Patch-Based Difference-in-Level Detection with Segmented Ground Mask
-
Published:2023-02-06
Issue:4
Volume:12
Page:806
-
ISSN:2079-9292
-
Container-title:Electronics
-
language:en
-
Short-container-title:Electronics
Author:
Nonaka Yusuke1ORCID, Uchiyama Hideaki12ORCID, Saito Hideo1ORCID, Yachida Shoji3, Iwamoto Kota3
Affiliation:
1. Graduate School of Science and Technology, Keio University, Yokohama 223-8522, Japan 2. Information Science, Science and Technology, Nara Institute of Science and Technology, Nara 630-0192, Japan 3. Visual Intelligence Research Lab., NEC Corporation, Kawasaki 211-8666, Japan
Abstract
Difference-in-level detection in outdoor scenes has various possible applications, including walking assistance for blind people, robot walking assistance, and mapping the hazards of factory premises. It is difficult to detect all outdoor differences in level, such as RGB or RGB-D images, not only including road curbs, which are often targeted for detection in automated driving, but also differences in level on factory premises and sidewalks, because the pattern of outdoor differences in level is abundant and complex. This paper proposes a novel method for detecting differences in level from RGB-D images with segmented ground masks. First, image patches of differences in level were extracted from outdoor images to create the dataset. The change in the normal vector of the contour part on the detected plane is used to generate image patches of the difference in level, but this method strongly depends on the accuracy of planar detection, and it detects only some differences in level. Then, we created the dataset, consisting of image patches and including the extracted differences in level. The dataset is used for training a deep learning model for detecting differences in level in outdoor images without limitations. In addition, because the purpose of this paper is to detect differences in level in outdoor walking areas, regions in the image other than the target areas were excluded by the segmented ground mask. For the performance evaluation, we implemented our algorithm using a modern smartphone with a high-performance depth camera. To evaluate the effectiveness of the proposed method, the results from various inputs, such as RGB, depth, grayscale, normal, and combinations of them, were qualitatively and quantitatively evaluated, and Blender was used to generate synthetic test images for a quantitative evaluation of the difference in level. We confirm that the suggested method successfully detects various types of differences in level in outdoor images, even in complex scenes.
Subject
Electrical and Electronic Engineering,Computer Networks and Communications,Hardware and Architecture,Signal Processing,Control and Systems Engineering
Reference36 articles.
1. Conde, M.V., Vasluianu, F., Vazquez-Corral, J., and Timofte, R. (2023, January 2–7). Perceptual Image Enhancement for Smartphone Real-Time Applications. Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Waikoloa, HI, USA. 2. Super-Resolution Mapping Based on Spatial–Spectral Correlation for Spectral Imagery;Wang;IEEE Trans. Geosci. Remote Sens.,2021 3. Heterogeneous Knowledge Distillation for Simultaneous Infrared-Visible Image Fusion and Super-Resolution;Xiao;IEEE Trans. Instrum. Meas.,2022 4. Dong, J., Pan, J., Su, Z., and Yang, M.-H. (2017, January 22–29). Blind Image Deblurring with Outlier Handling. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Venice, Italy. 5. Saleh, F.S., Aliakbarian, M.S., Salzmann, M., Petersson, L., and Alvarez, J.M. (2018, January 8–14). Effective Use of Synthetic Data for Urban Scene Semantic Segmentation. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.
|
|