Special Issue "Scene Understanding and Semantic Analysis in Images and 3D Data"

A special issue of Applied Sciences (ISSN 2076-3417). This special issue belongs to the section "Computing and Artificial Intelligence".

Deadline for manuscript submissions: closed (10 October 2021) | Viewed by 760

Special Issue Editors

Prof. Dr. Pietro Zanuttigh
E-Mail Website
Guest Editor
Multimedia Technology and Telecommunications Lab, University of Padova, 35131 Padova PD, Italy
Interests: computer vision; semantic segmentation; transfer learning; 3D data acquisition and processing; time-of-flight sensors
Special Issues, Collections and Topics in MDPI journals
Dr. Stefano Ghidoni
E-Mail Website
Guest Editor
Department of Information Engineering, IAS-Lab (Intelligent Autonomous Systems Lab), University of Padova, 35131 Padova PD, Italy
Interests: computer vision; deep learning for semantic segmentation and scene understanding; people detection and re-identification; industrial vision systems

Special Issue Information

Dear Colleagues,

Scene understanding from visual data is a key tool for many applications, including autonomous driving, robotic motion and path planning, industrial automation, and video surveillance. The recent introduction of deep learning techniques has fostered an impressive improvement in performance for approaches dealing with such very challenging tasks, even though the need for a large amount of training data remains a critical aspect. This Special Issue welcomes novel research works presenting effective strategies for scene understanding from both images and 3D data. Possible applications include segmentation, semantic analysis, detection or recognition of objects and people, and many others. Papers focusing on novel segmentation strategies together with machine learning techniques for semantic segmentation and, more generally, scene understanding from visual data are welcome. Covered topics also include techniques exploiting 3D information for the aforementioned applications, both in the form of depth data and of point clouds. Finally, possible submissions also include approaches for solving the critical issue of acquiring training data, including transfer learning, reinforcement learning, domain adaption, and incremental learning strategies for scene understanding.

Prof. Dr. Pietro Zanuttigh
Dr. Stefano Ghidoni
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Applied Sciences is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2300 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • Semantic segmentation
  • Image and 3D data segmentation
  • Deep learning for scene understanding
  • Transfer learning
  • Reinforcement learning
  • Domain adaptation
  • Point cloud segmentation
  • Depth data analysis
  • Incremental learning
  • 3D scene understanding
  • Robotic applications of scene understanding and human–robot cooperation
  • Scene understanding for autonomous driving
  • Scene understanding for drone applications

Published Papers (1 paper)

Order results
Result details
Select all
Export citation of selected articles as:

Research

Article
Throwaway Shadows Using Parallel Encoders Generative Adversarial Network
Appl. Sci. 2022, 12(2), 824; https://doi.org/10.3390/app12020824 - 14 Jan 2022
Viewed by 345
Abstract
Face photographs taken on a bright sunny day or in floodlight contain unnecessary shadows of objects on the face. Most previous works deal with removing shadow from scene images and struggle with doing so for facial images. Faces have a complex semantic structure, [...] Read more.
Face photographs taken on a bright sunny day or in floodlight contain unnecessary shadows of objects on the face. Most previous works deal with removing shadow from scene images and struggle with doing so for facial images. Faces have a complex semantic structure, due to which shadow removal is challenging. The aim of this research is to remove the shadow of an object in facial images. We propose a novel generative adversarial network (GAN) based image-to-image translation approach for shadow removal in face images. The first stage of our model automatically produces a binary segmentation mask for the shadow region. Then, the second stage, which is a GAN-based network, removes the object shadow and synthesizes the effected region. The generator network of our GAN has two parallel encoders—one is standard convolution path and the other is a partial convolution. We find that this combination in the generator results not only in learning an incorporated semantic structure but also in disentangling visual discrepancies problems under the shadow area. In addition to GAN loss, we exploit low level L1, structural level SSIM and perceptual loss from a pre-trained loss network for better texture and perceptual quality, respectively. Since there is no paired dataset for the shadow removal problem, we created a synthetic shadow dataset for training our network in a supervised manner. The proposed approach effectively removes shadows from real and synthetic test samples, while retaining complex facial semantics. Experimental evaluations consistently show the advantages of the proposed method over several representative state-of-the-art approaches. Full article
(This article belongs to the Special Issue Scene Understanding and Semantic Analysis in Images and 3D Data)
Show Figures

Figure 1

Back to TopTop