195 Hits in 7.5 sec

ME R-CNN: Multi-Expert R-CNN for Object Detection [article]

Hyungtae Lee and Sungmin Eum and Heesung Kwon
2017 arXiv   pre-print
We introduce Multi-Expert Region-based CNN (ME R-CNN) which is equipped with multiple experts and built on top of the R-CNN framework known to be one of the state-of-the-art object detection methods.  ...  On top of using selective search which provides a compact, yet effective set of region of interests (RoIs) for object detection, we augmented the set by also employing the exhaustive search for training  ...  The ME R-CNN inherits the architecture of the region-based CNN (R-CNN) [7, 13, 14, 16, 28] which uses a single stream pipeline for processing each region-of-interest (RoI).  ... 
arXiv:1704.01069v2 fatcat:uid44wfc7zfj5jvrfsq2d7bthq

Contour Extraction of Individual Cattle from an Image Using Enhanced Mask R-CNN Instance Segmentation Method

Rotimi-Williams Bello, Ahmad Sufril Azlan Mohamed, Abdullah Zawawi Talib
2021 IEEE Access  
In [37] , the region-based convolutional neural network (R-CNN) method employs selective search to produce region proposals and employs deep CNN for classifying the object proposals.  ...  In the aspect of object segmentation, the MASK R-CNN has great image object detection and segmentation tactics [18] .  ... 
doi:10.1109/access.2021.3072636 fatcat:n6nszhd6afhvzh7oxqvfclnuoa

Mask R‐CNN‐based building extraction from VHR satellite data in operational humanitarian action: An example related to Covid‐19 response in Khartoum, Sudan

Dirk Tiede, Gina Schwendemann, Ahmad Alobaidi, Lorenz Wendt, Stefan Lang
2021 Transactions on GIS  
We extracted approximately 1.2 million dwellings and buildings, using a Mask R-CNN deep learning approach from a Pléiades very high-resolution satellite image with 0.5 m pixel resolution.  ...  Within the constraints of operational work supporting humanitarian organizations in their response to the Covid-19 pandemic, we conducted building extraction for Khartoum, Sudan.  ...  Mask R-CNN is an extension of Faster R-CNN (Ren, He, Girshick, & Sun, 2017) , a class of region-based CNN that has been speed-optimized for classification as well as object detection using proposed regions  ... 
doi:10.1111/tgis.12766 pmid:34220286 pmcid:PMC8237065 fatcat:kltq3wbumzahvpz3dciooe6d5u

Making a Bird AI Expert Work for You and Me [article]

Dongliang Chang, Kaiyue Pang, Ruoyi Du, Zhanyu Ma, Yi-Zhe Song, Jun Guo
2021 arXiv   pre-print
Codes are available at:  ...  For that, we devise a multi-stage learning framework, which starts with modelling visual attention of domain experts and novices before discriminatively distilling their differences to acquire the expert  ...  Part-based r-cnns for fine-grained category detection. In ECCV, 2014. 5 10  ... 
arXiv:2112.02747v1 fatcat:dkj6gwdolzgg5hmyajwqdp3n3a

Artificial Convolutional Neural Network in Object Detection and Semantic Segmentation for Medical Imaging Analysis

Ruixin Yang, Yingyan Yu
2021 Frontiers in Oncology  
CNN and its extension algorithms play important roles on medical imaging classification, object detection, and semantic segmentation.  ...  In this review article, we introduce the progression of object detection and semantic segmentation in medical imaging study.  ...  2016YFC1303200), National Natural Science Foundation of China (82072602 and 81772505), the Cross-Institute Research Fund of Shanghai Jiao Tong University (YG2017ZD01), Shanghai Collaborative Innovation Center for  ... 
doi:10.3389/fonc.2021.638182 pmid:33768000 pmcid:PMC7986719 fatcat:2jztcaixnfaajpe3b3spwwn5f4

Various OCT Segmentation and Classification Techniques

Neenu Joy
2020 International Journal of Information Systems and Computer Sciences  
Optical coherence tomography is a non-intrusive method for the image. OCT is a well-known modality of detecting and inventing ocular disease on time.  ...  This paper describes different methods for the analysis of OCT images and their comparison. In this paper various models of image segmentation and classification are discussed.  ...  detection algorithm known as Faster R-CNN is suggested in 5.A deep FCN called RPN and a Fast R-CNN detector are its two modules.RPN proposes regions and the proposed regions are utilized by Fast R-CNN.The  ... 
doi:10.30534/ijiscs/2020/05932020 fatcat:2ryhljqlbraztospd3amkt6l4q

Computer Vision: A Review of Detecting Objects in Videos – Challenges and Techniques

Mohammad Ali A. Hammoudeh, Mohammad Alsaykhan, Ryan Alsalameh, Nahs Althwaibi
2022 International Journal of Online and Biomedical Engineering (iJOE)  
Object detection is part of a computer's vision where objects that can be observed externally and are found in videos can be identified and tracked by computers.  ...  Therefore, object tracking is an important part of video analysis. There are many proposed methods such as Tracking, Learning, Detection, Mean shift and MIL.  ...  Faster R-CNN: This architecture is the modified version of Fast R-CNN. Faster RCNN uses "Region Proposal Network" (RPN), while Fast RCNN uses the elective search for producing (ROI).  ... 
doi:10.3991/ijoe.v18i01.27577 fatcat:unp4mywqkza2rh725wkwpvmo3a

A Survey of Deep Learning-based Object Detection

Licheng Jiao, Fan Zhang, Fang Liu, Shuyuan Yang, Lingling Li, Zhixi Feng, Rong Qu
2019 IEEE Access  
With the rapid development of deep learning networks for detection tasks, the performance of object detectors has been greatly improved.  ...  Some representative branches of object detection are analyzed as well.  ...  R-CNN [8] further improves the region-based CNN baseline.  ... 
doi:10.1109/access.2019.2939201 fatcat:jesz2av2tjbkxfpaqyecptgls4

ME-Net: A Deep Convolutional Neural Network for Extracting Mangrove Using Sentinel-2A Data

Mingqiang Guo, Zhongyang Yu, Yongyang Xu, Ying Huang, Chunfeng Li
2021 Remote Sensing  
Then, the dataset was used to train deep convolutional neural network (CNN) for extracting the mangrove.  ...  However, popular mangrove extraction methods, such as the object-oriented method, still have some defects for remote sensing imagery, such as being low-intelligence, time-consuming, and laborious.  ...  Acknowledgments: The authors thank Dezhi Wang for helping guiding the research. Conflicts of Interest: We declare that we have no conflict of interest. Remote Sens. 2021, 13, 1292  ... 
doi:10.3390/rs13071292 fatcat:nnmjjvhrcvdw7hce2qoprz5jai

A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasets [article]

Muhammed Muzammul, Xi Li
2021 arXiv   pre-print
Furthermore, we explained results with the help of some object detection algorithms, i.e., R-CNN, Fast R-CNN, Faster R-CNN, YOLO, and SSD, which are generally considered the base bone of CV, CNN, and OD  ...  In part 2) we mainly focused on tiny object detection techniques (multi-scale feature learning, Data augmentation, Training strategy (TS), Context-based detection, GAN-based detection).  ...  Fast R-CNN Fast R-CNN [146] Object detection by process of multi-region & semantic segmentation-aware CNN model MRCNN [147] Faster R-CNN: for real-time object detection with region proposal networks and  ... 
arXiv:2107.07927v1 fatcat:pgwxu5tnvzhj7ln3ccndmpilsi

A Collaborative Region Detection and Grading Framework for Forest Fire Smoke Using Weakly Supervised Fine Segmentation and Lightweight Faster-RCNN

Jin Pan, Xiaoming Ou, Liang Xu
2021 Forests  
This paper presents a novel collaborative region detection and grading framework for fire smoke using a weakly supervised fine segmentation and a lightweight Faster R-CNN.  ...  Currently, convolutional neural networks (CNN) have yielded excellent performance in image recognition. Previous studies mostly paid attention to CNN-based image classification for fire detection.  ...  Acknowledgments: We thank MDPI for its linguistic assistance during the preparation of this manuscript. Conflicts of Interest: The authors declare no conflict of interest. Forests 2021, 12, 768  ... 
doi:10.3390/f12060768 fatcat:or2n5uy2dngj7pqjpoc7kep2h4

Deep Learning in Diabetic Foot Ulcers Detection: A Comprehensive Evaluation [article]

Moi Hoon Yap and Ryo Hachiuma and Azadeh Alavi and Raphael Brungel and Bill Cassidy and Manu Goyal and Hongtao Zhu and Johannes Ruckert and Moshe Olshansky and Xiao Huang and Hideo Saito and Saeed Hassanpour and Christoph M. Friedrich and David Ascher and Anping Song and Hiroki Kajita and David Gillespie and Neil D. Reeves and Joseph Pappachan and Claire O'Shea and Eibe Frank
2021 arXiv   pre-print
This paper summarises the results of DFUC2020 by comparing the deep learning-based algorithms proposed by the winning teams: Faster R-CNN, three variants of Faster R-CNN and an ensemble method; YOLOv3;  ...  of state-of-the-art deep learning object detection frameworks applied to this problem.  ...  Acknowledgments We gratefully acknowledge the support of NVIDIA Corporation for the use of GPUs for this challenge and sponsoring our event.  ... 
arXiv:2010.03341v3 fatcat:5glrdmtztjhf7dz5v6exdm4epu

A Comprehensive Review on 3D Object Detection and 6D Pose Estimation with Deep Learning

Sabera Hoque, MD. Yasir Arafat, Shuxiang Xu, Ananda Maiti, Yuchen Wei
2021 IEEE Access  
First, in R-CNN, the image is divided into about 2000 regions, and then CNN (Convent) is applied to each region gradually.  ...  So the difference between the Fast R-CNN and R-CNN is that the former does not divide into official region recom-560 mendations but first applies CNN and then allocates it to region recommendations.  ... 
doi:10.1109/access.2021.3114399 fatcat:kvdwsslqxff3lkh27tsdsciqma

The Role and Impact of Deep Learning Methods in Computer-Aided Diagnosis Using Gastrointestinal Endoscopy

Xuejiao Pang, Zijian Zhao, Ying Weng
2021 Diagnostics  
Thus, they are promising for the classification and detection of lesions through gastrointestinal endoscopy using a computer-aided diagnosis (CAD) system based on deep learning.  ...  This study aimed to address the research development of a CAD system based on deep learning in order to assist doctors in classifying and detecting lesions in the stomach, intestines, and esophagus.  ...  Acknowledgments: The authors would like to thank Yanbing Wu for his technical support. Conflicts of Interest: The authors declare no conflict of interest. Diagnostics 2021, 11, 694  ... 
doi:10.3390/diagnostics11040694 pmid:33919669 fatcat:zr36gjuhnzfbbkt3oytjakfnya

Machine learning in orthodontics: Challenges and perspectives

Jialing Liu, Ye Chen, Shihao Li, Zhihe Zhao, Zhihong Wu
2021 Advances in Clinical and Experimental Medicine  
Meanwhile, compared to human experts, ML algorithms allow for high agreement and stability in orthodontic decision-making procedures and treatment effect evaluation.  ...  It is hopeful that AI, especially machine learning (ML), due to its powerful capacity for image processing and decision support systems, will find extensive application in orthodontics in the future.  ...  are similar tasks in AI, but segmentation mainly aims to define the contours of an object, whereas detection aims to define the position of objects. 25 Region-based CNN (R-CNN) is commonly utilized  ... 
doi:10.17219/acem/138702 pmid:34610222 fatcat:re6hs745sjdfhjapvmwzioms44
« Previous Showing results 1 — 15 out of 195 results