SlideShare a Scribd company logo
Aerial Object Detection
HyeongJun Kwon
2019-2
Contents
2
1. EAST: An Efficient and Accurate Scene Text Detector
2. Towards Multi-class Object Detection in Unconstrained Remote Sensing
Imagery
EAST: An Efficient and Accurate Scene Text Detector
3
Network Overview Pipeline
Input
image
Multi-channel
FCN
Multi-channel
FCN
Multi-oriented
Task-wise boxes
4
EAST: An Efficient and Accurate Scene Text Detector
Main Contributions :
1. propose two stage(step) method : FCN and NMS merging stage
2. pipeline is flexible
5
EAST: An Efficient and Accurate Scene Text Detector
Relate work: PVANet
6
EAST: An Efficient and Accurate Scene Text Detector
Pipeline
input
conv2
conv3
conv1
conv3
merging1
merging2
merging3 For reduce computation cost, using
U-shape not using HyperNet in
PVANet that merge all feature maps
output
EAST: An Efficient and Accurate Scene Text Detector
7
Label Generation
EAST: An Efficient and Accurate Scene Text Detector
8
Label Generation: Score Map Generation
Score map generation eq
𝑟𝑖 = min(D 𝑝𝑖, 𝑝 𝑖 𝑚𝑜𝑑 4 +1 ,
D 𝑝𝑖, 𝑝 𝑖+2 𝑚𝑜𝑑 4 +1
we shrink it by moving its two endpoints inward along the edge
by 0.3𝑟𝑖 and 0.3𝑟 𝑖 𝑚𝑜𝑑 4 +1 espectively.
9
EAST: An Efficient and Accurate Scene Text Detector
𝐿 = 𝐿 𝑠 + 𝜆 𝑔 𝐿 𝑔
Label Generation: Loss
Where Y = 𝐹S is the prediction of the score map, and Y∗ is the
ground truth
𝐿 𝑠 : loss for score map
𝐿 𝑔 : loss for geometry
10
EAST: An Efficient and Accurate Scene Text Detector
𝐿 = 𝐿 𝑠 + 𝜆 𝑔 𝐿 𝑔
Label Generation: Loss
RBOX: 𝐿 𝑔 = 𝐿 𝐴𝐴𝐵𝐵 + 𝜆 𝜃 𝐿 𝜃
𝐿 𝑠 : loss for score map
𝐿 𝑔 : loss for geometry
𝐿 𝑔 = 𝐿QUAD Q, Q∗
= min
Q∈𝑃 𝑄∗
𝑐 𝑖∈CQ
𝑐 𝑖∈CQ
smoothed 𝐿1 𝑐𝑖 − 𝑐𝑖
8 × 𝑁 𝑄∗
QUAD:
11
EAST: An Efficient and Accurate Scene Text Detector
Locality-Aware NMS
Problem: A naïve NMS algorithm runs in 𝑂 𝑛2
where 𝑛 is the number of candidate geometries.
The geometries from nearby pixels tend to be highly correlated.
Solution: locality-aware NMS
𝑎 = WEIGHTEDMERGE 𝑔, 𝑝 , then 𝑎i = V 𝑔 𝑔𝑖 + 𝑉 𝑝 𝑝𝑖 and V 𝑎 = V 𝑔 + V(𝑝)
12
EAST: An Efficient and Accurate Scene Text Detector
Towards Multi-class Object Detection in Unconstrained Remote Sensing
Imagery
13
Network Overview
14
Towards Multi-class Object Detection in Unconstrained Remote Sensing
Imagery
Main Contributions :
1. new joint image cascade and feature pyramid network(ICN and FPN)
2. design a DIN module as a domain adaptation module
3. new loss function to shape rectangles by constraining the angles between the edges to
90 degrees
Towards Multi-class Object Detection in Unconstrained Remote Sensing
Imagery
15
ICN, FPN and Deformable Inception Subnetworks
• Appropriate weights sharing
• Resize image size by bilinear
interpolation
ICN
• The low-level semantic feature
from high resolution
• The high-level semantic feature
from low-level resolution
Towards Multi-class Object Detection in Unconstrained Remote Sensing
Imagery
16
ICN, FPN and Deformable Inception Subnetworks
Towards Multi-class Object Detection in Unconstrained Remote Sensing
Imagery
17
R-RPN
Characteristics:
1. no difference between the front and back of objects
2. initialize anchor by using dimension clustering in YOLO v2
3. use the smooth 𝑙1 loss to regress the four coordinates
Towards Multi-class Object Detection in Unconstrained Remote Sensing
Imagery
18
R-ROI
Characteristics:
1. penalize angles that are not 90 degree
2. initialize anchor by using dimension clustering in YOLO v2
3. use the smooth 𝑙1 loss to regress the four coordinates
penalize angles that are not 90 degree
Towards Multi-class Object Detection in Unconstrained Remote Sensing
Imagery
19
Objective
Towards Multi-class Object Detection in Unconstrained Remote Sensing
Imagery
20
Objective
Towards Multi-class Object Detection in Unconstrained Remote Sensing
Imagery
21
Result
Towards Multi-class Object Detection in Unconstrained Remote Sensing
Imagery
22
Result
Towards Multi-class Object Detection in Unconstrained Remote Sensing
Imagery
23
Result
Reference
24
EAST:
PVANET: Deep but lightweight neural networks for real-time object detection.
Balanced-cross entropy:
Holistically-nested edge detection
Scene text detection via holistic, multi-channel prediction.
U-shape: U-net: Convolu-tional networks for biomedical image segmentation.
Towards Multi-class Object Detection in Unconstrained Remote Sensing Imagery:
Soft-NMS: Improving object detection with one line of code.
IoU distance: Yolo9000: Better, faster, stronger.
DIN: deformable convolutional networks

More Related Content

What's hot

Objects as points (CenterNet) review [CDM]
Objects as points (CenterNet) review [CDM]Objects as points (CenterNet) review [CDM]
Objects as points (CenterNet) review [CDM]
Dongmin Choi
 
Class Weighted Convolutional Features for Image Retrieval
Class Weighted Convolutional Features for Image Retrieval Class Weighted Convolutional Features for Image Retrieval
Class Weighted Convolutional Features for Image Retrieval
Universitat Politècnica de Catalunya
 
[unofficial] Pyramid Scene Parsing Network (CVPR 2017)
[unofficial] Pyramid Scene Parsing Network (CVPR 2017)[unofficial] Pyramid Scene Parsing Network (CVPR 2017)
[unofficial] Pyramid Scene Parsing Network (CVPR 2017)
Shunta Saito
 
Building and road detection from large aerial imagery
Building and road detection from large aerial imageryBuilding and road detection from large aerial imagery
Building and road detection from large aerial imagery
Shunta Saito
 
fusion of Camera and lidar for autonomous driving II
fusion of Camera and lidar for autonomous driving IIfusion of Camera and lidar for autonomous driving II
fusion of Camera and lidar for autonomous driving II
Yu Huang
 
Camera-based road Lane detection by deep learning III
Camera-based road Lane detection by deep learning IIICamera-based road Lane detection by deep learning III
Camera-based road Lane detection by deep learning III
Yu Huang
 
VJAI Paper Reading#3-KDD2019-ClusterGCN
VJAI Paper Reading#3-KDD2019-ClusterGCNVJAI Paper Reading#3-KDD2019-ClusterGCN
VJAI Paper Reading#3-KDD2019-ClusterGCN
Dat Nguyen
 
[PaperReview] LightGCN: Simplifying and Powering Graph Convolution Network fo...
[PaperReview] LightGCN: Simplifying and Powering Graph Convolution Network fo...[PaperReview] LightGCN: Simplifying and Powering Graph Convolution Network fo...
[PaperReview] LightGCN: Simplifying and Powering Graph Convolution Network fo...
Zimin Park
 
Auro tripathy - Localizing with CNNs
Auro tripathy -  Localizing with CNNsAuro tripathy -  Localizing with CNNs
Auro tripathy - Localizing with CNNs
Auro Tripathy
 
Matteoli ieee gold_2010_clean
Matteoli ieee gold_2010_cleanMatteoli ieee gold_2010_clean
Matteoli ieee gold_2010_clean
grssieee
 
Thesis Presentation
Thesis PresentationThesis Presentation
Thesis Presentation
Reuben Feinman
 
Multi sensor calibration by deep learning
Multi sensor calibration by deep learningMulti sensor calibration by deep learning
Multi sensor calibration by deep learning
Yu Huang
 
Detection focal loss 딥러닝 논문읽기 모임 발표자료
Detection focal loss 딥러닝 논문읽기 모임 발표자료Detection focal loss 딥러닝 논문읽기 모임 발표자료
Detection focal loss 딥러닝 논문읽기 모임 발표자료
taeseon ryu
 
Urban 3D Semantic Modelling Using Stereo Vision, ICRA 2013
Urban 3D Semantic Modelling Using Stereo Vision, ICRA 2013Urban 3D Semantic Modelling Using Stereo Vision, ICRA 2013
Urban 3D Semantic Modelling Using Stereo Vision, ICRA 2013
Sunando Sengupta
 
Remote Sensing IEEE 2015 Projects
Remote Sensing IEEE 2015 ProjectsRemote Sensing IEEE 2015 Projects
Remote Sensing IEEE 2015 Projects
Vijay Karan
 
Autonomous deployment for load balancing surface coverage in sensor networks
Autonomous deployment for load balancing    surface coverage in sensor networksAutonomous deployment for load balancing    surface coverage in sensor networks
Autonomous deployment for load balancing surface coverage in sensor networks
ieeepondy
 
Gnn overview
Gnn overviewGnn overview
Gnn overview
Louis (Yufeng) Wang
 
Unsupervised/Self-supervvised visual object tracking
Unsupervised/Self-supervvised visual object trackingUnsupervised/Self-supervvised visual object tracking
Unsupervised/Self-supervvised visual object tracking
Yu Huang
 
Comparative Study of Object Detection Algorithms
Comparative Study of Object Detection AlgorithmsComparative Study of Object Detection Algorithms
Comparative Study of Object Detection Algorithms
IRJET Journal
 
Depth Fusion from RGB and Depth Sensors by Deep Learning
Depth Fusion from RGB and Depth Sensors by Deep LearningDepth Fusion from RGB and Depth Sensors by Deep Learning
Depth Fusion from RGB and Depth Sensors by Deep Learning
Yu Huang
 

What's hot (20)

Objects as points (CenterNet) review [CDM]
Objects as points (CenterNet) review [CDM]Objects as points (CenterNet) review [CDM]
Objects as points (CenterNet) review [CDM]
 
Class Weighted Convolutional Features for Image Retrieval
Class Weighted Convolutional Features for Image Retrieval Class Weighted Convolutional Features for Image Retrieval
Class Weighted Convolutional Features for Image Retrieval
 
[unofficial] Pyramid Scene Parsing Network (CVPR 2017)
[unofficial] Pyramid Scene Parsing Network (CVPR 2017)[unofficial] Pyramid Scene Parsing Network (CVPR 2017)
[unofficial] Pyramid Scene Parsing Network (CVPR 2017)
 
Building and road detection from large aerial imagery
Building and road detection from large aerial imageryBuilding and road detection from large aerial imagery
Building and road detection from large aerial imagery
 
fusion of Camera and lidar for autonomous driving II
fusion of Camera and lidar for autonomous driving IIfusion of Camera and lidar for autonomous driving II
fusion of Camera and lidar for autonomous driving II
 
Camera-based road Lane detection by deep learning III
Camera-based road Lane detection by deep learning IIICamera-based road Lane detection by deep learning III
Camera-based road Lane detection by deep learning III
 
VJAI Paper Reading#3-KDD2019-ClusterGCN
VJAI Paper Reading#3-KDD2019-ClusterGCNVJAI Paper Reading#3-KDD2019-ClusterGCN
VJAI Paper Reading#3-KDD2019-ClusterGCN
 
[PaperReview] LightGCN: Simplifying and Powering Graph Convolution Network fo...
[PaperReview] LightGCN: Simplifying and Powering Graph Convolution Network fo...[PaperReview] LightGCN: Simplifying and Powering Graph Convolution Network fo...
[PaperReview] LightGCN: Simplifying and Powering Graph Convolution Network fo...
 
Auro tripathy - Localizing with CNNs
Auro tripathy -  Localizing with CNNsAuro tripathy -  Localizing with CNNs
Auro tripathy - Localizing with CNNs
 
Matteoli ieee gold_2010_clean
Matteoli ieee gold_2010_cleanMatteoli ieee gold_2010_clean
Matteoli ieee gold_2010_clean
 
Thesis Presentation
Thesis PresentationThesis Presentation
Thesis Presentation
 
Multi sensor calibration by deep learning
Multi sensor calibration by deep learningMulti sensor calibration by deep learning
Multi sensor calibration by deep learning
 
Detection focal loss 딥러닝 논문읽기 모임 발표자료
Detection focal loss 딥러닝 논문읽기 모임 발표자료Detection focal loss 딥러닝 논문읽기 모임 발표자료
Detection focal loss 딥러닝 논문읽기 모임 발표자료
 
Urban 3D Semantic Modelling Using Stereo Vision, ICRA 2013
Urban 3D Semantic Modelling Using Stereo Vision, ICRA 2013Urban 3D Semantic Modelling Using Stereo Vision, ICRA 2013
Urban 3D Semantic Modelling Using Stereo Vision, ICRA 2013
 
Remote Sensing IEEE 2015 Projects
Remote Sensing IEEE 2015 ProjectsRemote Sensing IEEE 2015 Projects
Remote Sensing IEEE 2015 Projects
 
Autonomous deployment for load balancing surface coverage in sensor networks
Autonomous deployment for load balancing    surface coverage in sensor networksAutonomous deployment for load balancing    surface coverage in sensor networks
Autonomous deployment for load balancing surface coverage in sensor networks
 
Gnn overview
Gnn overviewGnn overview
Gnn overview
 
Unsupervised/Self-supervvised visual object tracking
Unsupervised/Self-supervvised visual object trackingUnsupervised/Self-supervvised visual object tracking
Unsupervised/Self-supervvised visual object tracking
 
Comparative Study of Object Detection Algorithms
Comparative Study of Object Detection AlgorithmsComparative Study of Object Detection Algorithms
Comparative Study of Object Detection Algorithms
 
Depth Fusion from RGB and Depth Sensors by Deep Learning
Depth Fusion from RGB and Depth Sensors by Deep LearningDepth Fusion from RGB and Depth Sensors by Deep Learning
Depth Fusion from RGB and Depth Sensors by Deep Learning
 

Similar to Aerial detection part3

R-FCN : object detection via region-based fully convolutional networks
R-FCN :  object detection via region-based fully convolutional networksR-FCN :  object detection via region-based fully convolutional networks
R-FCN : object detection via region-based fully convolutional networks
Entrepreneur / Startup
 
Content-Based Image Retrieval (D2L6 Insight@DCU Machine Learning Workshop 2017)
Content-Based Image Retrieval (D2L6 Insight@DCU Machine Learning Workshop 2017)Content-Based Image Retrieval (D2L6 Insight@DCU Machine Learning Workshop 2017)
Content-Based Image Retrieval (D2L6 Insight@DCU Machine Learning Workshop 2017)
Universitat Politècnica de Catalunya
 
Convolutional Neural Network for pixel-wise skyline detection
Convolutional Neural Network for pixel-wise skyline detectionConvolutional Neural Network for pixel-wise skyline detection
Convolutional Neural Network for pixel-wise skyline detection
Darian Frajberg
 
camera-based Lane detection by deep learning
camera-based Lane detection by deep learningcamera-based Lane detection by deep learning
camera-based Lane detection by deep learning
Yu Huang
 
object detection paper review
object detection paper reviewobject detection paper review
object detection paper review
Yoonho Na
 
Object Detection is a very powerful field.pptx
Object Detection is a very powerful field.pptxObject Detection is a very powerful field.pptx
Object Detection is a very powerful field.pptx
usmanyaseen16
 
LiDAR-based Autonomous Driving III (by Deep Learning)
LiDAR-based Autonomous Driving III (by Deep Learning)LiDAR-based Autonomous Driving III (by Deep Learning)
LiDAR-based Autonomous Driving III (by Deep Learning)
Yu Huang
 
Adaptive object detection using adjacency and zoom prediction
Adaptive object detection using adjacency and zoom predictionAdaptive object detection using adjacency and zoom prediction
Adaptive object detection using adjacency and zoom prediction
Universitat Politècnica de Catalunya
 
Lidar for Autonomous Driving II (via Deep Learning)
Lidar for Autonomous Driving II (via Deep Learning)Lidar for Autonomous Driving II (via Deep Learning)
Lidar for Autonomous Driving II (via Deep Learning)
Yu Huang
 
Neural Radiance Fields & Neural Rendering.pdf
Neural Radiance Fields & Neural Rendering.pdfNeural Radiance Fields & Neural Rendering.pdf
Neural Radiance Fields & Neural Rendering.pdf
NavneetPaul2
 
PCA-SIFT: A More Distinctive Representation for Local Image Descriptors
PCA-SIFT: A More Distinctive Representation for Local Image DescriptorsPCA-SIFT: A More Distinctive Representation for Local Image Descriptors
PCA-SIFT: A More Distinctive Representation for Local Image Descriptors
wolf
 
Conditional Image Generation with PixelCNN Decoders
Conditional Image Generation with PixelCNN DecodersConditional Image Generation with PixelCNN Decoders
Conditional Image Generation with PixelCNN Decoders
suga93
 
D3L4-objects.pdf
D3L4-objects.pdfD3L4-objects.pdf
D3L4-objects.pdf
ssusere945ae
 
IRJET- Remote Sensing Image Retrieval using Convolutional Neural Network with...
IRJET- Remote Sensing Image Retrieval using Convolutional Neural Network with...IRJET- Remote Sensing Image Retrieval using Convolutional Neural Network with...
IRJET- Remote Sensing Image Retrieval using Convolutional Neural Network with...
IRJET Journal
 
最近の研究情勢についていくために - Deep Learningを中心に -
最近の研究情勢についていくために - Deep Learningを中心に - 最近の研究情勢についていくために - Deep Learningを中心に -
最近の研究情勢についていくために - Deep Learningを中心に -
Hiroshi Fukui
 
Image Retrieval (D4L5 2017 UPC Deep Learning for Computer Vision)
Image Retrieval (D4L5 2017 UPC Deep Learning for Computer Vision)Image Retrieval (D4L5 2017 UPC Deep Learning for Computer Vision)
Image Retrieval (D4L5 2017 UPC Deep Learning for Computer Vision)
Universitat Politècnica de Catalunya
 
物件偵測與辨識技術
物件偵測與辨識技術物件偵測與辨識技術
物件偵測與辨識技術
CHENHuiMei
 
Object Pose Estimation
Object Pose EstimationObject Pose Estimation
Object Pose Estimation
Arithmer Inc.
 
Image Segmentation (D3L1 2017 UPC Deep Learning for Computer Vision)
Image Segmentation (D3L1 2017 UPC Deep Learning for Computer Vision)Image Segmentation (D3L1 2017 UPC Deep Learning for Computer Vision)
Image Segmentation (D3L1 2017 UPC Deep Learning for Computer Vision)
Universitat Politècnica de Catalunya
 
NS - CUK Seminar : V.T.Hoang, Review on "Structure-Aware Transformer for Grap...
NS - CUK Seminar : V.T.Hoang, Review on "Structure-Aware Transformer for Grap...NS - CUK Seminar : V.T.Hoang, Review on "Structure-Aware Transformer for Grap...
NS - CUK Seminar : V.T.Hoang, Review on "Structure-Aware Transformer for Grap...
ssuser4b1f48
 

Similar to Aerial detection part3 (20)

R-FCN : object detection via region-based fully convolutional networks
R-FCN :  object detection via region-based fully convolutional networksR-FCN :  object detection via region-based fully convolutional networks
R-FCN : object detection via region-based fully convolutional networks
 
Content-Based Image Retrieval (D2L6 Insight@DCU Machine Learning Workshop 2017)
Content-Based Image Retrieval (D2L6 Insight@DCU Machine Learning Workshop 2017)Content-Based Image Retrieval (D2L6 Insight@DCU Machine Learning Workshop 2017)
Content-Based Image Retrieval (D2L6 Insight@DCU Machine Learning Workshop 2017)
 
Convolutional Neural Network for pixel-wise skyline detection
Convolutional Neural Network for pixel-wise skyline detectionConvolutional Neural Network for pixel-wise skyline detection
Convolutional Neural Network for pixel-wise skyline detection
 
camera-based Lane detection by deep learning
camera-based Lane detection by deep learningcamera-based Lane detection by deep learning
camera-based Lane detection by deep learning
 
object detection paper review
object detection paper reviewobject detection paper review
object detection paper review
 
Object Detection is a very powerful field.pptx
Object Detection is a very powerful field.pptxObject Detection is a very powerful field.pptx
Object Detection is a very powerful field.pptx
 
LiDAR-based Autonomous Driving III (by Deep Learning)
LiDAR-based Autonomous Driving III (by Deep Learning)LiDAR-based Autonomous Driving III (by Deep Learning)
LiDAR-based Autonomous Driving III (by Deep Learning)
 
Adaptive object detection using adjacency and zoom prediction
Adaptive object detection using adjacency and zoom predictionAdaptive object detection using adjacency and zoom prediction
Adaptive object detection using adjacency and zoom prediction
 
Lidar for Autonomous Driving II (via Deep Learning)
Lidar for Autonomous Driving II (via Deep Learning)Lidar for Autonomous Driving II (via Deep Learning)
Lidar for Autonomous Driving II (via Deep Learning)
 
Neural Radiance Fields & Neural Rendering.pdf
Neural Radiance Fields & Neural Rendering.pdfNeural Radiance Fields & Neural Rendering.pdf
Neural Radiance Fields & Neural Rendering.pdf
 
PCA-SIFT: A More Distinctive Representation for Local Image Descriptors
PCA-SIFT: A More Distinctive Representation for Local Image DescriptorsPCA-SIFT: A More Distinctive Representation for Local Image Descriptors
PCA-SIFT: A More Distinctive Representation for Local Image Descriptors
 
Conditional Image Generation with PixelCNN Decoders
Conditional Image Generation with PixelCNN DecodersConditional Image Generation with PixelCNN Decoders
Conditional Image Generation with PixelCNN Decoders
 
D3L4-objects.pdf
D3L4-objects.pdfD3L4-objects.pdf
D3L4-objects.pdf
 
IRJET- Remote Sensing Image Retrieval using Convolutional Neural Network with...
IRJET- Remote Sensing Image Retrieval using Convolutional Neural Network with...IRJET- Remote Sensing Image Retrieval using Convolutional Neural Network with...
IRJET- Remote Sensing Image Retrieval using Convolutional Neural Network with...
 
最近の研究情勢についていくために - Deep Learningを中心に -
最近の研究情勢についていくために - Deep Learningを中心に - 最近の研究情勢についていくために - Deep Learningを中心に -
最近の研究情勢についていくために - Deep Learningを中心に -
 
Image Retrieval (D4L5 2017 UPC Deep Learning for Computer Vision)
Image Retrieval (D4L5 2017 UPC Deep Learning for Computer Vision)Image Retrieval (D4L5 2017 UPC Deep Learning for Computer Vision)
Image Retrieval (D4L5 2017 UPC Deep Learning for Computer Vision)
 
物件偵測與辨識技術
物件偵測與辨識技術物件偵測與辨識技術
物件偵測與辨識技術
 
Object Pose Estimation
Object Pose EstimationObject Pose Estimation
Object Pose Estimation
 
Image Segmentation (D3L1 2017 UPC Deep Learning for Computer Vision)
Image Segmentation (D3L1 2017 UPC Deep Learning for Computer Vision)Image Segmentation (D3L1 2017 UPC Deep Learning for Computer Vision)
Image Segmentation (D3L1 2017 UPC Deep Learning for Computer Vision)
 
NS - CUK Seminar : V.T.Hoang, Review on "Structure-Aware Transformer for Grap...
NS - CUK Seminar : V.T.Hoang, Review on "Structure-Aware Transformer for Grap...NS - CUK Seminar : V.T.Hoang, Review on "Structure-Aware Transformer for Grap...
NS - CUK Seminar : V.T.Hoang, Review on "Structure-Aware Transformer for Grap...
 

More from ssuser456ad6

Scale invariant feature transform
Scale invariant feature transformScale invariant feature transform
Scale invariant feature transform
ssuser456ad6
 
Learning joint 2 d 3d representations for depth completion
Learning joint 2 d 3d representations for depth completion Learning joint 2 d 3d representations for depth completion
Learning joint 2 d 3d representations for depth completion
ssuser456ad6
 
Guided image filter
Guided image filterGuided image filter
Guided image filter
ssuser456ad6
 
Fast cost volume filtering for visual correspondence and beyond
Fast cost volume filtering for visual correspondence and beyondFast cost volume filtering for visual correspondence and beyond
Fast cost volume filtering for visual correspondence and beyond
ssuser456ad6
 
D2 net a trainable cnn for joint description and detection of local features
D2 net a trainable cnn for joint description and detection of local features D2 net a trainable cnn for joint description and detection of local features
D2 net a trainable cnn for joint description and detection of local features
ssuser456ad6
 
Gan dissection
Gan dissectionGan dissection
Gan dissection
ssuser456ad6
 

More from ssuser456ad6 (6)

Scale invariant feature transform
Scale invariant feature transformScale invariant feature transform
Scale invariant feature transform
 
Learning joint 2 d 3d representations for depth completion
Learning joint 2 d 3d representations for depth completion Learning joint 2 d 3d representations for depth completion
Learning joint 2 d 3d representations for depth completion
 
Guided image filter
Guided image filterGuided image filter
Guided image filter
 
Fast cost volume filtering for visual correspondence and beyond
Fast cost volume filtering for visual correspondence and beyondFast cost volume filtering for visual correspondence and beyond
Fast cost volume filtering for visual correspondence and beyond
 
D2 net a trainable cnn for joint description and detection of local features
D2 net a trainable cnn for joint description and detection of local features D2 net a trainable cnn for joint description and detection of local features
D2 net a trainable cnn for joint description and detection of local features
 
Gan dissection
Gan dissectionGan dissection
Gan dissection
 

Recently uploaded

1FIDIC-CONSTRUCTION-CONTRACT-2ND-ED-2017-RED-BOOK.pdf
1FIDIC-CONSTRUCTION-CONTRACT-2ND-ED-2017-RED-BOOK.pdf1FIDIC-CONSTRUCTION-CONTRACT-2ND-ED-2017-RED-BOOK.pdf
1FIDIC-CONSTRUCTION-CONTRACT-2ND-ED-2017-RED-BOOK.pdf
MadhavJungKarki
 
Null Bangalore | Pentesters Approach to AWS IAM
Null Bangalore | Pentesters Approach to AWS IAMNull Bangalore | Pentesters Approach to AWS IAM
Null Bangalore | Pentesters Approach to AWS IAM
Divyanshu
 
LLM Fine Tuning with QLoRA Cassandra Lunch 4, presented by Anant
LLM Fine Tuning with QLoRA Cassandra Lunch 4, presented by AnantLLM Fine Tuning with QLoRA Cassandra Lunch 4, presented by Anant
LLM Fine Tuning with QLoRA Cassandra Lunch 4, presented by Anant
Anant Corporation
 
CEC 352 - SATELLITE COMMUNICATION UNIT 1
CEC 352 - SATELLITE COMMUNICATION UNIT 1CEC 352 - SATELLITE COMMUNICATION UNIT 1
CEC 352 - SATELLITE COMMUNICATION UNIT 1
PKavitha10
 
Data Driven Maintenance | UReason Webinar
Data Driven Maintenance | UReason WebinarData Driven Maintenance | UReason Webinar
Data Driven Maintenance | UReason Webinar
UReason
 
AI for Legal Research with applications, tools
AI for Legal Research with applications, toolsAI for Legal Research with applications, tools
AI for Legal Research with applications, tools
mahaffeycheryld
 
Rainfall intensity duration frequency curve statistical analysis and modeling...
Rainfall intensity duration frequency curve statistical analysis and modeling...Rainfall intensity duration frequency curve statistical analysis and modeling...
Rainfall intensity duration frequency curve statistical analysis and modeling...
bijceesjournal
 
CompEx~Manual~1210 (2).pdf COMPEX GAS AND VAPOURS
CompEx~Manual~1210 (2).pdf COMPEX GAS AND VAPOURSCompEx~Manual~1210 (2).pdf COMPEX GAS AND VAPOURS
CompEx~Manual~1210 (2).pdf COMPEX GAS AND VAPOURS
RamonNovais6
 
Gas agency management system project report.pdf
Gas agency management system project report.pdfGas agency management system project report.pdf
Gas agency management system project report.pdf
Kamal Acharya
 
Software Engineering and Project Management - Software Testing + Agile Method...
Software Engineering and Project Management - Software Testing + Agile Method...Software Engineering and Project Management - Software Testing + Agile Method...
Software Engineering and Project Management - Software Testing + Agile Method...
Prakhyath Rai
 
Optimizing Gradle Builds - Gradle DPE Tour Berlin 2024
Optimizing Gradle Builds - Gradle DPE Tour Berlin 2024Optimizing Gradle Builds - Gradle DPE Tour Berlin 2024
Optimizing Gradle Builds - Gradle DPE Tour Berlin 2024
Sinan KOZAK
 
Object Oriented Analysis and Design - OOAD
Object Oriented Analysis and Design - OOADObject Oriented Analysis and Design - OOAD
Object Oriented Analysis and Design - OOAD
PreethaV16
 
DEEP LEARNING FOR SMART GRID INTRUSION DETECTION: A HYBRID CNN-LSTM-BASED MODEL
DEEP LEARNING FOR SMART GRID INTRUSION DETECTION: A HYBRID CNN-LSTM-BASED MODELDEEP LEARNING FOR SMART GRID INTRUSION DETECTION: A HYBRID CNN-LSTM-BASED MODEL
DEEP LEARNING FOR SMART GRID INTRUSION DETECTION: A HYBRID CNN-LSTM-BASED MODEL
ijaia
 
Engineering Standards Wiring methods.pdf
Engineering Standards Wiring methods.pdfEngineering Standards Wiring methods.pdf
Engineering Standards Wiring methods.pdf
edwin408357
 
132/33KV substation case study Presentation
132/33KV substation case study Presentation132/33KV substation case study Presentation
132/33KV substation case study Presentation
kandramariana6
 
morris_worm_intro_and_source_code_analysis_.pdf
morris_worm_intro_and_source_code_analysis_.pdfmorris_worm_intro_and_source_code_analysis_.pdf
morris_worm_intro_and_source_code_analysis_.pdf
ycwu0509
 
An Introduction to the Compiler Designss
An Introduction to the Compiler DesignssAn Introduction to the Compiler Designss
An Introduction to the Compiler Designss
ElakkiaU
 
一比一原版(uofo毕业证书)美国俄勒冈大学毕业证如何办理
一比一原版(uofo毕业证书)美国俄勒冈大学毕业证如何办理一比一原版(uofo毕业证书)美国俄勒冈大学毕业证如何办理
一比一原版(uofo毕业证书)美国俄勒冈大学毕业证如何办理
upoux
 
Use PyCharm for remote debugging of WSL on a Windo cf5c162d672e4e58b4dde5d797...
Use PyCharm for remote debugging of WSL on a Windo cf5c162d672e4e58b4dde5d797...Use PyCharm for remote debugging of WSL on a Windo cf5c162d672e4e58b4dde5d797...
Use PyCharm for remote debugging of WSL on a Windo cf5c162d672e4e58b4dde5d797...
shadow0702a
 
AI + Data Community Tour - Build the Next Generation of Apps with the Einstei...
AI + Data Community Tour - Build the Next Generation of Apps with the Einstei...AI + Data Community Tour - Build the Next Generation of Apps with the Einstei...
AI + Data Community Tour - Build the Next Generation of Apps with the Einstei...
Paris Salesforce Developer Group
 

Recently uploaded (20)

1FIDIC-CONSTRUCTION-CONTRACT-2ND-ED-2017-RED-BOOK.pdf
1FIDIC-CONSTRUCTION-CONTRACT-2ND-ED-2017-RED-BOOK.pdf1FIDIC-CONSTRUCTION-CONTRACT-2ND-ED-2017-RED-BOOK.pdf
1FIDIC-CONSTRUCTION-CONTRACT-2ND-ED-2017-RED-BOOK.pdf
 
Null Bangalore | Pentesters Approach to AWS IAM
Null Bangalore | Pentesters Approach to AWS IAMNull Bangalore | Pentesters Approach to AWS IAM
Null Bangalore | Pentesters Approach to AWS IAM
 
LLM Fine Tuning with QLoRA Cassandra Lunch 4, presented by Anant
LLM Fine Tuning with QLoRA Cassandra Lunch 4, presented by AnantLLM Fine Tuning with QLoRA Cassandra Lunch 4, presented by Anant
LLM Fine Tuning with QLoRA Cassandra Lunch 4, presented by Anant
 
CEC 352 - SATELLITE COMMUNICATION UNIT 1
CEC 352 - SATELLITE COMMUNICATION UNIT 1CEC 352 - SATELLITE COMMUNICATION UNIT 1
CEC 352 - SATELLITE COMMUNICATION UNIT 1
 
Data Driven Maintenance | UReason Webinar
Data Driven Maintenance | UReason WebinarData Driven Maintenance | UReason Webinar
Data Driven Maintenance | UReason Webinar
 
AI for Legal Research with applications, tools
AI for Legal Research with applications, toolsAI for Legal Research with applications, tools
AI for Legal Research with applications, tools
 
Rainfall intensity duration frequency curve statistical analysis and modeling...
Rainfall intensity duration frequency curve statistical analysis and modeling...Rainfall intensity duration frequency curve statistical analysis and modeling...
Rainfall intensity duration frequency curve statistical analysis and modeling...
 
CompEx~Manual~1210 (2).pdf COMPEX GAS AND VAPOURS
CompEx~Manual~1210 (2).pdf COMPEX GAS AND VAPOURSCompEx~Manual~1210 (2).pdf COMPEX GAS AND VAPOURS
CompEx~Manual~1210 (2).pdf COMPEX GAS AND VAPOURS
 
Gas agency management system project report.pdf
Gas agency management system project report.pdfGas agency management system project report.pdf
Gas agency management system project report.pdf
 
Software Engineering and Project Management - Software Testing + Agile Method...
Software Engineering and Project Management - Software Testing + Agile Method...Software Engineering and Project Management - Software Testing + Agile Method...
Software Engineering and Project Management - Software Testing + Agile Method...
 
Optimizing Gradle Builds - Gradle DPE Tour Berlin 2024
Optimizing Gradle Builds - Gradle DPE Tour Berlin 2024Optimizing Gradle Builds - Gradle DPE Tour Berlin 2024
Optimizing Gradle Builds - Gradle DPE Tour Berlin 2024
 
Object Oriented Analysis and Design - OOAD
Object Oriented Analysis and Design - OOADObject Oriented Analysis and Design - OOAD
Object Oriented Analysis and Design - OOAD
 
DEEP LEARNING FOR SMART GRID INTRUSION DETECTION: A HYBRID CNN-LSTM-BASED MODEL
DEEP LEARNING FOR SMART GRID INTRUSION DETECTION: A HYBRID CNN-LSTM-BASED MODELDEEP LEARNING FOR SMART GRID INTRUSION DETECTION: A HYBRID CNN-LSTM-BASED MODEL
DEEP LEARNING FOR SMART GRID INTRUSION DETECTION: A HYBRID CNN-LSTM-BASED MODEL
 
Engineering Standards Wiring methods.pdf
Engineering Standards Wiring methods.pdfEngineering Standards Wiring methods.pdf
Engineering Standards Wiring methods.pdf
 
132/33KV substation case study Presentation
132/33KV substation case study Presentation132/33KV substation case study Presentation
132/33KV substation case study Presentation
 
morris_worm_intro_and_source_code_analysis_.pdf
morris_worm_intro_and_source_code_analysis_.pdfmorris_worm_intro_and_source_code_analysis_.pdf
morris_worm_intro_and_source_code_analysis_.pdf
 
An Introduction to the Compiler Designss
An Introduction to the Compiler DesignssAn Introduction to the Compiler Designss
An Introduction to the Compiler Designss
 
一比一原版(uofo毕业证书)美国俄勒冈大学毕业证如何办理
一比一原版(uofo毕业证书)美国俄勒冈大学毕业证如何办理一比一原版(uofo毕业证书)美国俄勒冈大学毕业证如何办理
一比一原版(uofo毕业证书)美国俄勒冈大学毕业证如何办理
 
Use PyCharm for remote debugging of WSL on a Windo cf5c162d672e4e58b4dde5d797...
Use PyCharm for remote debugging of WSL on a Windo cf5c162d672e4e58b4dde5d797...Use PyCharm for remote debugging of WSL on a Windo cf5c162d672e4e58b4dde5d797...
Use PyCharm for remote debugging of WSL on a Windo cf5c162d672e4e58b4dde5d797...
 
AI + Data Community Tour - Build the Next Generation of Apps with the Einstei...
AI + Data Community Tour - Build the Next Generation of Apps with the Einstei...AI + Data Community Tour - Build the Next Generation of Apps with the Einstei...
AI + Data Community Tour - Build the Next Generation of Apps with the Einstei...
 

Aerial detection part3

  • 2. Contents 2 1. EAST: An Efficient and Accurate Scene Text Detector 2. Towards Multi-class Object Detection in Unconstrained Remote Sensing Imagery
  • 3. EAST: An Efficient and Accurate Scene Text Detector 3 Network Overview Pipeline Input image Multi-channel FCN Multi-channel FCN Multi-oriented Task-wise boxes
  • 4. 4 EAST: An Efficient and Accurate Scene Text Detector Main Contributions : 1. propose two stage(step) method : FCN and NMS merging stage 2. pipeline is flexible
  • 5. 5 EAST: An Efficient and Accurate Scene Text Detector Relate work: PVANet
  • 6. 6 EAST: An Efficient and Accurate Scene Text Detector Pipeline input conv2 conv3 conv1 conv3 merging1 merging2 merging3 For reduce computation cost, using U-shape not using HyperNet in PVANet that merge all feature maps output
  • 7. EAST: An Efficient and Accurate Scene Text Detector 7 Label Generation
  • 8. EAST: An Efficient and Accurate Scene Text Detector 8 Label Generation: Score Map Generation Score map generation eq 𝑟𝑖 = min(D 𝑝𝑖, 𝑝 𝑖 𝑚𝑜𝑑 4 +1 , D 𝑝𝑖, 𝑝 𝑖+2 𝑚𝑜𝑑 4 +1 we shrink it by moving its two endpoints inward along the edge by 0.3𝑟𝑖 and 0.3𝑟 𝑖 𝑚𝑜𝑑 4 +1 espectively.
  • 9. 9 EAST: An Efficient and Accurate Scene Text Detector 𝐿 = 𝐿 𝑠 + 𝜆 𝑔 𝐿 𝑔 Label Generation: Loss Where Y = 𝐹S is the prediction of the score map, and Y∗ is the ground truth 𝐿 𝑠 : loss for score map 𝐿 𝑔 : loss for geometry
  • 10. 10 EAST: An Efficient and Accurate Scene Text Detector 𝐿 = 𝐿 𝑠 + 𝜆 𝑔 𝐿 𝑔 Label Generation: Loss RBOX: 𝐿 𝑔 = 𝐿 𝐴𝐴𝐵𝐵 + 𝜆 𝜃 𝐿 𝜃 𝐿 𝑠 : loss for score map 𝐿 𝑔 : loss for geometry 𝐿 𝑔 = 𝐿QUAD Q, Q∗ = min Q∈𝑃 𝑄∗ 𝑐 𝑖∈CQ 𝑐 𝑖∈CQ smoothed 𝐿1 𝑐𝑖 − 𝑐𝑖 8 × 𝑁 𝑄∗ QUAD:
  • 11. 11 EAST: An Efficient and Accurate Scene Text Detector Locality-Aware NMS Problem: A naïve NMS algorithm runs in 𝑂 𝑛2 where 𝑛 is the number of candidate geometries. The geometries from nearby pixels tend to be highly correlated. Solution: locality-aware NMS 𝑎 = WEIGHTEDMERGE 𝑔, 𝑝 , then 𝑎i = V 𝑔 𝑔𝑖 + 𝑉 𝑝 𝑝𝑖 and V 𝑎 = V 𝑔 + V(𝑝)
  • 12. 12 EAST: An Efficient and Accurate Scene Text Detector
  • 13. Towards Multi-class Object Detection in Unconstrained Remote Sensing Imagery 13 Network Overview
  • 14. 14 Towards Multi-class Object Detection in Unconstrained Remote Sensing Imagery Main Contributions : 1. new joint image cascade and feature pyramid network(ICN and FPN) 2. design a DIN module as a domain adaptation module 3. new loss function to shape rectangles by constraining the angles between the edges to 90 degrees
  • 15. Towards Multi-class Object Detection in Unconstrained Remote Sensing Imagery 15 ICN, FPN and Deformable Inception Subnetworks • Appropriate weights sharing • Resize image size by bilinear interpolation ICN • The low-level semantic feature from high resolution • The high-level semantic feature from low-level resolution
  • 16. Towards Multi-class Object Detection in Unconstrained Remote Sensing Imagery 16 ICN, FPN and Deformable Inception Subnetworks
  • 17. Towards Multi-class Object Detection in Unconstrained Remote Sensing Imagery 17 R-RPN Characteristics: 1. no difference between the front and back of objects 2. initialize anchor by using dimension clustering in YOLO v2 3. use the smooth 𝑙1 loss to regress the four coordinates
  • 18. Towards Multi-class Object Detection in Unconstrained Remote Sensing Imagery 18 R-ROI Characteristics: 1. penalize angles that are not 90 degree 2. initialize anchor by using dimension clustering in YOLO v2 3. use the smooth 𝑙1 loss to regress the four coordinates penalize angles that are not 90 degree
  • 19. Towards Multi-class Object Detection in Unconstrained Remote Sensing Imagery 19 Objective
  • 20. Towards Multi-class Object Detection in Unconstrained Remote Sensing Imagery 20 Objective
  • 21. Towards Multi-class Object Detection in Unconstrained Remote Sensing Imagery 21 Result
  • 22. Towards Multi-class Object Detection in Unconstrained Remote Sensing Imagery 22 Result
  • 23. Towards Multi-class Object Detection in Unconstrained Remote Sensing Imagery 23 Result
  • 24. Reference 24 EAST: PVANET: Deep but lightweight neural networks for real-time object detection. Balanced-cross entropy: Holistically-nested edge detection Scene text detection via holistic, multi-channel prediction. U-shape: U-net: Convolu-tional networks for biomedical image segmentation. Towards Multi-class Object Detection in Unconstrained Remote Sensing Imagery: Soft-NMS: Improving object detection with one line of code. IoU distance: Yolo9000: Better, faster, stronger. DIN: deformable convolutional networks

Editor's Notes

  1. DIN 내부에 deformable convolution을 통해 geometric transformation을 적용하는 것을 도와주고 더욱 offset regression property는 kernel 외부의 object를 localization하는 것을 도움 줍니다.
  2. DIN 내부에 deformable convolution을 통해 geometric transformation을 적용하는 것을 도와주고 더욱 offset regression property는 kernel 외부의 object를 localization하는 것을 도움 줍니다.
  3. DIN 내부에 deformable convolution을 통해 geometric transformation을 적용하는 것을 도와주고 더욱 offset regression property는 kernel 외부의 object를 localization하는 것을 도움 줍니다.
  4. DIN 내부에 deformable convolution을 통해 geometric transformation을 적용하는 것을 도와주고 더욱 offset regression property는 kernel 외부의 object를 localization하는 것을 도움 줍니다.
  5. DIN 내부에 deformable convolution을 통해 geometric transformation을 적용하는 것을 도와주고 더욱 offset regression property는 kernel 외부의 object를 localization하는 것을 도움 줍니다.
  6. DIN 내부에 deformable convolution을 통해 geometric transformation을 적용하는 것을 도와주고 더욱 offset regression property는 kernel 외부의 object를 localization하는 것을 도움 줍니다.
  7. DIN 내부에 deformable convolution을 통해 geometric transformation을 적용하는 것을 도와주고 더욱 offset regression property는 kernel 외부의 object를 localization하는 것을 도움 줍니다.
  8. DIN 내부에 deformable convolution을 통해 geometric transformation을 적용하는 것을 도와주고 더욱 offset regression property는 kernel 외부의 object를 localization하는 것을 도움 줍니다.
  9. DIN 내부에 deformable convolution을 통해 geometric transformation을 적용하는 것을 도와주고 더욱 offset regression property는 kernel 외부의 object를 localization하는 것을 도움 줍니다.