Abstract
Construction of 3D topographic maps from stereo or monocular video, over coverage areas of kilometer scale, taken by low-altitude airborne platforms is addressed. Two computational frameworks for these two cases are considered, accommodating the online processing of video along the path. In these formulations, stereo disparity information enables the computation of 3D motions and depth maps to be done more readily, however, monocular motion cues provide similar accuracy with more computational steps. The critical issue is to overcome the drift error, which is inherent of the causal frame-to frame motion estimation, as the video frames are acquired. A novel global alignment scheme is proposed, aimed at determining the 3D trajectory most consistent with the estimated 3D motions between pairs of nearby positions. Performance is demonstrated based on experiment with a sequence of 5000 stereo pairs, simulating aerial photographic data from an airborne platform flying at 110 m above (the reference plane of) a 1 km /spl times/ 1 km terrain with 5-65m elevation. Maximum geo-referenced positioning accuracy is roughly 2 m, with elevation error of 1 m or less over 95% of the terrain.
| Original language | English (US) |
|---|---|
| Title of host publication | Proceedings - IEEE Conference on Advanced Video and Signal Based Surveillance, AVSS 2003 |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| Pages | 305-312 |
| Number of pages | 8 |
| ISBN (Print) | 0769519717, 9780769519715 |
| DOIs | |
| State | Published - 2003 |
| Event | IEEE Conference on Advanced Video and Signal Based Surveillance, AVSS 2003 - Miami, United States Duration: Jul 21 2003 → Jul 22 2003 |
Other
| Other | IEEE Conference on Advanced Video and Signal Based Surveillance, AVSS 2003 |
|---|---|
| Country | United States |
| City | Miami |
| Period | 7/21/03 → 7/22/03 |
Fingerprint
Keywords
- Layout
- Mobile robots
- Motion estimation
- Navigation
- Reconnaissance
- Remotely operated vehicles
- Surveillance
- Terrain mapping
- Three dimensional displays
- Unmanned aerial vehicles
ASJC Scopus subject areas
- Computer Networks and Communications
- Signal Processing
Cite this
Vision-based positioning and terrain mapping by global alignment for UAVs. / Madjidi, H.; Negahdaripour, Shahriar; Bandari, E.
Proceedings - IEEE Conference on Advanced Video and Signal Based Surveillance, AVSS 2003. Institute of Electrical and Electronics Engineers Inc., 2003. p. 305-312 1217936.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Vision-based positioning and terrain mapping by global alignment for UAVs
AU - Madjidi, H.
AU - Negahdaripour, Shahriar
AU - Bandari, E.
PY - 2003
Y1 - 2003
N2 - Construction of 3D topographic maps from stereo or monocular video, over coverage areas of kilometer scale, taken by low-altitude airborne platforms is addressed. Two computational frameworks for these two cases are considered, accommodating the online processing of video along the path. In these formulations, stereo disparity information enables the computation of 3D motions and depth maps to be done more readily, however, monocular motion cues provide similar accuracy with more computational steps. The critical issue is to overcome the drift error, which is inherent of the causal frame-to frame motion estimation, as the video frames are acquired. A novel global alignment scheme is proposed, aimed at determining the 3D trajectory most consistent with the estimated 3D motions between pairs of nearby positions. Performance is demonstrated based on experiment with a sequence of 5000 stereo pairs, simulating aerial photographic data from an airborne platform flying at 110 m above (the reference plane of) a 1 km /spl times/ 1 km terrain with 5-65m elevation. Maximum geo-referenced positioning accuracy is roughly 2 m, with elevation error of 1 m or less over 95% of the terrain.
AB - Construction of 3D topographic maps from stereo or monocular video, over coverage areas of kilometer scale, taken by low-altitude airborne platforms is addressed. Two computational frameworks for these two cases are considered, accommodating the online processing of video along the path. In these formulations, stereo disparity information enables the computation of 3D motions and depth maps to be done more readily, however, monocular motion cues provide similar accuracy with more computational steps. The critical issue is to overcome the drift error, which is inherent of the causal frame-to frame motion estimation, as the video frames are acquired. A novel global alignment scheme is proposed, aimed at determining the 3D trajectory most consistent with the estimated 3D motions between pairs of nearby positions. Performance is demonstrated based on experiment with a sequence of 5000 stereo pairs, simulating aerial photographic data from an airborne platform flying at 110 m above (the reference plane of) a 1 km /spl times/ 1 km terrain with 5-65m elevation. Maximum geo-referenced positioning accuracy is roughly 2 m, with elevation error of 1 m or less over 95% of the terrain.
KW - Layout
KW - Mobile robots
KW - Motion estimation
KW - Navigation
KW - Reconnaissance
KW - Remotely operated vehicles
KW - Surveillance
KW - Terrain mapping
KW - Three dimensional displays
KW - Unmanned aerial vehicles
UR - http://www.scopus.com/inward/record.url?scp=29844439627&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=29844439627&partnerID=8YFLogxK
U2 - 10.1109/AVSS.2003.1217936
DO - 10.1109/AVSS.2003.1217936
M3 - Conference contribution
AN - SCOPUS:29844439627
SN - 0769519717
SN - 9780769519715
SP - 305
EP - 312
BT - Proceedings - IEEE Conference on Advanced Video and Signal Based Surveillance, AVSS 2003
PB - Institute of Electrical and Electronics Engineers Inc.
ER -