SlideShare a Scribd company logo
1 of 44
Download to read offline
第7回全日本CV勉強会 CVPR2021読み会(前編)
DeepI2P: Image-to-Point Cloud Registration
via Deep Classification
2021/07/11 takmin
自己紹介
2
株式会社ビジョン&ITラボ 代表取締役
皆川 卓也(みながわ たくや)
博士(工学)
「コンピュータビジョン勉強会@関東」主催
株式会社フューチャースタンダード 技術顧問
略歴:
1999-2003年
日本HP(後にアジレント・テクノロジーへ分社)にて、ITエンジニアとしてシステム構築、プリ
セールス、プロジェクトマネジメント、サポート等の業務に従事
2004-2009年
コンピュータビジョンを用いたシステム/アプリ/サービス開発等に従事
2007-2010年
慶應義塾大学大学院 後期博士課程にて、コンピュータビジョンを専攻
単位取得退学後、博士号取得(2014年)
2009年-現在
フリーランスとして、コンピュータビジョンのコンサル/研究/開発等に従事(2018年法人化)
http://visitlab.jp
ビジョン
技術の町医者
AIビジネスについて、気軽に相談できる
紹介する論文
4
 DeepI2P: Image-to-Point Cloud Registration via Deep
Classification
 Jiaxin Li (Bytedance), Gim Hee Lee (National University of
Singapore)
 選んだ理由:
 個人的に興味のあるテーマ
興味をもった背景
5
都市等の点群化が進展
Project PLATEAU Shizuoka Point Cloud DB
都営大江戸線都庁駅前点群データ
興味をもった背景
6
都市等の点群化が進展
人物検出、車両検出等、AIを導入したカメラも普及
カメラ画像が点群内のどの位置を撮影しているかがわ
かれば、三次元空間中の人やモノの位置を動的に把握
できるようになる
目的
7
 点群におけるカメラの自己位置推定を行う
 LiDARはカメラに比べて高コスト。
 一度LiDARで三次元マップを作製したら、カメラを用いて自己
位置推定する方が安価
特徴点マッチングによる自己位置推定 識別による自己位置推定(本手法)
Related Work: 2D3D-MatchNet
 画像はSIFT、点群はISSによってキーポイントを抽出し、キー
ポイント間のマッチングを行うための特徴量をTriplet Lossを
用いて学習
Feng, M., Hu, S.,Ang, M., & Lee, G. H. (2019). 2D3D-MatchNet: Learning to Match Keypoints Across 2D Image and 3D Point Cloud.
International Conference on Robotics and Automation .
Related Work: 2D-3D Line Correspondences
 画像と点群上の直線をマッチさせることで自己位置推定
Visual SLAMによるTrackingが前提条件
Yu, H., Zhen,W.,Yang,W., Zhang, J., & Scherer, S. (2020). Monocular Camera Localization in Prior LiDAR Maps with 2D-3D Line
Correspondences. IEEE International Conference on Intelligent Robots and Systems
概要
 既存手法(2D3D-MatchNet)では、点群の特徴
点と画像の特徴点とのマッチングによる自己
位置推定
SIFTとISSで取る特徴点が違う
 Cross-Modalな特徴学習を避けて、点群が画
像のFrustumやGrid内に収まるかという識別
問題として解く。
1. 点群が画像のFrustum/Grid内に存在するかを判
定するネットワーク(Classification)
2. 点群を画像上に投影し、姿勢を最適化(Pose
Optimization)
1. Classification
 LiDARで取得した点の1つ1つが画像に投影可能な範囲
(Frustum内)かどうかを判定
Frustum=カメラの視野を表す四角錐
Network Architecture
Network Architecture
PointNet++で点群
をグルーピングしな
がら特徴量抽出
Network Architecture
ResNetで画像から
特徴量抽出
Network Architecture
画像のグローバル
特徴と点群特徴か
ら画像の重み付き
特徴算出
Network Architecture
画像と点群のグロー
バル特徴、Attention
Fusionの出力、点群
グループ特徴から点
群特徴をUp Sampling
Network Architecture
各点がFrustum(また
は画像グリッド)内に
含まれるかの判定
Network Architecture
画像グローバル特徴 点群局所特徴
画像特徴
Attention
重み付き画像特徴
Network Architecture
画像グローバル特徴 点群局所特徴
画像特徴
Attention
重み付き画像特徴
Training Pipeline
1. データセットから画像と点群のペア(𝐼, 𝑃𝑟𝑎𝑤)、および相
対位置𝐺𝑐
𝑝
を取得
𝐼
𝑃𝑟𝑎𝑤
𝐺𝑐
𝑝
カメラ座標系 LiDAR座標系
Training Pipeline
2. ランダムな回転/移動𝐺𝑟を与え、それに合わせて点群
の座標とLiDARの相対位置を変換
𝐼
𝑃 = 𝐺𝑟𝑃𝑟𝑎𝑤
𝐺𝑐
𝑝
カメラ座標系 LiDAR座標系
𝐺 = 𝐺𝑐
𝑝
𝐺𝑟
−1
Training Pipeline
3. 点群がFrustum内に入っているかを判定し、各点にラベ
ル𝑙𝑖
𝑐
∈ 0,1 を付与
𝐼
カメラ座標系
LiDAR座標系
𝐺 = 𝐺𝑐
𝑝
𝐺𝑟
−1
𝑙𝑖
𝑐
= 0
𝑙𝑖
𝑐
= 1
Training Pipeline
4. 画像と点群のペア 𝐼, 𝑃 でネットワークへ入力
5. Frustum内かどうかを識別
6. Cross Entropy Lossでネットワークを学習
𝐼
𝑃
2. Pose Optimization
 ClassificationでFrustum内と判定された点を画像内に投
影可能な姿勢 ෠
𝐺を推定
投影
2. Pose Optimization
解きたい問題
෠
𝐺 = argmax
𝐺∈SE(3)
෍
𝑖=1
𝑁
𝑓 𝐏𝑖; 𝐺, 𝐾, 𝐻, 𝑊 − 0.5 መ
𝑙𝑖
𝑐
− 0.5
投影
点をカメラ姿勢𝑮で画像
に投影し、画像内に収
まるかどうかを判定
(6)
点がfrustum
内か
投影点が
画像内か
カメラ姿勢
コスト関数の最小化
 (6)式を緩和
෠
𝐺 = argmin
𝐺∈SE(3)
෍
𝑖=1
𝑁
𝑟𝑖 𝐺; መ
𝑙𝑖
𝑐
(12)
መ
𝑙𝑖
𝑐
= 0 (frustum外)の時、投影した点が画像の内側でコストが正
መ
𝑙𝑖
𝑐
= 1 (frustum内)の時、投影した点が画像の外側でコストが正
となるコスト関数
点群の各点を画像上へ投影し、コストの総和が最小となる姿勢
෡
𝑮をガウスニュートン法で求める
ニューラルネットは使わない
ClassificationでFrustum内と判定された点の
コスト
姿勢𝐺で投影された点 𝑝𝑥𝑖
′ , 𝑝𝑦𝑖
′
𝑔 𝑝𝑥𝑖
′ ; 𝑊 = max −𝑝𝑥𝑖
′ , 0 + max 𝑝𝑥𝑖
′ − 𝑊, 0
𝑔 𝑝𝑦𝑖
′ ; 𝐻 = max −𝑝𝑦𝑖
′ , 0 + max 𝑝𝑦𝑖
′ − 𝐻, 0
ℎ 𝑧𝑖
′
; 𝑊 = 𝛼 ∙ max −𝑧𝑖
′
, 0
𝑝𝑥𝑖
′
, 𝑝𝑦𝑖
′
画像内はコストゼロ
画像外は画像からのL1距離
焦点より後ろにある場合のコスト
(7)
(8)
ClassificationでFrustum外と判定された点の
コスト
𝑢 𝑝𝑥𝑖
′
; 𝑊 =
𝑊
2
− 𝑝𝑥𝑖
′
−
𝑊
2
𝑢 𝑝𝑦𝑖
′
; 𝐻 =
𝐻
2
− 𝑝𝑦𝑖
′
−
𝐻
2
𝑝𝑥𝑖
′ , 𝑝𝑦𝑖
′
画像内は正のL1距離
画像外は画像からの負のL1距離
(9)
コスト関数の最小化
 コストの総和が最小となる姿勢 ෠
𝐺をガウスニュートン法で求める
෠
𝐺 = argmin
𝐺∈SE(3)
෍
𝑖=1
𝑁
𝑟𝑖 𝐺; መ
𝑙𝑖
𝑐
(12)
Iteration = 0 Iteration = 40 Iteration = 80
𝑟𝑖
0
= 𝑢 𝑝𝑥𝑖
′
; 𝑊 + 𝑢 𝑝𝑦𝑖
′
; 𝐻 ∙ 𝕝 𝑝𝑥𝑖
′
, 𝑝𝑦𝑖
′
, 𝑧𝑖
′
; 𝐻, 𝑊
𝑟𝑖
1
= 𝑔 𝑝𝑥𝑖
′
; 𝑊 + 𝑔 𝑝𝑦𝑖
′
; 𝐻 + ℎ 𝑧𝑖
′ (11)
: መ
𝑙𝑖
𝑐
= 0
: መ
𝑙𝑖
𝑐
= 1
(𝑝𝑥𝑖
′
, 𝑝𝑦𝑖
′
)が画像内なら0、それ以外1
Experiments
 Oxfordデータセット+KITTIデータセット
で評価
点群と画像のペアは±10mの範囲でラン
ダムに選択
 Pose Optimization
初期姿勢𝐺(0)
を60回ランダムに生成し、最
適化の結果最小コストとなるものを採用
初期姿勢𝐺(0)
のrotationはz軸を中心とした
回転のみ、translationはxy平面上でのみ
Experiments
Grid ClassificationとFrustum Classificationの可視化
 緑:どちらでも正しく識別
 黄色:Frustum Classificationのみ正しく識別
 赤: Frustum Classificationで外と判定
 青: Frustum Classificationで内と判定
Experiments
Frustum Classification + Pose Optimizationの結果例
Oxford KITTI
Experiments: Registration Accuracy
 RTE = Relative Translational Error
 RRE = Relative Rotation Error
Experiments: Registration Accuracy
 RTE = Relative Translational Error
 RRE = Relative Rotation Error
Global Image Feature +
Global Point Cloud Feature
からMLPでPose推定
Experiments: Registration Accuracy
 RTE = Relative Translational Error
 RRE = Relative Rotation Error
ニューラルネットによる単眼
デプス推定+点群キーポイ
ントマッチング
Experiments: Registration Accuracy
 RTE = Relative Translational Error
 RRE = Relative Rotation Error
ニューラルネットによる単眼
デプス推定+Ground Truthを
初期位置としたICP
Experiments: Registration Accuracy
 RTE = Relative Translational Error
 RRE = Relative Rotation Error
Experiments: Registration Accuracy
 RTE = Relative Translational Error
 RRE = Relative Rotation Error
32x32の画像Grid単位
で点のIn/Outを識別し、
PnPで姿勢推定
Experiments: Registration Accuracy
 RTE = Relative Translational Error
 RRE = Relative Rotation Error
画像全体でFrustumの
In/Out判定+6DoFで姿
勢推定
Experiments: Registration Accuracy
 RTE = Relative Translational Error
 RRE = Relative Rotation Error
画像全体でFrustumの
In/Out判定+3DoFで姿
勢推定
Experiments: Registration Accuracy
 RTE = Relative Translational Error
 RRE = Relative Rotation Error
MonoDepth2 + GT-ICPは初期値がGround Truthであるが、RREは上回り、RTEは同等
Ablation Study
Ablation Study
点群の密度
Pose Optimization
の初期値試行回数
点群と画像間の距
離の最大値
まとめ
 画像と点群という異なる領域の位置合わせ(レジスト
レーション)を提案
 レジストレーションを2つの問題に分割
点が画像内に収まるかという識別問題をニューラルネットワー
クで解く
カメラ/LiDAR間の姿勢を、点群のカメラへの投影によって最
小二乗問題として解く
 OxfordおよびKITTIデータセットで有用性確認

More Related Content

What's hot

SSII2021 [SS1] Transformer x Computer Visionの 実活用可能性と展望 〜 TransformerのCompute...
SSII2021 [SS1] Transformer x Computer Visionの 実活用可能性と展望 〜 TransformerのCompute...SSII2021 [SS1] Transformer x Computer Visionの 実活用可能性と展望 〜 TransformerのCompute...
SSII2021 [SS1] Transformer x Computer Visionの 実活用可能性と展望 〜 TransformerのCompute...SSII
 
【DL輪読会】"Instant Neural Graphics Primitives with a Multiresolution Hash Encoding"
【DL輪読会】"Instant Neural Graphics Primitives with a Multiresolution Hash Encoding"【DL輪読会】"Instant Neural Graphics Primitives with a Multiresolution Hash Encoding"
【DL輪読会】"Instant Neural Graphics Primitives with a Multiresolution Hash Encoding"Deep Learning JP
 
畳み込みニューラルネットワークの高精度化と高速化
畳み込みニューラルネットワークの高精度化と高速化畳み込みニューラルネットワークの高精度化と高速化
畳み込みニューラルネットワークの高精度化と高速化Yusuke Uchida
 
ブラックボックスからXAI (説明可能なAI) へ - LIME (Local Interpretable Model-agnostic Explanat...
ブラックボックスからXAI (説明可能なAI) へ - LIME (Local Interpretable Model-agnostic Explanat...ブラックボックスからXAI (説明可能なAI) へ - LIME (Local Interpretable Model-agnostic Explanat...
ブラックボックスからXAI (説明可能なAI) へ - LIME (Local Interpretable Model-agnostic Explanat...西岡 賢一郎
 
SSII2019企画: 点群深層学習の研究動向
SSII2019企画: 点群深層学習の研究動向SSII2019企画: 点群深層学習の研究動向
SSII2019企画: 点群深層学習の研究動向SSII
 
【メタサーベイ】数式ドリブン教師あり学習
【メタサーベイ】数式ドリブン教師あり学習【メタサーベイ】数式ドリブン教師あり学習
【メタサーベイ】数式ドリブン教師あり学習cvpaper. challenge
 
backbone としての timm 入門
backbone としての timm 入門backbone としての timm 入門
backbone としての timm 入門Takuji Tahara
 
[DL輪読会]相互情報量最大化による表現学習
[DL輪読会]相互情報量最大化による表現学習[DL輪読会]相互情報量最大化による表現学習
[DL輪読会]相互情報量最大化による表現学習Deep Learning JP
 
Triplet Loss 徹底解説
Triplet Loss 徹底解説Triplet Loss 徹底解説
Triplet Loss 徹底解説tancoro
 
[DL輪読会]PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metr...
[DL輪読会]PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metr...[DL輪読会]PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metr...
[DL輪読会]PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metr...Deep Learning JP
 
[DL輪読会]Flow-based Deep Generative Models
[DL輪読会]Flow-based Deep Generative Models[DL輪読会]Flow-based Deep Generative Models
[DL輪読会]Flow-based Deep Generative ModelsDeep Learning JP
 
Swin Transformer (ICCV'21 Best Paper) を完璧に理解する資料
Swin Transformer (ICCV'21 Best Paper) を完璧に理解する資料Swin Transformer (ICCV'21 Best Paper) を完璧に理解する資料
Swin Transformer (ICCV'21 Best Paper) を完璧に理解する資料Yusuke Uchida
 
【メタサーベイ】Neural Fields
【メタサーベイ】Neural Fields【メタサーベイ】Neural Fields
【メタサーベイ】Neural Fieldscvpaper. challenge
 
[DL輪読会]Vision Transformer with Deformable Attention (Deformable Attention Tra...
[DL輪読会]Vision Transformer with Deformable Attention (Deformable Attention Tra...[DL輪読会]Vision Transformer with Deformable Attention (Deformable Attention Tra...
[DL輪読会]Vision Transformer with Deformable Attention (Deformable Attention Tra...Deep Learning JP
 
ICCV 2019 論文紹介 (26 papers)
ICCV 2019 論文紹介 (26 papers)ICCV 2019 論文紹介 (26 papers)
ICCV 2019 論文紹介 (26 papers)Hideki Okada
 
モデル高速化百選
モデル高速化百選モデル高速化百選
モデル高速化百選Yusuke Uchida
 
SHAP値の考え方を理解する(木構造編)
SHAP値の考え方を理解する(木構造編)SHAP値の考え方を理解する(木構造編)
SHAP値の考え方を理解する(木構造編)Kazuyuki Wakasugi
 
SSII2022 [SS2] 少ないデータやラベルを効率的に活用する機械学習技術 〜 足りない情報をどのように補うか?〜
SSII2022 [SS2] 少ないデータやラベルを効率的に活用する機械学習技術 〜 足りない情報をどのように補うか?〜SSII2022 [SS2] 少ないデータやラベルを効率的に活用する機械学習技術 〜 足りない情報をどのように補うか?〜
SSII2022 [SS2] 少ないデータやラベルを効率的に活用する機械学習技術 〜 足りない情報をどのように補うか?〜SSII
 
これからの Vision & Language ~ Acadexit した4つの理由
これからの Vision & Language ~ Acadexit した4つの理由これからの Vision & Language ~ Acadexit した4つの理由
これからの Vision & Language ~ Acadexit した4つの理由Yoshitaka Ushiku
 

What's hot (20)

SSII2021 [SS1] Transformer x Computer Visionの 実活用可能性と展望 〜 TransformerのCompute...
SSII2021 [SS1] Transformer x Computer Visionの 実活用可能性と展望 〜 TransformerのCompute...SSII2021 [SS1] Transformer x Computer Visionの 実活用可能性と展望 〜 TransformerのCompute...
SSII2021 [SS1] Transformer x Computer Visionの 実活用可能性と展望 〜 TransformerのCompute...
 
【DL輪読会】"Instant Neural Graphics Primitives with a Multiresolution Hash Encoding"
【DL輪読会】"Instant Neural Graphics Primitives with a Multiresolution Hash Encoding"【DL輪読会】"Instant Neural Graphics Primitives with a Multiresolution Hash Encoding"
【DL輪読会】"Instant Neural Graphics Primitives with a Multiresolution Hash Encoding"
 
畳み込みニューラルネットワークの高精度化と高速化
畳み込みニューラルネットワークの高精度化と高速化畳み込みニューラルネットワークの高精度化と高速化
畳み込みニューラルネットワークの高精度化と高速化
 
ブラックボックスからXAI (説明可能なAI) へ - LIME (Local Interpretable Model-agnostic Explanat...
ブラックボックスからXAI (説明可能なAI) へ - LIME (Local Interpretable Model-agnostic Explanat...ブラックボックスからXAI (説明可能なAI) へ - LIME (Local Interpretable Model-agnostic Explanat...
ブラックボックスからXAI (説明可能なAI) へ - LIME (Local Interpretable Model-agnostic Explanat...
 
SSII2019企画: 点群深層学習の研究動向
SSII2019企画: 点群深層学習の研究動向SSII2019企画: 点群深層学習の研究動向
SSII2019企画: 点群深層学習の研究動向
 
【メタサーベイ】数式ドリブン教師あり学習
【メタサーベイ】数式ドリブン教師あり学習【メタサーベイ】数式ドリブン教師あり学習
【メタサーベイ】数式ドリブン教師あり学習
 
backbone としての timm 入門
backbone としての timm 入門backbone としての timm 入門
backbone としての timm 入門
 
[DL輪読会]相互情報量最大化による表現学習
[DL輪読会]相互情報量最大化による表現学習[DL輪読会]相互情報量最大化による表現学習
[DL輪読会]相互情報量最大化による表現学習
 
Triplet Loss 徹底解説
Triplet Loss 徹底解説Triplet Loss 徹底解説
Triplet Loss 徹底解説
 
[DL輪読会]PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metr...
[DL輪読会]PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metr...[DL輪読会]PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metr...
[DL輪読会]PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metr...
 
[DL輪読会]Flow-based Deep Generative Models
[DL輪読会]Flow-based Deep Generative Models[DL輪読会]Flow-based Deep Generative Models
[DL輪読会]Flow-based Deep Generative Models
 
Point net
Point netPoint net
Point net
 
Swin Transformer (ICCV'21 Best Paper) を完璧に理解する資料
Swin Transformer (ICCV'21 Best Paper) を完璧に理解する資料Swin Transformer (ICCV'21 Best Paper) を完璧に理解する資料
Swin Transformer (ICCV'21 Best Paper) を完璧に理解する資料
 
【メタサーベイ】Neural Fields
【メタサーベイ】Neural Fields【メタサーベイ】Neural Fields
【メタサーベイ】Neural Fields
 
[DL輪読会]Vision Transformer with Deformable Attention (Deformable Attention Tra...
[DL輪読会]Vision Transformer with Deformable Attention (Deformable Attention Tra...[DL輪読会]Vision Transformer with Deformable Attention (Deformable Attention Tra...
[DL輪読会]Vision Transformer with Deformable Attention (Deformable Attention Tra...
 
ICCV 2019 論文紹介 (26 papers)
ICCV 2019 論文紹介 (26 papers)ICCV 2019 論文紹介 (26 papers)
ICCV 2019 論文紹介 (26 papers)
 
モデル高速化百選
モデル高速化百選モデル高速化百選
モデル高速化百選
 
SHAP値の考え方を理解する(木構造編)
SHAP値の考え方を理解する(木構造編)SHAP値の考え方を理解する(木構造編)
SHAP値の考え方を理解する(木構造編)
 
SSII2022 [SS2] 少ないデータやラベルを効率的に活用する機械学習技術 〜 足りない情報をどのように補うか?〜
SSII2022 [SS2] 少ないデータやラベルを効率的に活用する機械学習技術 〜 足りない情報をどのように補うか?〜SSII2022 [SS2] 少ないデータやラベルを効率的に活用する機械学習技術 〜 足りない情報をどのように補うか?〜
SSII2022 [SS2] 少ないデータやラベルを効率的に活用する機械学習技術 〜 足りない情報をどのように補うか?〜
 
これからの Vision & Language ~ Acadexit した4つの理由
これからの Vision & Language ~ Acadexit した4つの理由これからの Vision & Language ~ Acadexit した4つの理由
これからの Vision & Language ~ Acadexit した4つの理由
 

Similar to 20210711 deepI2P

A Beginner's Guide to Monocular Depth Estimation
A Beginner's Guide to Monocular Depth EstimationA Beginner's Guide to Monocular Depth Estimation
A Beginner's Guide to Monocular Depth EstimationRyo Takahashi
 
Final Report for project
Final Report for projectFinal Report for project
Final Report for projectRajarshi Roy
 
Class[4][19th jun] [three js-camera&light]
Class[4][19th jun] [three js-camera&light]Class[4][19th jun] [three js-camera&light]
Class[4][19th jun] [three js-camera&light]Saajid Akram
 
ANISH_and_DR.DANIEL_augmented_reality_presentation
ANISH_and_DR.DANIEL_augmented_reality_presentationANISH_and_DR.DANIEL_augmented_reality_presentation
ANISH_and_DR.DANIEL_augmented_reality_presentationAnish Patel
 
IRJET- An Acute Method of Encryption & Decryption by using Histograms and Che...
IRJET- An Acute Method of Encryption & Decryption by using Histograms and Che...IRJET- An Acute Method of Encryption & Decryption by using Histograms and Che...
IRJET- An Acute Method of Encryption & Decryption by using Histograms and Che...IRJET Journal
 
Flow Trajectory Approach for Human Action Recognition
Flow Trajectory Approach for Human Action RecognitionFlow Trajectory Approach for Human Action Recognition
Flow Trajectory Approach for Human Action RecognitionIRJET Journal
 
Lecture-1-2-+(1).pdf
Lecture-1-2-+(1).pdfLecture-1-2-+(1).pdf
Lecture-1-2-+(1).pdfsamaghorab
 
Lecture-1-2-+(1).pdf
Lecture-1-2-+(1).pdfLecture-1-2-+(1).pdf
Lecture-1-2-+(1).pdfsamaghorab
 
Y1 gd engine_terminology
Y1 gd engine_terminologyY1 gd engine_terminology
Y1 gd engine_terminologyJaket123
 
IRJET- Real Time Implementation of Bi-Histogram Equalization Method on Androi...
IRJET- Real Time Implementation of Bi-Histogram Equalization Method on Androi...IRJET- Real Time Implementation of Bi-Histogram Equalization Method on Androi...
IRJET- Real Time Implementation of Bi-Histogram Equalization Method on Androi...IRJET Journal
 
IRJET- Design and Implementation of ATM Security System using Vibration Senso...
IRJET- Design and Implementation of ATM Security System using Vibration Senso...IRJET- Design and Implementation of ATM Security System using Vibration Senso...
IRJET- Design and Implementation of ATM Security System using Vibration Senso...IRJET Journal
 
Design and Implementation of EZW & SPIHT Image Coder for Virtual Images
Design and Implementation of EZW & SPIHT Image Coder for Virtual ImagesDesign and Implementation of EZW & SPIHT Image Coder for Virtual Images
Design and Implementation of EZW & SPIHT Image Coder for Virtual ImagesCSCJournals
 
Y1 gd engine_terminology
Y1 gd engine_terminologyY1 gd engine_terminology
Y1 gd engine_terminologyJordanianmc
 
Keynote at Tracking Workshop during ISMAR 2014
Keynote at Tracking Workshop during ISMAR 2014Keynote at Tracking Workshop during ISMAR 2014
Keynote at Tracking Workshop during ISMAR 2014Darius Burschka
 
Intro to computer vision in .net
Intro to computer vision in .netIntro to computer vision in .net
Intro to computer vision in .netStephen Lorello
 
Low Light Image Enhancement Using Zero-DCE algorithm
Low Light Image Enhancement Using Zero-DCE algorithmLow Light Image Enhancement Using Zero-DCE algorithm
Low Light Image Enhancement Using Zero-DCE algorithmIRJET Journal
 
Radar application project help
Radar application project helpRadar application project help
Radar application project helpAssignmentpedia
 
Techniques of Brain Cancer Detection from MRI using Machine Learning
Techniques of Brain Cancer Detection from MRI using Machine LearningTechniques of Brain Cancer Detection from MRI using Machine Learning
Techniques of Brain Cancer Detection from MRI using Machine LearningIRJET Journal
 

Similar to 20210711 deepI2P (20)

Log polar coordinates
Log polar coordinatesLog polar coordinates
Log polar coordinates
 
A Beginner's Guide to Monocular Depth Estimation
A Beginner's Guide to Monocular Depth EstimationA Beginner's Guide to Monocular Depth Estimation
A Beginner's Guide to Monocular Depth Estimation
 
Final Report for project
Final Report for projectFinal Report for project
Final Report for project
 
Class[4][19th jun] [three js-camera&light]
Class[4][19th jun] [three js-camera&light]Class[4][19th jun] [three js-camera&light]
Class[4][19th jun] [three js-camera&light]
 
ANISH_and_DR.DANIEL_augmented_reality_presentation
ANISH_and_DR.DANIEL_augmented_reality_presentationANISH_and_DR.DANIEL_augmented_reality_presentation
ANISH_and_DR.DANIEL_augmented_reality_presentation
 
Ijcet 06 10_001
Ijcet 06 10_001Ijcet 06 10_001
Ijcet 06 10_001
 
IRJET- An Acute Method of Encryption & Decryption by using Histograms and Che...
IRJET- An Acute Method of Encryption & Decryption by using Histograms and Che...IRJET- An Acute Method of Encryption & Decryption by using Histograms and Che...
IRJET- An Acute Method of Encryption & Decryption by using Histograms and Che...
 
Flow Trajectory Approach for Human Action Recognition
Flow Trajectory Approach for Human Action RecognitionFlow Trajectory Approach for Human Action Recognition
Flow Trajectory Approach for Human Action Recognition
 
Lecture-1-2-+(1).pdf
Lecture-1-2-+(1).pdfLecture-1-2-+(1).pdf
Lecture-1-2-+(1).pdf
 
Lecture-1-2-+(1).pdf
Lecture-1-2-+(1).pdfLecture-1-2-+(1).pdf
Lecture-1-2-+(1).pdf
 
Y1 gd engine_terminology
Y1 gd engine_terminologyY1 gd engine_terminology
Y1 gd engine_terminology
 
IRJET- Real Time Implementation of Bi-Histogram Equalization Method on Androi...
IRJET- Real Time Implementation of Bi-Histogram Equalization Method on Androi...IRJET- Real Time Implementation of Bi-Histogram Equalization Method on Androi...
IRJET- Real Time Implementation of Bi-Histogram Equalization Method on Androi...
 
IRJET- Design and Implementation of ATM Security System using Vibration Senso...
IRJET- Design and Implementation of ATM Security System using Vibration Senso...IRJET- Design and Implementation of ATM Security System using Vibration Senso...
IRJET- Design and Implementation of ATM Security System using Vibration Senso...
 
Design and Implementation of EZW & SPIHT Image Coder for Virtual Images
Design and Implementation of EZW & SPIHT Image Coder for Virtual ImagesDesign and Implementation of EZW & SPIHT Image Coder for Virtual Images
Design and Implementation of EZW & SPIHT Image Coder for Virtual Images
 
Y1 gd engine_terminology
Y1 gd engine_terminologyY1 gd engine_terminology
Y1 gd engine_terminology
 
Keynote at Tracking Workshop during ISMAR 2014
Keynote at Tracking Workshop during ISMAR 2014Keynote at Tracking Workshop during ISMAR 2014
Keynote at Tracking Workshop during ISMAR 2014
 
Intro to computer vision in .net
Intro to computer vision in .netIntro to computer vision in .net
Intro to computer vision in .net
 
Low Light Image Enhancement Using Zero-DCE algorithm
Low Light Image Enhancement Using Zero-DCE algorithmLow Light Image Enhancement Using Zero-DCE algorithm
Low Light Image Enhancement Using Zero-DCE algorithm
 
Radar application project help
Radar application project helpRadar application project help
Radar application project help
 
Techniques of Brain Cancer Detection from MRI using Machine Learning
Techniques of Brain Cancer Detection from MRI using Machine LearningTechniques of Brain Cancer Detection from MRI using Machine Learning
Techniques of Brain Cancer Detection from MRI using Machine Learning
 

More from Takuya Minagawa

Machine Learning Operations (MLOps): Overview, Definition, and Architecture
Machine Learning Operations (MLOps): Overview, Definition, and ArchitectureMachine Learning Operations (MLOps): Overview, Definition, and Architecture
Machine Learning Operations (MLOps): Overview, Definition, and ArchitectureTakuya Minagawa
 
点群SegmentationのためのTransformerサーベイ
点群SegmentationのためのTransformerサーベイ点群SegmentationのためのTransformerサーベイ
点群SegmentationのためのTransformerサーベイTakuya Minagawa
 
Learning to Solve Hard Minimal Problems
Learning to Solve Hard Minimal ProblemsLearning to Solve Hard Minimal Problems
Learning to Solve Hard Minimal ProblemsTakuya Minagawa
 
ConditionalPointDiffusion.pdf
ConditionalPointDiffusion.pdfConditionalPointDiffusion.pdf
ConditionalPointDiffusion.pdfTakuya Minagawa
 
楽しいコンピュータビジョンの受託仕事
楽しいコンピュータビジョンの受託仕事楽しいコンピュータビジョンの受託仕事
楽しいコンピュータビジョンの受託仕事Takuya Minagawa
 
20200910コンピュータビジョン今昔物語(JPTA講演資料)
20200910コンピュータビジョン今昔物語(JPTA講演資料)20200910コンピュータビジョン今昔物語(JPTA講演資料)
20200910コンピュータビジョン今昔物語(JPTA講演資料)Takuya Minagawa
 
2020/07/04 BSP-Net (CVPR2020)
2020/07/04 BSP-Net (CVPR2020)2020/07/04 BSP-Net (CVPR2020)
2020/07/04 BSP-Net (CVPR2020)Takuya Minagawa
 
20190706cvpr2019_3d_shape_representation
20190706cvpr2019_3d_shape_representation20190706cvpr2019_3d_shape_representation
20190706cvpr2019_3d_shape_representationTakuya Minagawa
 
20190307 visualslam summary
20190307 visualslam summary20190307 visualslam summary
20190307 visualslam summaryTakuya Minagawa
 
20190131 lidar-camera fusion semantic segmentation survey
20190131 lidar-camera fusion semantic segmentation survey20190131 lidar-camera fusion semantic segmentation survey
20190131 lidar-camera fusion semantic segmentation surveyTakuya Minagawa
 
2018/12/28 LiDARで取得した道路上点群に対するsemantic segmentation
2018/12/28 LiDARで取得した道路上点群に対するsemantic segmentation2018/12/28 LiDARで取得した道路上点群に対するsemantic segmentation
2018/12/28 LiDARで取得した道路上点群に対するsemantic segmentationTakuya Minagawa
 
run Keras model on opencv
run Keras model on opencvrun Keras model on opencv
run Keras model on opencvTakuya Minagawa
 
20181130 lidar object detection survey
20181130 lidar object detection survey20181130 lidar object detection survey
20181130 lidar object detection surveyTakuya Minagawa
 
object detection with lidar-camera fusion: survey (updated)
object detection with lidar-camera fusion: survey (updated)object detection with lidar-camera fusion: survey (updated)
object detection with lidar-camera fusion: survey (updated)Takuya Minagawa
 
object detection with lidar-camera fusion: survey
object detection with lidar-camera fusion: surveyobject detection with lidar-camera fusion: survey
object detection with lidar-camera fusion: surveyTakuya Minagawa
 

More from Takuya Minagawa (20)

Machine Learning Operations (MLOps): Overview, Definition, and Architecture
Machine Learning Operations (MLOps): Overview, Definition, and ArchitectureMachine Learning Operations (MLOps): Overview, Definition, and Architecture
Machine Learning Operations (MLOps): Overview, Definition, and Architecture
 
MobileNeRF
MobileNeRFMobileNeRF
MobileNeRF
 
点群SegmentationのためのTransformerサーベイ
点群SegmentationのためのTransformerサーベイ点群SegmentationのためのTransformerサーベイ
点群SegmentationのためのTransformerサーベイ
 
Learning to Solve Hard Minimal Problems
Learning to Solve Hard Minimal ProblemsLearning to Solve Hard Minimal Problems
Learning to Solve Hard Minimal Problems
 
ConditionalPointDiffusion.pdf
ConditionalPointDiffusion.pdfConditionalPointDiffusion.pdf
ConditionalPointDiffusion.pdf
 
楽しいコンピュータビジョンの受託仕事
楽しいコンピュータビジョンの受託仕事楽しいコンピュータビジョンの受託仕事
楽しいコンピュータビジョンの受託仕事
 
20201010 personreid
20201010 personreid20201010 personreid
20201010 personreid
 
20200910コンピュータビジョン今昔物語(JPTA講演資料)
20200910コンピュータビジョン今昔物語(JPTA講演資料)20200910コンピュータビジョン今昔物語(JPTA講演資料)
20200910コンピュータビジョン今昔物語(JPTA講演資料)
 
2020/07/04 BSP-Net (CVPR2020)
2020/07/04 BSP-Net (CVPR2020)2020/07/04 BSP-Net (CVPR2020)
2020/07/04 BSP-Net (CVPR2020)
 
20200704 bsp net
20200704 bsp net20200704 bsp net
20200704 bsp net
 
20190825 vins mono
20190825 vins mono20190825 vins mono
20190825 vins mono
 
20190706cvpr2019_3d_shape_representation
20190706cvpr2019_3d_shape_representation20190706cvpr2019_3d_shape_representation
20190706cvpr2019_3d_shape_representation
 
20190307 visualslam summary
20190307 visualslam summary20190307 visualslam summary
20190307 visualslam summary
 
Visual slam
Visual slamVisual slam
Visual slam
 
20190131 lidar-camera fusion semantic segmentation survey
20190131 lidar-camera fusion semantic segmentation survey20190131 lidar-camera fusion semantic segmentation survey
20190131 lidar-camera fusion semantic segmentation survey
 
2018/12/28 LiDARで取得した道路上点群に対するsemantic segmentation
2018/12/28 LiDARで取得した道路上点群に対するsemantic segmentation2018/12/28 LiDARで取得した道路上点群に対するsemantic segmentation
2018/12/28 LiDARで取得した道路上点群に対するsemantic segmentation
 
run Keras model on opencv
run Keras model on opencvrun Keras model on opencv
run Keras model on opencv
 
20181130 lidar object detection survey
20181130 lidar object detection survey20181130 lidar object detection survey
20181130 lidar object detection survey
 
object detection with lidar-camera fusion: survey (updated)
object detection with lidar-camera fusion: survey (updated)object detection with lidar-camera fusion: survey (updated)
object detection with lidar-camera fusion: survey (updated)
 
object detection with lidar-camera fusion: survey
object detection with lidar-camera fusion: surveyobject detection with lidar-camera fusion: survey
object detection with lidar-camera fusion: survey
 

Recently uploaded

Benefits Of Flutter Compared To Other Frameworks
Benefits Of Flutter Compared To Other FrameworksBenefits Of Flutter Compared To Other Frameworks
Benefits Of Flutter Compared To Other FrameworksSoftradix Technologies
 
Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024BookNet Canada
 
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhi
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | DelhiFULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhi
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhisoniya singh
 
Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...
Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...
Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...HostedbyConfluent
 
IAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsIAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsEnterprise Knowledge
 
Next-generation AAM aircraft unveiled by Supernal, S-A2
Next-generation AAM aircraft unveiled by Supernal, S-A2Next-generation AAM aircraft unveiled by Supernal, S-A2
Next-generation AAM aircraft unveiled by Supernal, S-A2Hyundai Motor Group
 
Presentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreterPresentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreternaman860154
 
How to Remove Document Management Hurdles with X-Docs?
How to Remove Document Management Hurdles with X-Docs?How to Remove Document Management Hurdles with X-Docs?
How to Remove Document Management Hurdles with X-Docs?XfilesPro
 
My Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 PresentationMy Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 PresentationRidwan Fadjar
 
Swan(sea) Song – personal research during my six years at Swansea ... and bey...
Swan(sea) Song – personal research during my six years at Swansea ... and bey...Swan(sea) Song – personal research during my six years at Swansea ... and bey...
Swan(sea) Song – personal research during my six years at Swansea ... and bey...Alan Dix
 
Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)Allon Mureinik
 
CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):comworks
 
Unblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen FramesUnblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen FramesSinan KOZAK
 
Beyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry InnovationBeyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry InnovationSafe Software
 
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...shyamraj55
 
WhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure service
WhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure serviceWhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure service
WhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure servicePooja Nehwal
 
08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking MenDelhi Call girls
 
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticsKotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticscarlostorres15106
 

Recently uploaded (20)

Vulnerability_Management_GRC_by Sohang Sengupta.pptx
Vulnerability_Management_GRC_by Sohang Sengupta.pptxVulnerability_Management_GRC_by Sohang Sengupta.pptx
Vulnerability_Management_GRC_by Sohang Sengupta.pptx
 
Benefits Of Flutter Compared To Other Frameworks
Benefits Of Flutter Compared To Other FrameworksBenefits Of Flutter Compared To Other Frameworks
Benefits Of Flutter Compared To Other Frameworks
 
Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
Transcript: #StandardsGoals for 2024: What’s new for BISAC - Tech Forum 2024
 
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhi
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | DelhiFULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhi
FULL ENJOY 🔝 8264348440 🔝 Call Girls in Diplomatic Enclave | Delhi
 
Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...
Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...
Transforming Data Streams with Kafka Connect: An Introduction to Single Messa...
 
IAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsIAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI Solutions
 
Next-generation AAM aircraft unveiled by Supernal, S-A2
Next-generation AAM aircraft unveiled by Supernal, S-A2Next-generation AAM aircraft unveiled by Supernal, S-A2
Next-generation AAM aircraft unveiled by Supernal, S-A2
 
Presentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreterPresentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreter
 
How to Remove Document Management Hurdles with X-Docs?
How to Remove Document Management Hurdles with X-Docs?How to Remove Document Management Hurdles with X-Docs?
How to Remove Document Management Hurdles with X-Docs?
 
The transition to renewables in India.pdf
The transition to renewables in India.pdfThe transition to renewables in India.pdf
The transition to renewables in India.pdf
 
My Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 PresentationMy Hashitalk Indonesia April 2024 Presentation
My Hashitalk Indonesia April 2024 Presentation
 
Swan(sea) Song – personal research during my six years at Swansea ... and bey...
Swan(sea) Song – personal research during my six years at Swansea ... and bey...Swan(sea) Song – personal research during my six years at Swansea ... and bey...
Swan(sea) Song – personal research during my six years at Swansea ... and bey...
 
Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)
 
CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):CloudStudio User manual (basic edition):
CloudStudio User manual (basic edition):
 
Unblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen FramesUnblocking The Main Thread Solving ANRs and Frozen Frames
Unblocking The Main Thread Solving ANRs and Frozen Frames
 
Beyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry InnovationBeyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
Beyond Boundaries: Leveraging No-Code Solutions for Industry Innovation
 
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
Automating Business Process via MuleSoft Composer | Bangalore MuleSoft Meetup...
 
WhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure service
WhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure serviceWhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure service
WhatsApp 9892124323 ✓Call Girls In Kalyan ( Mumbai ) secure service
 
08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men
 
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticsKotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
 

20210711 deepI2P