• Home
  • Search
  • MonoSOD: Monocular Salient Object Detection based on Predicted Depth
  • Cite Icon4
  • https://doi.org/10.1109/icra48506.2021.9561211Copy DOI Icon

MonoSOD: Monocular Salient Object Detection based on Predicted Depth

  • May 30, 2021
  • George Dimas +2 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Salient object detection (SOD) can directly improve the performance of tasks like obstacle detection, semantic segmentation and object recognition. Such tasks are important for robotic and other autonomous navigation systems. State-of-the-art SOD methodologies, provide improved performance by incorporating depth information, usually acquired using additional specialized sensors, e.g., RGB-D cameras. This introduces an overhead to the overall cost and flexibility of such systems. Nevertheless, the recent advances of machine learning, have provided models, capable of generating depth map approximations, given a single RGB image. In this work, we propose a novel monocular SOD (MonoSOD) methodology, based on a two-branch CNN autoencoder architecture capable of predicting depth maps and estimating saliency through a trainable refinement scheme. Its application on benchmark datasets, indicates that its performance is comparable to that of state-of-the-art SOD methods relying on RGB-D data. Therefore, it could be considered as a lower-cost alternative of such methods for future applications.

Similar Papers
  • PDF
  • Research Article
  • Citations319

RGB-D salient object detection: A survey

  • Jan 01, 2021
  • Computational Visual Media
  • Tao Zhou +4
  • Research Article
  • Citations21

Depth Injection Framework for RGBD Salient Object Detection.

  • Jan 01, 2023
  • IEEE Transactions on Image Processing
  • Shunyu Yao +4
  • Book Chapter
  • Citations146

RGB-D Salient Object Detection with Cross-Modality Modulation and Selection

  • Jan 01, 2020
  • Chongyi Li +4
  • Book Chapter

Depth Supporting Semantic Segmentation via Deep Neural Markov Random Field

  • Jan 01, 2016
  • Wen Su +1
  • Conference Article
  • Citations1

A study of training free salient object detection methods in presence of noise

  • Sep 01, 2017
  • Nitin Kumar +3
  • Research Article
  • Citations31

Salient object detection using content-sensitive hypergraph representation and partitioning

  • May 01, 2012
  • Pattern Recognition
  • Zhen Liang +3
  • Book Chapter
  • Citations3

A Genetic Programming Approach for Constructing Foreground and Background Saliency Features for Salient Object Detection

  • Jan 01, 2018
  • Shima Afzali +4
  • Research Article
  • Citations208

Unified Information Fusion Network for Multi-Modal RGB-D and RGB-T Salient Object Detection

  • May 24, 2021
  • IEEE Transactions on Circuits and Systems for Video Technology
  • Wei Gao +5
  • Research Article
  • Citations26

Embedding topological features into convolutional neural network salient object detection

  • Sep 25, 2019
  • Neural Networks
  • Lecheng Zhou +1
  • Research Article
  • Citations298

ECFFNet: Effective and Consistent Feature Fusion Network for RGB-T Salient Object Detection

  • Mar 01, 2022
  • IEEE Transactions on Circuits and Systems for Video Technology
  • Wujie Zhou +4
  • Research Article
  • Citations8

Learning to Reconstruct and Understand Indoor Scenes From Sparse Views.

  • Jan 01, 2020
  • IEEE Transactions on Image Processing
  • Jingyu Yang +7
  • Research Article
  • Citations1

Salient object detection via reciprocal function filter

  • Jul 16, 2019
  • IET Image Processing
  • Wenbing Chen +2
  • Research Article
  • Citations9

A contour self-compensated network for salient object detection

  • Jun 27, 2020
  • The Visual Computer
  • Yanan Wang +2
  • Research Article
  • Citations9

Augmented Semi-Supervised Learning for Salient Object Detection with Edge Computing

  • Jun 01, 2022
  • IEEE Wireless Communications
  • Chengjin Yu +3
  • Research Article
  • Citations3

A Review of Recent Advancements in Appearance-based Object Recognition

  • Jan 01, 2019
  • Procedia Computer Science
  • Gede Putra Kusuma +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.