A dedicated lightweight binocular stereo system for real-time depth-map generation

被引:0
|
作者
Gee, Trevor [1 ]
Delmas, Patrice [1 ]
Joly, Sylvain [2 ]
Baron, Valentin [3 ]
Ababou, Rachel [4 ]
Nezan, Jean-Francois [2 ]
机构
[1] Univ Auckland, Auckland, New Zealand
[2] INSA Rennes, Rennes, France
[3] ENSE3 Grenoble, Grenoble, France
[4] Ecole Mil ST CYR Coetquiden, Guer, France
关键词
VISION;
D O I
暂无
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
This work describes a light weight dedicated system, capable of generating a sequence of depth-maps computed from image streams acquired from a synchronized pair of GoPro HERO 3+ cameras in real-time. The envisioned purpose is to capture depth-maps from mid-sized drones for computer vision applications (e.g. surveillance and management of ecosystems). The implementation is of modular design, consisting of a dedicated camera synchronisation box, fast lookup based rectification system, a block matching based dense correspondence finder that uses dynamic programming, and a simple disparity-to-depth conversion module. The final output is transmitted to a server via WIFIor G4 LTE cellular Internet connection for further processing. The complete pipeline is implemented on an Android tablet. The main novelty is the system's ability to operate on small portable devices while retaining reasonable quality and real-time performance for outdoor applications. Our experimental results in estuary, forestry and dairy farming environment support this claim.
引用
收藏
页码:215 / 221
页数:7
相关论文
共 50 条
  • [21] Efficient ASIC implementation of a real-time depth mapping stereo vision system
    Kuhn, M
    Moser, S
    Isler, O
    Gürkaynak, FK
    Burg, A
    Felber, N
    Kaeslin, H
    Fichtner, W
    Proceedings of the 46th IEEE International Midwest Symposium on Circuits & Systems, Vols 1-3, 2003, : 1478 - 1481
  • [22] Real-time dense map fusion for stereo SLAM
    Pire, Taihu
    Baravalle, Rodrigo
    D'Alessandro, Ariel
    Civera, Javier
    ROBOTICA, 2018, 36 (10) : 1510 - 1526
  • [23] Depth-Map Merging for Multi-View Stereo with High Resolution Images
    Shen, Shuhan
    2012 21ST INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR 2012), 2012, : 788 - 791
  • [24] Real-Time Stereo Matching System
    Zhu, Angfan
    Cao, Zhiguo
    Xiao, Yang
    INTELLIGENT ROBOTICS AND APPLICATIONS (ICIRA 2018), PT II, 2018, 10985 : 377 - 386
  • [25] Real-time binocular visual localization system based on the improved BGNet stereo matching framework
    Qu, Zanxi
    Li, Li
    Jin, Weiqi
    Yang, Ye
    JOURNAL OF THE OPTICAL SOCIETY OF AMERICA A-OPTICS IMAGE SCIENCE AND VISION, 2024, 41 (03) : 500 - 509
  • [26] Lightweight real-time stereo matching algorithm for AI chips
    Liu, Yi
    Wang, Wenhao
    Xu, Xintao
    Guo, Xiaozhou
    Gong, Guoliang
    Lu, Huaxiang
    COMPUTER COMMUNICATIONS, 2023, 199 : 210 - 217
  • [27] Depth-Guided Aggregation for Real-Time Binocular Depth Estimation Network
    Fu, Dongxin
    Zheng, Shaowu
    Xie, Pengcheng
    Li, Weihua
    IEEE MULTIMEDIA, 2024, 31 (02) : 36 - 47
  • [28] Real-time Depth Map Generation Using Hybrid Multi-view Cameras
    Song, Yunseok
    Shin, Dong-Won
    Ko, Eunsang
    Ho, Yo-Sung
    2014 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA), 2014,
  • [29] Real-Time Action Recognition System for Elderly People Using Stereo Depth Camera
    Zin, Thi Thi
    Htet, Ye
    Akagi, Yuya
    Tamura, Hiroki
    Kondo, Kazuhiro
    Araki, Sanae
    Chosa, Etsuo
    SENSORS, 2021, 21 (17)
  • [30] A Residual Network and FPGA Based Real-Time Depth Map Enhancement System
    Li, Zhenni
    Sun, Haoyi
    Gao, Yuliang
    Wang, Jiao
    ENTROPY, 2021, 23 (05)