Mapping with Monocular Camera Sensor under Adversarial Illumination for Intelligent Vehicles

被引:1
|
作者
Tian, Wei [1 ]
Wen, Yongkun [1 ]
Chu, Xinning [1 ]
机构
[1] Tongji Univ, Sch Automot Studies, Shanghai 201804, Peoples R China
基金
国家重点研发计划;
关键词
intelligent vehicle; monocular camera sensor; visual mapping; adversarial illumination; unsupervised keypoint learning; scale drift reduction; VERSATILE; ROBUST;
D O I
10.3390/s23063296
中图分类号
O65 [分析化学];
学科分类号
070302 ; 081704 ;
摘要
High-precision maps are widely applied in intelligent-driving vehicles for localization and planning tasks. The vision sensor, especially monocular cameras, has become favoured in mapping approaches due to its high flexibility and low cost. However, monocular visual mapping suffers from great performance degradation in adversarial illumination environments such as on low-light roads or in underground spaces. To address this issue, in this paper, we first introduce an unsupervised learning approach to improve keypoint detection and description on monocular camera images. By emphasizing the consistency between feature points in the learning loss, visual features in dim environment can be better extracted. Second, to suppress the scale drift in monocular visual mapping, a robust loop-closure detection scheme is presented, which integrates both feature-point verification and multi-grained image similarity measurements. With experiments on public benchmarks, our keypoint detection approach is proven robust against varied illumination. With scenario tests including both underground and on-road driving, we demonstrate that our approach is able to reduce the scale drift in reconstructing the scene and achieve a mapping accuracy gain of up to 0.14 m in textureless or low-illumination environments.
引用
收藏
页数:21
相关论文
共 50 条
  • [21] Camera External Self-Calibration for Intelligent Vehicles
    Yu, Guoqing
    Chen, Jian
    Zhang, Kaixiang
    Zhang, Xinfang
    2019 IEEE 28TH INTERNATIONAL SYMPOSIUM ON INDUSTRIAL ELECTRONICS (ISIE), 2019, : 1688 - 1693
  • [22] Multimedia sensor fusion for intelligent camera control
    Goodridge, SG
    Kay, MG
    MF '96 - 1996 IEEE/SICE/RSJ INTERNATIONAL CONFERENCE ON MULTISENSOR FUSION AND INTEGRATION FOR INTELLIGENT SYSTEMS, 1996, : 655 - 662
  • [23] Tracking Multiple Unmanned Aerial Vehicles on SE(3) Using a Monocular Camera
    Petersen, Mark E.
    Ellingson, Jaron C.
    Beard, Randal W.
    IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS, 2023, 59 (04) : 3726 - 3735
  • [24] Monocular Camera Based Fruit Counting and Mapping With Semantic Data Association
    Liu, Xu
    Chen, Steven W.
    Liu, Chenhao
    Shivakumar, Shreyas S.
    Das, Jnaneshwar
    Taylor, Camillo J.
    Underwood, James
    Kumar, Vijay
    IEEE ROBOTICS AND AUTOMATION LETTERS, 2019, 4 (03) : 2296 - 2303
  • [25] Simulation and emulation of sensor systems for intelligent vehicles
    Ujvari, S
    Eriksson, P
    Moore, P
    Pu, JS
    MECHATRONICS '98, 1998, : 385 - 390
  • [26] The use of smartphones as a smart sensor for intelligent vehicles
    de Carvalho Neto, Geraldo Luciano
    de Lima, Danilo Alves
    Neto, Arthur de Miranda
    PROCEEDINGS OF 13TH LATIN AMERICAN ROBOTICS SYMPOSIUM AND 4TH BRAZILIAN SYMPOSIUM ON ROBOTICS - LARS/SBR 2016, 2016, : 37 - 42
  • [27] A combination of monocular CCD camera and inertial-sensor for range estimation
    Derrouich, S
    Izumida, K
    Shiiya, K
    IECON-2002: PROCEEDINGS OF THE 2002 28TH ANNUAL CONFERENCE OF THE IEEE INDUSTRIAL ELECTRONICS SOCIETY, VOLS 1-4, 2002, : 2191 - 2196
  • [28] Real-Time Lane Detection for Intelligent Vehicles Based on Monocular Vision
    Xu Fangfang
    Wang Bo
    Zhou Zhiqiang
    Zheng Zhihui
    PROCEEDINGS OF THE 31ST CHINESE CONTROL CONFERENCE, 2012, : 7332 - 7337
  • [29] Pose Estimation Based on Monocular Visual Odometry and Lane Detection for Intelligent Vehicles
    Galarza, Juan
    Perez, Esteban
    Serrano, Esteban
    Tapia, Andres
    Aguilar, Wilbert G.
    AUGMENTED REALITY, VIRTUAL REALITY, AND COMPUTER GRAPHICS, AVR 2018, PT II, 2018, 10851 : 562 - 566
  • [30] Detection and recognition method of monocular vision traffic safety information for intelligent vehicles
    Jin, Zhi
    Ge, Dong-Yuan
    JOURNAL OF INTELLIGENT & FUZZY SYSTEMS, 2020, 39 (04) : 5017 - 5026