Yukiko Yanagawa

Depth map upsampling by self-guided residual interpolation

In this paper, we propose a simple and effective depth upsampling technique using self-guided residual interpolation. The original residual interpolation requires guidance information such as high-resolution RGB color image. However, self-guided residual interpolation requires only a single depth map. In the proposed algorithm, a tentative estimation of a high-resolution depth map is first generated from an input low-resolution depth map. Then, re-interpolation is applied to the residual domain, which is defined by differences between the input depth map and the tentative estimate. A precise high-resolution depth map is obtainable by interpolating in the residual domain. Experimental results demonstrate that our algorithm can outperform state-of-the-art depth map upsampling algorithms.

Tracking abnormalities in video capsule endoscopy using surrounding features with a triangular constraint

This paper proposes a method to track abnormalities in successive frames in a capsule endoscopic image sequence. Exact tracking of an abnormality in the gastrointestinal tract is useful in preparing the content for educational systems. However, if the abnormality is de-formable over continuous frames and its features are not highly distinct, it is difficult to track abnormalities precisely. The proposed method uses not only the abnormality image features, but also surrounding features, called supporters. In a capsule endoscopic image sequence, however, both the supporters and the target are difficult to track using only their image features, because these features are indistinguishable. Since estimation using only surrounding features is hard, the proposed method uses triangular constraints among supporters as well. The proposed method is able to track successfully even if the target and supporter features are indistinguishable. Finally, we evaluate the proposed method using eight major types of abnormalities.

Abnormality tracking during video capsule endoscopy using an affine triangular constraint based on surrounding features

The precise tracking of an abnormality in the gastrointestinal tract is useful for medical training purposes. However, the gastrointestinal wall deforms continuously in an unpredictable manner, while abnormalities lack distinctive features, making them difficult to track over continuous frames. To address this problem, we propose a tracking method for capsule endoscopy using the surrounding features of abnormalities. By applying triangular constraints using an affine transformation, we are able to track abnormalities that do not have distinctive features over consecutive image frames. We demonstrate the efficacy of our approach using eight common types of gastrointestinal abnormalities.

Segmenting Reddish Lesions in Capsule Endoscopy Images Using a Gastrointestinal Color Space

Segmenting reddish lesions in capsule endoscopy (CE) images is an initial step for further computer-assisted applications such as image enhancement, abnormal measurement/tracking, and so on. In this paper, we propose an automatic segmentation method that is successful even with CE image including unclear reddish lesions. To obtain this, the proposed method seeks good features to discriminate the reddish lesions from normal tissues. For implementations, we first extract only meaningful regions in a CE image through a pre-segmentation step. The proposed features then are extracted for the meaningful regions in stead of the whole image. We approaches segmentation task through considering a statistical operator for the extracted features, that is local mean image. Candidates of the abnormal regions are located in the local mean image with assistants of a diffusion process. Evaluations in the experiments confirm effectiveness of the proposed method with both qualitative and quantitative measurement.