3D change detection using low cost aerial imagery

Aravindhan K. Krishnan, Srikanth Saripalli, Edwin Nissen, Ramon Arrowsmith

Research output: Chapter in Book/Report/Conference proceedingConference contribution

  • 3 Citations

Abstract

We present a method to register point clouds obtained from aerial images through Structure from motion (SFM) techniques with data from airborne LiDAR systems. The data was obtained by the United States Geological Survey (USGS) over a 800 sq km stretch in California using airborne LiDAR. The images were obtained by a downward looking camera on an autonomous helicopter along the San Andreas fault [9]. A 3D point cloud is built by fusing GPS information with the aerial images. Our approach to detect changes is to compare the LiDAR data with 3D point cloud derived from aerial images. This comparison necessitates the two point clouds to be in the same co-ordinate frame. We adopt a registration approach to bring the point clouds to the same co-ordinate frame. We highlight the challenges involved in registering aerial point clouds and propose a semi automated way for registration. We also present a simulation of a change detection scenario by introducing displacement fields in the source point cloud and obtaining a target point cloud by additionally simulating the GPS offsets. We recover the displacement vectors in two steps (1) globally registering the source and target point clouds using the method described in this paper (2) using our change detection module [5] for computing the displacement fields. We present results for global registration and change detection.

LanguageEnglish (US)
Title of host publication2012 IEEE International Symposium on Safety, Security, and Rescue Robotics, SSRR 2012
DOIs
StatePublished - 2012
Event2012 IEEE International Symposium on Safety, Security, and Rescue Robotics, SSRR 2012 - College Station, TX, United States
Duration: Nov 5 2012Nov 8 2012

Other

Other2012 IEEE International Symposium on Safety, Security, and Rescue Robotics, SSRR 2012
CountryUnited States
CityCollege Station, TX
Period11/5/1211/8/12

Fingerprint

Antennas
Global positioning system
Costs
Geological surveys
Helicopters
Cameras

Keywords

  • change detection
  • ICP
  • Registration

ASJC Scopus subject areas

  • Artificial Intelligence
  • Human-Computer Interaction
  • Safety, Risk, Reliability and Quality

Cite this

Krishnan, A. K., Saripalli, S., Nissen, E., & Arrowsmith, R. (2012). 3D change detection using low cost aerial imagery. In 2012 IEEE International Symposium on Safety, Security, and Rescue Robotics, SSRR 2012 [6523892] https://doi.org/10.1109/SSRR.2012.6523892

3D change detection using low cost aerial imagery. / Krishnan, Aravindhan K.; Saripalli, Srikanth; Nissen, Edwin; Arrowsmith, Ramon.

2012 IEEE International Symposium on Safety, Security, and Rescue Robotics, SSRR 2012. 2012. 6523892.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Krishnan, AK, Saripalli, S, Nissen, E & Arrowsmith, R 2012, 3D change detection using low cost aerial imagery. in 2012 IEEE International Symposium on Safety, Security, and Rescue Robotics, SSRR 2012., 6523892, 2012 IEEE International Symposium on Safety, Security, and Rescue Robotics, SSRR 2012, College Station, TX, United States, 11/5/12. https://doi.org/10.1109/SSRR.2012.6523892
Krishnan AK, Saripalli S, Nissen E, Arrowsmith R. 3D change detection using low cost aerial imagery. In 2012 IEEE International Symposium on Safety, Security, and Rescue Robotics, SSRR 2012. 2012. 6523892 https://doi.org/10.1109/SSRR.2012.6523892
Krishnan, Aravindhan K. ; Saripalli, Srikanth ; Nissen, Edwin ; Arrowsmith, Ramon. / 3D change detection using low cost aerial imagery. 2012 IEEE International Symposium on Safety, Security, and Rescue Robotics, SSRR 2012. 2012.
@inproceedings{52374b2580dc456e81d62c8c23a47885,
title = "3D change detection using low cost aerial imagery",
abstract = "We present a method to register point clouds obtained from aerial images through Structure from motion (SFM) techniques with data from airborne LiDAR systems. The data was obtained by the United States Geological Survey (USGS) over a 800 sq km stretch in California using airborne LiDAR. The images were obtained by a downward looking camera on an autonomous helicopter along the San Andreas fault [9]. A 3D point cloud is built by fusing GPS information with the aerial images. Our approach to detect changes is to compare the LiDAR data with 3D point cloud derived from aerial images. This comparison necessitates the two point clouds to be in the same co-ordinate frame. We adopt a registration approach to bring the point clouds to the same co-ordinate frame. We highlight the challenges involved in registering aerial point clouds and propose a semi automated way for registration. We also present a simulation of a change detection scenario by introducing displacement fields in the source point cloud and obtaining a target point cloud by additionally simulating the GPS offsets. We recover the displacement vectors in two steps (1) globally registering the source and target point clouds using the method described in this paper (2) using our change detection module [5] for computing the displacement fields. We present results for global registration and change detection.",
keywords = "change detection, ICP, Registration",
author = "Krishnan, {Aravindhan K.} and Srikanth Saripalli and Edwin Nissen and Ramon Arrowsmith",
year = "2012",
doi = "10.1109/SSRR.2012.6523892",
language = "English (US)",
isbn = "9781479901654",
booktitle = "2012 IEEE International Symposium on Safety, Security, and Rescue Robotics, SSRR 2012",

}

TY - GEN

T1 - 3D change detection using low cost aerial imagery

AU - Krishnan, Aravindhan K.

AU - Saripalli, Srikanth

AU - Nissen, Edwin

AU - Arrowsmith, Ramon

PY - 2012

Y1 - 2012

N2 - We present a method to register point clouds obtained from aerial images through Structure from motion (SFM) techniques with data from airborne LiDAR systems. The data was obtained by the United States Geological Survey (USGS) over a 800 sq km stretch in California using airborne LiDAR. The images were obtained by a downward looking camera on an autonomous helicopter along the San Andreas fault [9]. A 3D point cloud is built by fusing GPS information with the aerial images. Our approach to detect changes is to compare the LiDAR data with 3D point cloud derived from aerial images. This comparison necessitates the two point clouds to be in the same co-ordinate frame. We adopt a registration approach to bring the point clouds to the same co-ordinate frame. We highlight the challenges involved in registering aerial point clouds and propose a semi automated way for registration. We also present a simulation of a change detection scenario by introducing displacement fields in the source point cloud and obtaining a target point cloud by additionally simulating the GPS offsets. We recover the displacement vectors in two steps (1) globally registering the source and target point clouds using the method described in this paper (2) using our change detection module [5] for computing the displacement fields. We present results for global registration and change detection.

AB - We present a method to register point clouds obtained from aerial images through Structure from motion (SFM) techniques with data from airborne LiDAR systems. The data was obtained by the United States Geological Survey (USGS) over a 800 sq km stretch in California using airborne LiDAR. The images were obtained by a downward looking camera on an autonomous helicopter along the San Andreas fault [9]. A 3D point cloud is built by fusing GPS information with the aerial images. Our approach to detect changes is to compare the LiDAR data with 3D point cloud derived from aerial images. This comparison necessitates the two point clouds to be in the same co-ordinate frame. We adopt a registration approach to bring the point clouds to the same co-ordinate frame. We highlight the challenges involved in registering aerial point clouds and propose a semi automated way for registration. We also present a simulation of a change detection scenario by introducing displacement fields in the source point cloud and obtaining a target point cloud by additionally simulating the GPS offsets. We recover the displacement vectors in two steps (1) globally registering the source and target point clouds using the method described in this paper (2) using our change detection module [5] for computing the displacement fields. We present results for global registration and change detection.

KW - change detection

KW - ICP

KW - Registration

UR - http://www.scopus.com/inward/record.url?scp=84879584049&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84879584049&partnerID=8YFLogxK

U2 - 10.1109/SSRR.2012.6523892

DO - 10.1109/SSRR.2012.6523892

M3 - Conference contribution

SN - 9781479901654

BT - 2012 IEEE International Symposium on Safety, Security, and Rescue Robotics, SSRR 2012

ER -