Filters








18 Hits in 6.2 sec

Feature Selection and Pedestrian Detection Based on Sparse Representation

Shihong Yao, Tao Wang, Weiming Shen, Shaoming Pan, Yanwen Chong, Fei Ding, Hans A Kestler
2015 PLoS ONE  
and the sparse feature subsets of the combination of HOG-LSS show better distinguishing ability and parsimony.  ...  Based on the theoretical analysis of six frequently-used features, SIFT, SURF, Haar, HOG, LBP and LSS, and their comparison with experimental results, this paper screens out the sparse feature subsets  ...  [13] combined HOG, edgelet and covariance feature to make a new feature.  ... 
doi:10.1371/journal.pone.0134242 pmid:26295480 pmcid:PMC4546602 fatcat:syqwxg2bcva4pajwfh3nb5na6m

A Review on Pedestrian Detection in the Vehicle Dashpot and Surveillance Camera Video Footage

B. Thiyaneswaran, K. Anguraj, P. Keerthana, D. B.
2018 International Journal of Computer Applications  
A pedestrian detection is required for advance d driver assistance system and security surveillance system.  ...  The various techniques used in the pedestrian detection such as histogram oriented gradient method, SURF, SIFT, LDA are gathered using the review.  ...  The author confirms that the HOG-LSS provides the better result in pedestrian detection.  ... 
doi:10.5120/ijca2018916890 fatcat:uxs6lcu2izdrfabyjooowbvn3a

Traffic Sign Detection and Recognition using Features Combination and Random Forests

Ayoub ELLAHYANI, Mohamed EL, Ilyas EL, Said CHARFI
2016 International Journal of Advanced Computer Science and Applications  
In this paper, we present a computer vision based system for fast robust Traffic Sign Detection and Recognition (TSDR), consisting of three steps.  ...  The best results are given by the combination HOG with LSS together with the Random Forest classifier.  ...  For the feature extraction, inspired by the existing ones, we try to introduce new ones using different combinations. HOG, Gabor filters, LBP, and LSS are used in this work.  ... 
doi:10.14569/ijacsa.2016.070193 fatcat:3dnh6vn4uvb2vj47w4kvxlkxdi

Bio-inspired heterogeneous architecture for real-time pedestrian detection applications

Luca Maggiani, Cédric Bourrasset, Jean-Charles Quinton, François Berry, Jocelyn Sérot
2016 Journal of Real-Time Image Processing  
In this paper we propose a novel heterogeneous architecture for reliable pedestrian detection applications.  ...  A prototype implementation is described and the results obtained are discussed with respect to other state of the art solutions.  ...  employment 2007-2013 (ERDF Auvergne region), and by the Auvergne region.  ... 
doi:10.1007/s11554-016-0581-3 fatcat:7gmamchchres3m6qzdehreloqm

Indian Classical Dance Mudra Classification Using HOG Features and SVM Classifier

K.V.V. Kumar, P.V.V. Kishore
2017 International Journal of Electrical and Computer Engineering (IJECE)  
This work helps new learners and dance enthusiastic people to learn and understand dance forms and related information on their mobile devices.  ...  Popular feature vectors such as SIFT, SURF, LBP and HAAR are tested against HOG for precision and swiftness.  ...  A formal comparison of these methods indicate that each one has got their pros and cons. Table 1 characterizes these features based on the parameters required for good feature descriptor.  ... 
doi:10.11591/ijece.v7i5.pp2537-2546 fatcat:qghp7s3qbjgvfhxo367d7dpcoq

Gabor-enhanced histogram of oriented gradients for human presence detection applied in aerial monitoring

Anton Louise Pernez De Ocampo, Argel Bandala, Elmer Dadios
2020 IJAIN (International Journal of Advances in Intelligent Informatics)  
In UAV-based human detection, the extraction and selection of the feature vector are one of the critical tasks to ensure the optimal performance of the detection system.  ...  The bins of conventional HOG are enhanced based on the dominant orientation index and the accumulated local energy in Gabor images.  ...  ALPDO performed data acquisition, feature engineering, and analysis. AAB and EPD provided consultations in the conduct of experimentation.  ... 
doi:10.26555/ijain.v6i3.514 fatcat:yapayjp56ngbli2llv7y475tii

Machine Vision based Traffic Sign Detection Methods: Review, Analyses and Perspectives

Chunsheng Liu, Shuang Li, Faliang Chang, Yinhai Wang
2019 IEEE Access  
We divide the reviewed detection methods into five main categories: color-based methods, shape-based methods, color-and shape-based methods, machine-learning-based methods, and LIDAR-based methods.  ...  In recent years, there have been a large number of TSD algorithms based on machine vision and pattern recognition. In this paper, a comprehensive review of the literature on TSD is presented.  ...  In [63] , the HOG features were extended to the HIS color space and then combined with the local self-similarity (LSS) features to get the descriptor for TSD.  ... 
doi:10.1109/access.2019.2924947 fatcat:urejf36h4rauvgur6qvj63yzxe

A Systematic Literature Review about the impact of Artificial Intelligence on Autonomous Vehicle Safety [article]

A. M. Nascimento, L. F. Vismari, C. B. S. T. Molina, P.S. Cugnasca, J.B. Camargo Jr., J.R. de Almeida Jr., R. Inam, E. Fersman, M. V. Marquezini, A. Y. Hata
2019 arXiv   pre-print
However, while some researchers in this field believe AI is the core element to enhance safety, others believe AI imposes new challenges to assure the safety of these new AI-based systems and applications  ...  As a main result, we have reinforced our preliminary observation about the necessity of considering a serious safety agenda for the future studies on AI-based AV systems.  ...  [20] Road Detection Road area detection method using a support vector machine (SVM) and histogram of oriented gradient (HOG) features and 3D lidar Support Vector Machine (SVM) combined to other techniques  ... 
arXiv:1904.02697v1 fatcat:jsruqsy3kvcyvdyfhzo4ojfaqi

HOMPC: A Local Feature Descriptor Based on the Combination of Magnitude and Phase Congruency Information for Multi-Sensor Remote Sensing Images

Zhitao Fu, Qianqing Qin, Bin Luo, Hong Sun, Chun Wu
2018 Remote Sensing  
This paper presents a novel descriptor based on the combination of the magnitude and phase congruency information of local regions to capture the common features of images with non-linear radiation changes  ...  The two feature vectors are then quickly constructed based on the convolved PCMs and MBMs.  ...  method used in the HOG method and the methods of Ye et al.  ... 
doi:10.3390/rs10081234 fatcat:qyjmxyw6yjaupoyltly7jnzdny

Mutual Foreground Segmentation with Multispectral Stereo Pairs

Robert Bergevin, Pierre-Luc St-Charles, Guillaume-Alexandre Bilodeau
2017 2017 IEEE International Conference on Computer Vision Workshops (ICCVW)  
In this work, we study how the combination of sensors operating in the long-wavelength infrared (LWIR) and visible spectra can improve the performance of foregroundbackground segmentation methods.  ...  We show that by alternately minimizing a stereo disparity energy and a binary segmentation energy with dynamic priors, we can drastically improve the results of a traditional video segmentation approach  ...  We also gratefully acknowledge the support of NVIDIA Corporation with the donation of a Titan X GPU used for this research.  ... 
doi:10.1109/iccvw.2017.55 dblp:conf/iccvw/BergevinSB17 fatcat:bky5ptqjunevjfgw6pokf4t2ma

Structural health monitoring of the Tamar suspension bridge

K. Y. Koo, J. M. W. Brownjohn, D. I. List, R. Cole
2012 Structural Control and Health Monitoring: The Bulletin of ACS  
This paper presents experiences and lessons from the structural health monitoring practice on the Tamar Bridge in Plymouth, UK, a 335m span suspension bridge opened in 1961.  ...  Structural temperature leading to thermal expansion of the deck, main cables and additional stays is a major factor on global deformation, while vehicle loading and wind are apparently secondary factors  ...  Finally we are grateful to Prof Fritz Bruner of TU Graz for his advice on the deformation monitoring instrumentation.  ... 
doi:10.1002/stc.1481 fatcat:wvxdsl7exra5heskt2azy6kr6m

Learning Mid-Level Representations for Visual Recognition

Angela Eigenstetter
2015
In particular, this work is focusing on category level recognition which is still a very challenging and mainly unsolved task.  ...  Due to their number, we cannot directly train a powerful classifier to combine all parts.  ...  [151] who proposed a descriptor based on local self-similarity (LSS).  ... 
doi:10.11588/heidok.00018988 fatcat:mams2pp67nd5jplkh2imi6pvy4

CRIAÇÃO DE UM AMBIENTE DE SIMULAÇÃO DE CONTROLE AVANÇADO DE PROCESSOS EM UMA USINA SUCROENERGÉTICA [chapter]

Edilberto Pereira Teixeira, Luciano Rangel Pinheiro Neto
2020 A Produção do Conhecimento na Engenharia Elétrica 2  
., and Chong, Y. (2015). A new pedestrian detection method based on combined hog and lss features. Neurocomputing, 151, 1006 -1014. doi:https:// doi.org/10.1016/j.neucom.2014.08. 080.  ...  ., and Melho, W. (2017) . Automatic consumption reading on electromechanical meters using hog and svm.  ... 
doi:10.22533/at.ed.65220230312 fatcat:wtkpqgtb3vegfh2igt3c73yvfu

Survey and Systematization of 3D Object Detection Models and Methods [article]

Moritz Drobnitzky, Jonas Friederich, Bernhard Egger, Patrick Zschech
2022
on the methods level.  ...  This paper offers a comprehensive survey of recent developments in 3D object detection covering the full pipeline from input data, over data representation and feature extraction to the actual detection  ...  Based on the input data that is passed into the detection model, they divide the approaches into (i) monocular image-based methods, (ii) point cloud methods and (iii) fusion-based methods.  ... 
doi:10.48550/arxiv.2201.09354 fatcat:56srlqdgbff5vl63hecer5g2hq

Object detection with MicrosoftHoloLens 2. A comparison between image and point cloud based algorithms

Sophie Herrmann, Ioannis Giannopoulos, Markus Kattenbeck
2021
Accuracy increased and inference time decreased significantly and it came to a boom of 2D image-based object detection networks.  ...  The comparison is based on one representative object detection algorithm per domain, YOLOv3 is selected as 2D algorithm, VoteNet as 3D algorithm.  ...  View-based methods achieveq uite poor results on 3D object detection KITTI test set.  ... 
doi:10.34726/hss.2021.90361 fatcat:c3komdeidrbubckifkynp2dpg4
« Previous Showing results 1 — 15 out of 18 results