Filters








197 Hits in 11.1 sec

The Discriminative Generalized Hough Transform as a Proposal Generator for a Deep Network in Automatic Pedestrian Localization

Eric Gabriel, Hauke Schramm, Carsten Meyer
2018 Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications  
We propose an efficient pedestrian detection framework consisting of a proposal generation step based on the Discriminative Generalized Hough Transform and a rejection step based on a deep convolutional  ...  The image scaling approach requires a separate feature extraction for each scale as applied in (Gabriel et al., 2017) .  ...  Discriminative Generalized Hough Transform The Generalized Hough Transform (GHT) (Ballard, 1981) is well-known as a general model-based approach for object localization.  ... 
doi:10.5220/0006542401690176 dblp:conf/visapp/GabrielSM18 fatcat:4pnyyonppzghflvof64z36pidq

Invariant Hough Random Ferns for Object Detection and Tracking

Yimin Lin, Naiguang Lu, Xiaoping Lou, Fang Zou, Yanbin Yao, Zhaocai Du
2014 Mathematical Problems in Engineering  
This paper introduces an invariant Hough random ferns (IHRF) incorporating rotation and scale invariance into the local feature description, random ferns classifier training, and Hough voting stages.  ...  The efficacy of this approach is validated through experiments on a large set of challenging benchmark datasets, and the results demonstrate that the proposed method outperforms state-of-the-art conventional  ...  One specific subtype of this part-based detecting model is the implicit shape model (ISM) [28] , which is a well-known approach based on the generalized Hough transform technique.  ... 
doi:10.1155/2014/513283 fatcat:6d2ajxv5krhabf5lvoepazbkbi

Stratified Decision Forests for Accurate Anatomical Landmark Localization in Cardiac Images

Ozan Oktay, Wenjia Bai, Ricardo Guerrero, Martin Rajchl, Antonio de Marvao, Declan P. O'Regan, Stuart A. Cook, Mattias P. Heinrich, Ben Glocker, Daniel Rueckert
2017 IEEE Transactions on Medical Imaging  
To learn more data-adaptive and patient specific models, we propose a novel stratification based training model, and demonstrate its use in a decision forest.  ...  However, trained models may not generalize well in heterogeneous datasets when the images contain large differences due to size, pose and shape variations of organs.  ...  The research was also co-funded by the National Institute for Health Research (NIHR) Biomedical Research Centre based at Imperial College Healthcare NHS Trust, and by the Engineering and Physical Sciences  ... 
doi:10.1109/tmi.2016.2597270 pmid:28055830 fatcat:rklchx32nrbwjglvkca6oaxaxe

Fast PRISM: Branch and Bound Hough Transform for Object Class Detection

Alain Lehmann, Bastian Leibe, Luc Van Gool
2010 International Journal of Computer Vision  
It thereby gives a sound justification to the voting procedure and imposes minimal constraints.  ...  The PRincipled Implicit Shape Model (PRISM) overcomes these problems by interpreting Hough voting as a dual implementation of linear slidingwindow detection.  ...  Acknowledgements The authors wish to thank the Swiss National Fund (SNF) for support through the CASTOR project .  ... 
doi:10.1007/s11263-010-0342-x fatcat:fenhe3yqyzb3hn2ncblydaxacy

Visual Object Recognition

Kristen Grauman, Bastian Leibe
2011 Synthesis Lectures on Artificial Intelligence and Machine Learning  
via sliding windows; Hough voting; Generalized distance transform; the Implicit Shape Model; the Deformable Part-based Model vii Contents  ...  ; visual vocabularies and bags-of-words; methods to verify geometric consistency according to parameterized geometric transformations; dealing with outliers in correspondences, RANSAC and the Generalized  ...  Acknowledgments This project began after we gave a tutorial on the subject at AAAI 2008; we thank the conference organizers for hosting that event and the attendees for their questions and feedback.  ... 
doi:10.2200/s00332ed1v01y201103aim011 fatcat:fhz7aokkfjav7fuauuorfstq4y

Advances in Vision-Based Lane Detection: Algorithms, Integration, Assessment, and Perspectives on ACP-Based Parallel Vision

Yang Xing, Chen Lv, Long Chen, Huaji Wang, Hong Wang, Dongpu Cao, Efstathios Velenis, Fei-Yue Wang
2018 IEEE/CAA Journal of Automatica Sinica  
A large number of existing results focus on the study of vision-based lane detection methods due to the extensive knowledge background and the low-cost of camera devices.  ...  Finally, a discussion on the limitations of current lane detection systems and the future developing trends toward an Artificial Society, Computational experiment-based parallel lane detection framework  ...  In [18] , a real-time lane detection system based on FPGA and DSP was designed based on lane gradient amplitude features and an improved Hough Transform.  ... 
doi:10.1109/jas.2018.7511063 fatcat:tjewl25slfb2ngxlrlalktksvy

Viewpoint-aware object detection and continuous pose estimation

Daniel Glasner, Meirav Galun, Sharon Alpert, Ronen Basri, Gregory Shakhnarovich
2012 Image and Vision Computing  
Our method relies on a nonparametric representation of a joint distribution of shape and appearance of the object class.  ...  We evaluate the performance of our approach in detection and pose estimation of cars on a number of benchmark datasets.  ...  Each match generates a vote, in the spirit of [4] and other methods inspired by Hough transform.  ... 
doi:10.1016/j.imavis.2012.09.006 fatcat:pdh5j6uhybdixiq4kzxk5xksfa

Object Detection in Real Images [article]

Dilip K. Prasad
2013 arXiv   pre-print
We also propose a new hierarchical codebook, which provides good generalization and discriminative properties.  ...  The codebook enables fast multi-path inference mechanisms based on propagation of conditional likelihoods, that make it robust to occlusion and noise. It has the capability of dynamic learning.  ...  Leung for providing me with the opportunity to work on this project. I am also sincerely thankful for his patience and enthusiastic guidance.  ... 
arXiv:1302.5189v1 fatcat:qdjqvh44qra6lemyu7nzpsldfa

Geometric Hypergraph Learning for Visual Tracking [article]

Dawei Du and Honggang Qi and Longyin Wen and Qi Tian and Qingming Huang and Siwei Lyu
2016 arXiv   pre-print
Besides, a confidence-aware sampling method is developed to select representative vertices and hyperedges to construct the geometric hypergraph for more robustness and scalability.  ...  The experiments are carried out on two challenging datasets (VOT2014 and Deform-SOT) to demonstrate that the proposed method performs favorable against other existing trackers.  ...  [13] develop an improved online Hough Forests and couple the voting based detection and back-projection with a rough segmentation based on GrabCut.  ... 
arXiv:1603.05930v1 fatcat:7p7styik6redzaalvpay6jjaa4

Automatic extraction of retinal features from colour retinal images for glaucoma diagnosis: A review

Muhammad Salman Haleem, Liangxiu Han, Jano van Hemert, Baihua Li
2013 Computerized Medical Imaging and Graphics  
If the automatic methods are improved in terms of accuracy and generalization; they will serve as a benchmark for the clinicians to diagnose the disease based on measurements obtained by using those methods  ...  [43] extracted out vasculature structure based on tensor voting. Tensor voting is the voting process of the expected candidates based on geometrical features.  ... 
doi:10.1016/j.compmedimag.2013.09.005 pmid:24139134 fatcat:do4s63qepvbodgx4iegyw65p7e

Object Recognition, Segmentation, and Classification of Mobile Laser Scanning Point Clouds: A State of the Art Review

Erzhuo Che, Jaehoon Jung, Michael Olsen
2019 Sensors  
Mobile Laser Scanning (MLS) is a versatile remote sensing technology based on Light Detection and Ranging (lidar) technology that has been utilized for a wide range of applications.  ...  The methods for object recognition and point cloud classification are further reviewed including both the general concepts as well as technical details.  ...  The funders had no role in the design of the study; in the collection, analyses, or interpretation of data; in the writing of the manuscript, and in the decision to publish the results.  ... 
doi:10.3390/s19040810 fatcat:lvi4ty5qkvdqznwy6vx24buax4

Exploiting temporal and spatial constraints in traffic sign detection from a moving vehicle

Siniša Šegvić, Karla Brkić, Zoran Kalafatić, Axel Pinz
2011 Machine Vision and Applications  
The second stage improves the precision by filtering the detection tracks by a learned discriminative model.  ...  The two stages have been evaluated in extensive experiments performed on videos acquired from a moving vehicle.  ...  The project web site is at http://mastif.zemris.fer.hr The research has been additionally supported by the Austrian-Croatian bilateral programme funded by the Austrian Agency for International Mobility  ... 
doi:10.1007/s00138-011-0396-y fatcat:mdvnlnn6jrctpc2m2z3c56zbty

Automated Diagnosis of Otitis Media: Vocabulary and Grammar

Anupama Kuruvilla, Nader Shaikh, Alejandro Hoberman, Jelena Kovačević
2013 International Journal of Biomedical Imaging  
We also design a process to combine the vocabulary terms based on the decision process used by otoscopists; we term this theotitis media grammar.  ...  To that end, we design a feature set understood by both otoscopists and engineers based on the actual visual cues used by otoscopists; we term this theotitis media vocabulary.  ...  Jian Li for his work on features, and Miss Lakshmi Dhevi Jayagobi for implementing the random forest classifier. they follow the principles of reproducible research.  ... 
doi:10.1155/2013/327515 pmid:23997759 pmcid:PMC3749602 fatcat:s4t2aykj6nhirj5tf3k4lr55my

Counting and Classification of Malarial Parasite from Giemsa-Stained Thin Film Images

Wasu Kudisthalert, Kitsuchart Pasupa, Sissades Tongsima.
2020 IEEE Access  
The counting process is performed by computer vision techniques, namely Hough transform.  ...  The proposed framework consists of two main parts that are red blood cell counting and parasite life-cycle stage classification.  ...  Chairat Uthaipibull from the Protein-Ligand Engineering and Molecular Biology laboratory, National Center for Genetic Engineering and Biotechnology (BIOTEC), Thailand, for providing and validating Giemsa-stained  ... 
doi:10.1109/access.2020.2990497 fatcat:3bsme2rpdrapfkmbh7xemsiwy4

Representations and Techniques for 3D Object Recognition and Scene Interpretation

Derek Hoiem, Silvio Savarese
2011 Synthesis Lectures on Artificial Intelligence and Machine Learning  
This research was funded in part by NSF CAREER award IIS-0546547 and a Microsoft Research Fellowship. We also thank the reviewers for their kindly admonitions to expand derivation and discussion.  ...  example, Kevin Murphy for creating the Bayes Net Toolbox, and Antonio Torralba for making the gist code available.  ...  The ISM is in essence a probabilistic extension of the generalized Hough voting transform [6, 137] .  ... 
doi:10.2200/s00370ed1v01y201107aim015 fatcat:762pgoqa5jhwlji7w4laoiu3ym
« Previous Showing results 1 — 15 out of 197 results