Predicting depth from single RGB images with pyramidal three-streamed networks

14Citations
Citations of this article
10Readers
Mendeley users who have this article in their library.

Abstract

Predicting depth from a monocular image is an ill-posed and inherently ambiguous issue in computer vision. In this paper, we propose a pyramidal third-streamed network (PTSN) that recovers the depth information using a single given RGB image. PTSN uses pyramidal structure images, which can extract multiresolution features to improve the robustness of the network as the network input. The full connection layer is changed into fully convolutional layers with a new upconvolution structure, which reduces the network parameters and computational complexity. We propose a new loss function including scale-invariant, horizontal and vertical gradient loss that not only helps predict the depth values, but also clearly obtains local contours. We evaluate PTSN on the NYU Depth v2 dataset and the experimental results show that our depth predictions have better accuracy than competing methods.

References Powered by Scopus

Deep residual learning for image recognition

174051Citations
N/AReaders
Get full text

ImageNet Large Scale Visual Recognition Challenge

30411Citations
N/AReaders
Get full text

Delving deep into rectifiers: Surpassing human-level performance on imagenet classification

15452Citations
N/AReaders
Get full text

Cited by Powered by Scopus

Automated machine learning for high‐throughput image‐based plant phenotyping

68Citations
N/AReaders
Get full text

YOLOv3-Litchi Detection Method of Densely Distributed Litchi in Large Vision Scenes

40Citations
N/AReaders
Get full text

Cherry detection algorithm based on improved YOLOv5s network

14Citations
N/AReaders
Get full text

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Cite

CITATION STYLE

APA

Chen, S., Tang, M., & Kan, J. (2019). Predicting depth from single RGB images with pyramidal three-streamed networks. Sensors (Switzerland), 19(3). https://doi.org/10.3390/s19030667

Readers over time

‘19‘20‘22‘23‘2402468

Readers' Seniority

Tooltip

Lecturer / Post doc 2

67%

PhD / Post grad / Masters / Doc 1

33%

Readers' Discipline

Tooltip

Computer Science 2

67%

Earth and Planetary Sciences 1

33%

Article Metrics

Tooltip
Mentions
Blog Mentions: 1

Save time finding and organizing research with Mendeley

Sign up for free
0