are calculated by measuring Euclidean distance of feature vectors and keys of dual dictionary M g and M l .  ... 
arXiv:2010.07608v2 fatcat:c4zqhhd2wvex7ijmmvqh667a4m

2021 Index IEEE Transactions on Multimedia Vol. 23

2021 IEEE transactions on multimedia  
-that appeared in this periodical during 2021, and items from previous years that were commented upon or corrected in 2021.  ...  The primary entry includes the coauthors' names, the title of the paper or other item, and its location, specified by the publication abbreviation, year, month, and inclusive pagination.  ...  ., +, TMM 2021 4297-4310 Dictionaries Blind Quality Assessment of Screen Content Images Via Macro-Micro Mod-eling of Tensor Domain Dictionary.  ... 
doi:10.1109/tmm.2022.3141947 fatcat:lil2nf3vd5ehbfgtslulu7y3lq

2021 Index IEEE Transactions on Image Processing Vol. 30

2021 IEEE Transactions on Image Processing  
-that appeared in this periodical during 2021, and items from previous years that were commented upon or corrected in 2021.  ...  The primary entry includes the coauthors' names, the title of the paper or other item, and its location, specified by the publication abbreviation, year, month, and inclusive pagination.  ...  Li, Y., +, TIP 2021 4540-4554 Hypergraph Spectral Analysis and Processing in 3D Point Cloud.  ... 
doi:10.1109/tip.2022.3142569 fatcat:z26yhwuecbgrnb2czhwjlf73qu
« Previous Showing results 1 — 15 out of 936 results