研究内容 - Research Topics

研究テーマ一覧

  • 高ダイナミックレンジ画像の生成
  • フラッシュ/ノンフラッシュ画像統合に基づく画像復元
  • 固有画像分解(Intrinsic image decomposition)
  • 映り込み/雨の軌跡/霧除去
  • 車載カメラのための画像復元・補正技術
  • 凸最適化を用いたハイパースペクトル画像復元
  • スパースFIRフィルタの設計

信号処理, 画像処理, Computational Photographyに関する研究に取り組んでいます.

高ダイナミックレンジ画像の生成

Weight Optimization for Multiple Image Integration and Its Applications

Ryo Matsuoka, Tomohiro Yamauchi, Tatsuya Baba and Masahiro Okuda

IEICE Transactions on Information and Systems, Vol.E99-D,No.1,pp.228-235, Jan. 2016

We propose an image restoration technique that uses multiple image integration. The detail of the dark area when acquiring a dark scene is often deteriorated by sensor noise. Simple image integration inherently has the capability of reducing random noises, but it is especially insufficient in scenes that have a dark area. We introduce a novel image integration technique that optimizes the weights for the integration. We find the optimal weight map by solving a proposed convex optimization problem for the weight optimization. Additionally, we apply the proposed weight optimization scheme to a single-image super-resolution problem, where we slightly modify the proposed weight optimization problem to estimate the high-resolution image from a single low-resolution one. We use some of our experimental results to show that the weight optimization significantly improves the denoising and super-resolution performances.

フラッシュ/ノンフラッシュ画像統合に基づく画像復元

Misaligned Image Integration with Local Linear Model

Tatsuya Baba, Ryo Matsuoka, Keiichiro Shirai, Masahiro Okuda

IEEE Transactions on Image Processing, vol. 25, no. 5, pp. 2035-2044, May 2016

We present a new image integration technique for a flash and long-exposure image pair to capture a dark scene without incurring blurring or noisy artifacts. Most existing methods require well-aligned images for the integration, which is often a burdensome restriction in practical use. We address this issue by locally transferring the colors of the flash images using a small fraction of the corresponding pixels in the long-exposure images. We formulate the image integration as a convex optimization problem with the local linear model. The proposed method makes it possible to integrate the color of the long-exposure image with the detail of the flash image without causing any harmful effects to its contrast, where we do not need perfect alignment between the images by virtue of our new integration principle. We show that our method successfully outperforms the state of the art in the image integration and reference-based color transfer for challenging misaligned data sets.

固有画像分解(Intrinsic image decomposition )

White Balancing by Using Multiple Images via Intrinsic Image Decomposition

Ryo Matsuoka, Tatsuya Baba, Mia Rizkinia and Masahiro Okuda

IEICE Transactions on Information and Systems, Vol.E98-D, No.8, pp.1562-1570, Aug. 2015

物体表面の分光反射率測定は, リモートセンシング, 医療, 食品衛生管理, 物体表面の分光反射率測定は, リモートセンシング, 医療, 食品衛生管理, 植生管理, 生体認証や科学捜査など様々な分野で活用されている. しかしながら, 測定範囲が非常に狭いため被写体の規模が大きくなるにつれて測定効率が低下する問題がある. そこで, 観測画像から画素単位の分光反射率を効率よく推定し保存する技術が求められている. 本研究ではフラッシュ点灯画像を補助情報として, 最適化による分光反射率画像(固有色成分)推定技術を開発し, 色補正問題へ応用することでその有効性を示した.

L0勾配最小化を用いた平滑化手法

【Paper 1】L0勾配最小化を用いた詳細強調の検討

赤井 優志, 松岡 諒

SIPシンポジウム, 2017

L0勾配最小化を用いた画像の平滑化手法の研究に取り組んでいます。この平滑化手法を用いることで, より精度の高いトーンマッピングや画像の詳細強調などを実現することができると考えています。

【Paper 2】L0 Smoothing Based on Gradient Constraints

Yuji Akai, Toshihiro Shibata, Ryo Matsuoka, Masahiro Okuda

IEEE International Conference on Image Processing (ICIP), pp. 3943-3947, Athens, Greece, Oct. 2018

This paper proposes an effective smoothing method based on gradient constraints. Image smoothing based on ℓ0 gradient minimization is useful for some important applications, e.g ., image restoration, intrinsic image decomposition, detail enhancement, and so on. However, undesirable pseudo-edge artifacts often occur in output images. To solve this problem, we introduce novel range constraints in gradient domain. Specifically, the proposed method suppresses these artifacts by introducing appropriate range constraints constructed from a reference image. Experimental results demonstrate the advantages of the proposed method over several conventional methods.

可視画像/距離画像ペアを用いた映り込み除去

【Paper 1】Reflection Removal Based on Gradient Constraints

Ryo Matsuoka

IEEE Global Conference on Consumer Electronics (GCCE), pp. 1-2, Nagoya, 2017

ガラス越しの撮影では手前の風景が撮影した画像中に映り込むことがある. この映り込みの除去は, 撮影者やその周囲の人々のプライバシー保護やロボットビジョンにおける画像認識精度の向上など, 様々な分野において重要な課題である. 本研究では, RGB-D画像を用いた新たな映り込み分離法を提案している.

【Paper 2】Reflection Removal Using RGB-D Images

Toshi hiro Shibata, Yuji Akai, Ryo Matsuoka

IEEE International Conference on Image Processing (ICIP), pp. 1862-1866, Athens, Greece, Oct. 2018

This paper proposes a novel reflection removal method for RGB-D images that achieve reflection removal and depth map recovery simultaneously. In general, there is a strong structure correlation between an RGB image and a depth map in gradient domain. Based on this fact, we introduce a novel regularization for RGB-D images named the multi-modal structure tensor total variation (MSTV). A proposed minimization problem based on MSTV which is constructed by two minimization problems, reflection removal and depth map recovery, is solved by using alternating direction method of multipliers (ADMM). Experimental results show the effectiveness of our method by applying it to both artificial and real-world images.

Rain Streak Removal

多重画像を用いた雨の軌跡除去に関する検討

和田紗月, 松岡諒

香川大学 卒業研究

悪天候の場合は雨や雪などによって画面に視野妨害ノイズが映り込み, 人物や車などの画像認識に悪影響を及ぼしてしまう. 画像からこのような不必要な情報を分離し, 明瞭な画像を復元することでパターン認識や異常検出の精度向上が期待できるため, 解決すべき重要な課題である. 本研究では, 露光を変えて撮影した多重画像から雨の軌跡除去と飽和画素復元を同時に達成する新たな画像統合手法を提案する.

近赤外/可視画像ペアを用いた霧除去

近赤外/可視画像ペアを用いた霧除去に関する検討

早木皓祐, 松岡諒

香川大学 卒業研究

屋外で撮影された画像は, 霧や霞, 塵埃などの悪天候によって画像のコントラストが低下するという問題がある. このように悪天候下で撮影された画像から霧を除去し鮮明な画像を取得するための研究が近年活発に行われている. 本研究では近赤外画像と可視画像のペア画像を用いることで, より精度の高い霧除去を目標とする.

スパースFIRフィルタの設計

Joint Sparsity and Order Optimization based on ADMM with Non-uniform Group Hard Thresholding

Ryo Matsuoka, Seisuke Kyochi, Shunsuke Ono

and Masahiro Okuda

IEEE Transactions on Circuits and Systems I: Regular Papers, Vol. 65, No. 5, pp. 1602-1613, 2018

This paper proposes a new optimization framework for the joint optimization of sparsity and filter order (JOSFO) for FIR filter design. Since the cost function for JOSFO involves L0 and non-uniform overlapped group L0 norms, which are not convex, a global optimal solution is difficult to obtain. To find an approximate solution of the non-convex problem, existing approaches repeat the following steps: 1) approximate the cost function; 2) find candidates of zero coefficients by minimizing the cost function; and 3) set them to zero. On the other hand, this paper directly solves the optimization problem, without any approximation to the cost function, by using the alternating direction method of multipliers with the pseudo-proximity operators of L0 and non-uniform non-overlapped group L0 norms. Experimental results show that resulting filters designed by the proposed method have sparser coefficients and lower orders, while satisfying filter specifications, such as an error from a desired frequency response.

凸最適化を用いたハイパースペクトル画像復元

Under construction...

研究紹介