TY - GEN
T1 - Analyzing Sensor Quantization of Raw Images for Visual Slam
AU - Christie, Olivia
AU - Rego, Joshua
AU - Jayasuriya, Suren
N1 - Funding Information:
Acknowledgements: This work was supported by NSF REU Site CCF-1659871 and ASU’s Fulton Undergraduate Research Initiative (FURI) for O.C., NSF CCF-1909663 for J.R. and S.J., and the SenSIP Center at ASU.
Publisher Copyright:
© 2020 IEEE.
PY - 2020/10
Y1 - 2020/10
N2 - Visual simultaneous localization and mapping (SLAM) is an emerging technology that enables low-power devices with a single camera to perform robotic navigation. However, most visual SLAM algorithms are tuned for images produced through the image sensor processing (ISP) pipeline optimized for highly aesthetic photography. In this paper, we investigate the feasibility of varying sensor quantization on RAW images directly from the sensor to save energy for visual SLAM. In particular, we compare linear and logarithmic image quantization and show visual SLAM is robust to the latter. Further, we introduce a new gradient-based image quantization scheme that outperforms logarithmic quantization's energy savings while preserving accuracy for feature-based visual SLAM algorithms. This work opens a new direction in energy-efficient image sensing for SLAM in the future.
AB - Visual simultaneous localization and mapping (SLAM) is an emerging technology that enables low-power devices with a single camera to perform robotic navigation. However, most visual SLAM algorithms are tuned for images produced through the image sensor processing (ISP) pipeline optimized for highly aesthetic photography. In this paper, we investigate the feasibility of varying sensor quantization on RAW images directly from the sensor to save energy for visual SLAM. In particular, we compare linear and logarithmic image quantization and show visual SLAM is robust to the latter. Further, we introduce a new gradient-based image quantization scheme that outperforms logarithmic quantization's energy savings while preserving accuracy for feature-based visual SLAM algorithms. This work opens a new direction in energy-efficient image sensing for SLAM in the future.
KW - RAW images
KW - Visual SLAM
KW - embedded computer vision
KW - image sensor quantization
UR - http://www.scopus.com/inward/record.url?scp=85098646377&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85098646377&partnerID=8YFLogxK
U2 - 10.1109/ICIP40778.2020.9191352
DO - 10.1109/ICIP40778.2020.9191352
M3 - Conference contribution
AN - SCOPUS:85098646377
T3 - Proceedings - International Conference on Image Processing, ICIP
SP - 246
EP - 250
BT - 2020 IEEE International Conference on Image Processing, ICIP 2020 - Proceedings
PB - IEEE Computer Society
T2 - 2020 IEEE International Conference on Image Processing, ICIP 2020
Y2 - 25 September 2020 through 28 September 2020
ER -