Yuuki Sawabe’s research while affiliated with The University of Tokyo and other places

What is this page?


This page lists works of an author who doesn't have a ResearchGate profile or hasn't added the works to their profile yet. It is automatically generated from public (personal) data to further our legitimate goal of comprehensive and accurate scientific recordkeeping. If you are this author and want this page removed, please let us know.

Publications (2)


FIGURE 4. Top row: Inputs for the RoI extraction. Bottom row:Before and after thresholding output regions of Selective Search in NFoV=65°
FIGURE 5. An example of 360° image viewer with the RoIs.
FIGURE 7. Examples of user-annotated RoIs dataset for evaluation.
Saliency-based Multiple Region of Interest Detection from a Single 360{\deg} image
  • Preprint
  • File available

September 2022

·

34 Reads

Yuuki Sawabe

·

Satoshi Ikehata

·

360{\deg} images are informative -- it contains omnidirectional visual information around the camera. However, the areas that cover a 360{\deg} image is much larger than the human's field of view, therefore important information in different view directions is easily overlooked. To tackle this issue, we propose a method for predicting the optimal set of Region of Interest (RoI) from a single 360{\deg} image using the visual saliency as a clue. To deal with the scarce, strongly biased training data of existing single 360{\deg} image saliency prediction dataset, we also propose a data augmentation method based on the spherical random data rotation. From the predicted saliency map and redundant candidate regions, we obtain the optimal set of RoIs considering both the saliency within a region and the Interaction-Over-Union (IoU) between regions. We conduct the subjective evaluation to show that the proposed method can select regions that properly summarize the input 360{\deg} image.

Download

FIGURE 4. Top row: Inputs for the RoI extraction. Bottom row:Before and after thresholding output regions of Selective Search in NFoV=65°
FIGURE 7. Examples of user-annotated RoIs dataset for evaluation.
Saliency-Based Multiple Region of Interest Detection From a Single 360° Image

January 2022

·

30 Reads

·

2 Citations

IEEE Access

360° images are informative – it contains omnidirectional visual information around the camera. However, the areas that cover a 360° image is much larger than the human’s field of view, therefore important information in different view directions is easily overlooked. To tackle this issue, we propose a method for predicting the optimal set of Region of Interest (RoI) from a single 360° image using the visual saliency as a clue. To deal with the scarce, strongly biased training data of existing single 360° image saliency prediction dataset, we also propose a data augmentation method based on the spherical random data rotation. From the predicted saliency map and redundant candidate regions, we obtain the optimal set of RoIs considering both the saliency within a region and the Interaction-Over-Union (IoU) between regions. We conduct the subjective evaluation to show that the proposed method can select regions that properly summarize the input 360° image.

Citations (1)


... They performed basic image processing, key bone point localization, and RoI enhancement. Sawabe et al. [29] worked on RoI extraction in 360 • images. Considering the benefits obtained in different fields, the RoI extraction is also considered in this work. ...

Reference:

Multiscale Attention-Based Hand Keypoint Detection
Saliency-Based Multiple Region of Interest Detection From a Single 360° Image

IEEE Access