An Optimized SIFT-OCT Algorithm for Stitching Aerial Images of a Loblolly Pine Plantation
When producing orthomosaic from aerial images of a forested area, challenges arise when the forest canopy is closed, and tie points are hard to find between images. The recent development in deep leaning has shed some light in tackling this problem with an algorithm that examines each image pixel-by...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-09-01
|
| Series: | Forests |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1999-4907/13/9/1475 |
| _version_ | 1797488260316921856 |
|---|---|
| author | Tao Wu I-Kuai Hung Hao Xu Laibang Yang Yongzhong Wang Luming Fang Xiongwei Lou |
| author_facet | Tao Wu I-Kuai Hung Hao Xu Laibang Yang Yongzhong Wang Luming Fang Xiongwei Lou |
| author_sort | Tao Wu |
| collection | DOAJ |
| description | When producing orthomosaic from aerial images of a forested area, challenges arise when the forest canopy is closed, and tie points are hard to find between images. The recent development in deep leaning has shed some light in tackling this problem with an algorithm that examines each image pixel-by-pixel. The scale-invariant feature transform (SIFT) algorithm and its many variants are widely used in feature-based image stitching, which is ideal for orthomosaic production. However, although feature-based image registration can find many feature points in forest image stitching, the similarity between images is too high, resulting in a low correct matching rate and long splicing time. To counter this problem by considering the characteristics of forest images, the inverse cosine function ratio of the unit vector dot product (arccos) is introduced into the SIFT-OCT (SIFT skipping the first scale-space octave) algorithm to overcome the shortfalls of too long a matching time caused by too many feature points for matching. Then, the fast sample consensus (FSC) algorithm was introduced to realize the deletion of mismatched point pairs and improve the matching accuracy. This optimized method was tested on three sets of forest images, representing the forest core, edge, and road areas of a loblolly pine plantation. The same process was repeated by using the regular SIFT and SIFT-OCT algorithms for comparison. The results showed the optimized SIFT-OCT algorithm not only greatly reduced the splicing time, but also increased the correct matching rate. |
| first_indexed | 2024-03-10T00:00:34Z |
| format | Article |
| id | doaj.art-9d8274fee2814aab971bf51e05458f97 |
| institution | Directory Open Access Journal |
| issn | 1999-4907 |
| language | English |
| last_indexed | 2024-03-10T00:00:34Z |
| publishDate | 2022-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Forests |
| spelling | doaj.art-9d8274fee2814aab971bf51e05458f972023-11-23T16:18:07ZengMDPI AGForests1999-49072022-09-01139147510.3390/f13091475An Optimized SIFT-OCT Algorithm for Stitching Aerial Images of a Loblolly Pine PlantationTao Wu0I-Kuai Hung1Hao Xu2Laibang Yang3Yongzhong Wang4Luming Fang5Xiongwei Lou6College of Mathematics and Computer Science, Zhejiang A&F University, Hangzhou 311300, ChinaCollege of Forestry and Agriculture, Stephen F. Austin State University, Nacogdoches, TX 75962, USAZhejiang Forestry Bureau, Hangzhou 310000, ChinaHangzhou Ganzhi Technology Co., Ltd., Hangzhou 310000, ChinaHangzhou Ganzhi Technology Co., Ltd., Hangzhou 310000, ChinaCollege of Mathematics and Computer Science, Zhejiang A&F University, Hangzhou 311300, ChinaCollege of Mathematics and Computer Science, Zhejiang A&F University, Hangzhou 311300, ChinaWhen producing orthomosaic from aerial images of a forested area, challenges arise when the forest canopy is closed, and tie points are hard to find between images. The recent development in deep leaning has shed some light in tackling this problem with an algorithm that examines each image pixel-by-pixel. The scale-invariant feature transform (SIFT) algorithm and its many variants are widely used in feature-based image stitching, which is ideal for orthomosaic production. However, although feature-based image registration can find many feature points in forest image stitching, the similarity between images is too high, resulting in a low correct matching rate and long splicing time. To counter this problem by considering the characteristics of forest images, the inverse cosine function ratio of the unit vector dot product (arccos) is introduced into the SIFT-OCT (SIFT skipping the first scale-space octave) algorithm to overcome the shortfalls of too long a matching time caused by too many feature points for matching. Then, the fast sample consensus (FSC) algorithm was introduced to realize the deletion of mismatched point pairs and improve the matching accuracy. This optimized method was tested on three sets of forest images, representing the forest core, edge, and road areas of a loblolly pine plantation. The same process was repeated by using the regular SIFT and SIFT-OCT algorithms for comparison. The results showed the optimized SIFT-OCT algorithm not only greatly reduced the splicing time, but also increased the correct matching rate.https://www.mdpi.com/1999-4907/13/9/1475feature matchingforest image stitchingSIFT-OCTFSC |
| spellingShingle | Tao Wu I-Kuai Hung Hao Xu Laibang Yang Yongzhong Wang Luming Fang Xiongwei Lou An Optimized SIFT-OCT Algorithm for Stitching Aerial Images of a Loblolly Pine Plantation Forests feature matching forest image stitching SIFT-OCT FSC |
| title | An Optimized SIFT-OCT Algorithm for Stitching Aerial Images of a Loblolly Pine Plantation |
| title_full | An Optimized SIFT-OCT Algorithm for Stitching Aerial Images of a Loblolly Pine Plantation |
| title_fullStr | An Optimized SIFT-OCT Algorithm for Stitching Aerial Images of a Loblolly Pine Plantation |
| title_full_unstemmed | An Optimized SIFT-OCT Algorithm for Stitching Aerial Images of a Loblolly Pine Plantation |
| title_short | An Optimized SIFT-OCT Algorithm for Stitching Aerial Images of a Loblolly Pine Plantation |
| title_sort | optimized sift oct algorithm for stitching aerial images of a loblolly pine plantation |
| topic | feature matching forest image stitching SIFT-OCT FSC |
| url | https://www.mdpi.com/1999-4907/13/9/1475 |
| work_keys_str_mv | AT taowu anoptimizedsiftoctalgorithmforstitchingaerialimagesofaloblollypineplantation AT ikuaihung anoptimizedsiftoctalgorithmforstitchingaerialimagesofaloblollypineplantation AT haoxu anoptimizedsiftoctalgorithmforstitchingaerialimagesofaloblollypineplantation AT laibangyang anoptimizedsiftoctalgorithmforstitchingaerialimagesofaloblollypineplantation AT yongzhongwang anoptimizedsiftoctalgorithmforstitchingaerialimagesofaloblollypineplantation AT lumingfang anoptimizedsiftoctalgorithmforstitchingaerialimagesofaloblollypineplantation AT xiongweilou anoptimizedsiftoctalgorithmforstitchingaerialimagesofaloblollypineplantation AT taowu optimizedsiftoctalgorithmforstitchingaerialimagesofaloblollypineplantation AT ikuaihung optimizedsiftoctalgorithmforstitchingaerialimagesofaloblollypineplantation AT haoxu optimizedsiftoctalgorithmforstitchingaerialimagesofaloblollypineplantation AT laibangyang optimizedsiftoctalgorithmforstitchingaerialimagesofaloblollypineplantation AT yongzhongwang optimizedsiftoctalgorithmforstitchingaerialimagesofaloblollypineplantation AT lumingfang optimizedsiftoctalgorithmforstitchingaerialimagesofaloblollypineplantation AT xiongweilou optimizedsiftoctalgorithmforstitchingaerialimagesofaloblollypineplantation |