A Model of Dual Fabry-Perot Etalon-Based External-Cavity Tunable Laser Us...
Internal motion within pulsating pure-quartic soliton molecules in a fibe...
Enhanced light emission of germanium light-emitting-diode on 150 mm germa...
The Fabrication of GaN Nanostructures Using Cost-Effective Methods for Ap...
Negative-to-Positive Tunnel Magnetoresistance in van der Waals Fe3GeTe2/C...
Quantum Light Source Based on Semiconductor Quantum Dots: A Review
A High-Reliability RF MEMS Metal-Contact Switch Based on Al-Sc Alloy
Development of a Mode-Locked Fiber Laser Utilizing a Niobium Diselenide S...
Development of Multiple Fano-Resonance-Based All-Dielectric Metastructure...
Traffic Vibration Signal Analysis of DAS Fiber Optic Cables with Differen...
官方微信
友情链接

Transformer Based Binocular Disparity Prediction with Occlusion Predict and Novel Full Connection Layers

2022-11-03

 

Author(s): Liu, Y (Liu, Yi); Xu, XT (Xu, Xintao); Xiang, BJ (Xiang, Bajian); Chen, G (Chen, Gang); Gong, GL (Gong, Guoliang); Lu, HX (Lu, Huaxiang)

Source: SENSORS Volume: 22 Issue: 19 Article Number: 7577 DOI: 10.3390/s22197577 Published: OCT 2022

Abstract: The depth estimation algorithm based on the convolutional neural network has many limitations and defects by constructing matching cost volume to calculate the disparity: using a limited disparity range, the authentic disparity beyond the predetermined range can not be acquired; Besides, the matching process lacks constraints on occlusion and matching uniqueness; Also, as a local feature extractor, a convolutional neural network lacks the ability of global context information perception. Aiming at the problems in the matching method of constructing matching cost volume, we propose a disparity prediction algorithm based on Transformer, which specifically comprises the Swin-SPP module for feature extraction based on Swin Transformer, Transformer disparity matching network based on self-attention and cross-attention mechanism, and occlusion prediction sub-network. In addition, we propose a double skip connection fully connected layer to solve the problems of gradient vanishing and explosion during the training process for the Transformer model, thus further enhancing inference accuracy. The proposed model in this paper achieved an EPE (Absolute error) of 0.57 and 0.61, and a 3PE (Percentage error greater than 3 px) of 1.74% and 1.56% on KITTI 2012 and KITTI 2015 datasets, respectively, with an inference time of 0.46 s and parameters as low as only 2.6 M, showing great advantages compared with other algorithms in various evaluation metrics.

Accession Number: WOS:000867173300001

PubMed ID: 36236675

Author Identifiers:

Author        Web of Science ResearcherID        ORCID Number

刘, 毅         GXN-1792-2022         0000-0003-3056-7713

eISSN: 1424-8220

Full Text: https://www.mdpi.com/1424-8220/22/19/7577



关于我们
下载视频观看
联系方式
通信地址

北京市海淀区清华东路甲35号(林大北路中段) 北京912信箱 (100083)

电话

010-82304210/010-82305052(传真)

E-mail

semi@semi.ac.cn

交通地图
版权所有 中国科学院半导体研究所

备案号:京ICP备05085259-1号 京公网安备110402500052 中国科学院半导体所声明