STEREOVISION MOBILE MAPPING: SYSTEM DESIGN AND PERFORMANCE EVALUATION

Image-based mobile mapping systems enable the efficient acquisition of georeferenced image sequences, which can later be exploited in cloud-based 3D geoinformation services. In order to provide a 360° coverage with accurate 3D measuring capabilities, we present a novel 360° stereo panoramic camera configuration. By using two 360° panorama cameras tilted forward and backward in combination with conventional forward and backward looking stereo camera systems, we achieve a full 360° multi-stereo coverage. We furthermore developed a fully operational new mobile mapping system based on our proposed approach, which fulfils our high accuracy requirements. We successfully implemented a rigorous sensor and system calibration procedure, which allows calibrating all stereo systems with a superior accuracy compared to that of previous work. Our study delivered absolute 3D point accuracies in the range of 4 to 6 cm and relative accuracies of 3D distances in the range of 1 to 3 cm. These results were achieved in a challenging urban area. Furthermore, we automatically reconstructed a 3D city model of our study area by employing all captured and georeferenced mobile mapping imagery. The result is a very high detailed and almost complete 3D city model of the street environment.

Download Full-text

PORTABLE IMAGE-BASED HIGH PERFORMANCE MOBILE MAPPING SYSTEM IN UNDERGROUND ENVIRONMENTS – SYSTEM CONFIGURATION AND PERFORMANCE EVALUATION

ISPRS Annals of Photogrammetry Remote Sensing and Spatial Information Sciences ◽

10.5194/isprs-annals-iv-2-w5-255-2019 ◽

2019 ◽

Vol IV-2/W5 ◽

pp. 255-262

Author(s):

S. Blaser ◽

S. Nebiker ◽

D. Wisler

Keyword(s):

High Performance ◽

Life Cycle Management ◽

Measurement Unit ◽

Indoor Environments ◽

Mobile Mapping ◽

Mapping System ◽

Order Of Magnitude ◽

Mobile Mapping System ◽

And Performance ◽

Measurement Campaigns

<p><strong>Abstract.</strong> The progression in urbanization increases the need for different types of underground infrastructure. Consequently, infrastructure and life cycle management are rapidly gaining in importance. Mobile reality capturing systems and cloud-based services exploiting georeferenced metric 3D imagery are already extensively used for infrastructure management in outdoor environments. These services minimise dangerous and expensive field visits or measurement campaigns. In this paper, we introduce the BIMAGE Backpack, a portable image-based mobile mapping system for 3D data acquisition in indoor environments. The system consists of a multi-head panorama camera, two multi-profile laser scanners and an inertial measurement unit. With this system, we carried out underground measurement campaigns in the Hagerbach Test Gallery, located in Flums Hochwiese, Switzerland. For our performance evaluations in two different tunnel sections, we employed LiDAR SLAM as well as advanced image-based georeferencing. The obtained absolute accuracies were in the range from 6.2 to 7.4&thinsp;cm. The relative accuracy, which for many applications is even more important, was in the range of 2&ndash;6&thinsp;mm. These figures demonstrate an accuracy improvement of the subsequent image-based georeferencing over LiDAR SLAM by about an order of magnitude. The investigations show the application potential of image-based portable mobile mapping systems for infrastructure inventory and management in large underground facilities.</p>

Download Full-text

VERIFICATION OF THE RELATIONSHIP BETWEEN ADJUSTMENT EFFECT BY THE GROUND CONTROL POINT AND DRIVING SPEED OF MOBILE MAPPING SYSTEM

Journal of Japan Society of Civil Engineers Ser F3 (Civil Engineering Informatics) ◽

10.2208/jscejcei.72.ii_31 ◽

2016 ◽

Vol 72 (2) ◽

pp. II_31-II_39

Author(s):

Naoki OKAMOTO ◽

Tatsunori SADA ◽

Hisashi EMORI

Keyword(s):

Control Point ◽

Ground Control ◽

Mobile Mapping ◽

Ground Control Point ◽

Driving Speed ◽

Mapping System ◽

Mobile Mapping System ◽

The Relationship

Download Full-text

UAV-based Multi-cell HAPS Communication: System Design and Performance Evaluation

GLOBECOM 2020 - 2020 IEEE Global Communications Conference ◽

10.1109/globecom42002.2020.9322476 ◽

2020 ◽

Author(s):

Frank Hsieh ◽

Fanny Jardel ◽

Eugene Visotsky ◽

Frederick Vook ◽

Amitava Ghosh ◽

...

Keyword(s):

Performance Evaluation ◽

System Design ◽

Communication System ◽

Communication System Design ◽

And Performance

Download Full-text

Deep Learning Based Pavement Inspection Using Self-Reconfigurable Robot

Sensors ◽

10.3390/s21082595 ◽

2021 ◽

Vol 21 (8) ◽

pp. 2595

Author(s):

Balakrishnan Ramalingam ◽

Abdullah Aamir Hayat ◽

Mohan Rajesh Elara ◽

Braulio Félix Gómez ◽

Lim Yi ◽

...

Keyword(s):

Deep Learning ◽

Semantic Segmentation ◽

High Accuracy ◽

Experimental Results ◽

Mobile Mapping ◽

Mapping System ◽

Mobile Mapping System ◽

Reconfigurable Robot ◽

Nvidia Gpu ◽

Inspection Task

The pavement inspection task, which mainly includes crack and garbage detection, is essential and carried out frequently. The human-based or dedicated system approach for inspection can be easily carried out by integrating with the pavement sweeping machines. This work proposes a deep learning-based pavement inspection framework for self-reconfigurable robot named Panthera. Semantic segmentation framework SegNet was adopted to segment the pavement region from other objects. Deep Convolutional Neural Network (DCNN) based object detection is used to detect and localize pavement defects and garbage. Furthermore, Mobile Mapping System (MMS) was adopted for the geotagging of the defects. The proposed system was implemented and tested with the Panthera robot having NVIDIA GPU cards. The experimental results showed that the proposed technique identifies the pavement defects and litters or garbage detection with high accuracy. The experimental results on the crack and garbage detection are presented. It is found that the proposed technique is suitable for deployment in real-time for garbage detection and, eventually, sweeping or cleaning tasks.

Download Full-text