Abstract | ||
---|---|---|
Environmental monitoring is a critical aspect of marine renewable energy project success. A new system called Unobtrusive Multistatic Serial LiDAR Imager (UMSLI) has been prepared to capture and classify marine life interaction with electrical generation equipment. We present both hardware and software innovations of the UMSLI system. Underwater marine animal imagery has been captured for the first time using red laser diode serial LiDAR, which has advantages over conventional optical cameras in many areas. Moreover, given the scarcity of existing underwater LiDAR data, a shape matching based classification algorithm is proposed which requires few training data. On top of applying shape descriptors, the algorithm also adopts information theoretical learning based affine shape registration, improving point correspondences found by shape descriptors as well as the final similarity measure. Within Florida Atlantic University’s Harbor Branch Oceanographic Institute optical test facility, experimental LiDAR data are collected through the front end of the UMSLI prototype, on which the classification algorithm is validated. |
Year | DOI | Venue |
---|---|---|
2017 | 10.1007/s11042-017-4833-4 | Multimedia Tools Appl. |
Keywords | Field | DocType |
UMSLI, Optical test facility, Shape matching, Similarity measure | Affine transformation,Front and back ends,Computer vision,Test facility,Similarity measure,Computer science,Lidar,Software,Artificial intelligence,Environmental monitoring,Underwater | Journal |
Volume | Issue | ISSN |
76 | 21 | 1380-7501 |
Citations | PageRank | References |
0 | 0.34 | 7 |
Authors | ||
7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Zheng Cao | 1 | 15 | 1.88 |
José C. Principe | 2 | 46 | 5.08 |
Bing Ouyang | 3 | 3 | 2.40 |
Fraser R. Dalgleish | 4 | 1 | 1.03 |
Anni K. Vuorenkoski | 5 | 1 | 1.37 |
Brian Ramos | 6 | 0 | 0.68 |
Alsenas, G. | 7 | 2 | 1.11 |