arXiv subjects

Masanori Onishi

Publications and source records attributed to Masanori Onishi.

4 recordsLinked to original sources

arXiv2026

Highly Detailed and Generalizable Broadleaf Tree Crown Instance Segmentation from UAV Imagery

We present a highly detailed instance segmentation model for delineating individual tree crowns in natural broadleaf forests using aerial imagery acquired by unmanned aerial vehicles (UAVs). Tree crown delineation in broadleaf forests is more challenging than in other forest types due to diversity of crown shapes and the lack of clearly defined treetops. To address this issue, we developed a deep-learning-based crown segmentation model trained on high-quality annotated crown outlines. We manually delineated 18,507 crown polygons from orthomosaic images collected across seven forests in Japan by skilled annotators, and developed a model based on Mask2Former with multiple backbone architectures. The best model achieved high segmentation performance in structurally complex broadleaf forests using only RGB imagery. This performance was maintained when applied to geographically distinct forests within Japan, as well as to biologically distinct tropical rainforests in Borneo. These results demonstrate that using a large number of high-quality annotated datasets is critical for achieving detailed and generalizable crown segmentation across diverse forest ecosystems. The developed model has been integrated into DF Scanner Pro, a software that supports practical forest monitoring using UAVs, and this implementation is expected to enable a wide range of users to analyze tree-level information in broadleaf forest from UAVs.

eess.IV↗

arXiv2018

Automatic classification of trees using a UAV onboard camera and deep learning

Automatic classification of trees using remotely sensed data has been a dream of many scientists and land use managers. Recently, Unmanned aerial vehicles (UAV) has been expected to be an easy-to-use, cost-effective tool for remote sensing of forests, and deep learning has attracted attention for its ability concerning machine vision. In this study, using a commercially available UAV and a publicly available package for deep learning, we constructed a machine vision system for the automatic classification of trees. In our method, we segmented a UAV photography image of forest into individual tree crowns and carried out object-based deep learning. As a result, the system was able to classify 7 tree types at 89.0% accuracy. This performance is notable because we only used basic RGB images from a standard UAV. In contrast, most of previous studies used expensive hardware such as multispectral imagers to improve the performance. This result means that our method has the potential to classify individual trees in a cost-effective manner. This can be a usable tool for many forest researchers and managements.

cs.CV↗

arXiv2017

Identifying 3 moss species by deep learning, using the "chopped picture" method

In general, object identification tends not to work well on ambiguous, amorphous objects such as vegetation. In this study, we developed a simple but effective approach to identify ambiguous objects and applied the method to several moss species. As a result, the model correctly classified test images with accuracy more than 90%. Using this approach will help progress in computer vision studies.

stat.ML↗

arXiv2015

Lifetime and Spectral Evolution of a Magma Ocean with a Steam Atmosphere: Its Detectability by Future Direct Imaging

We present the thermal evolution and emergent spectra of solidifying terrestrial planets along with the formation of steam atmospheres. The lifetime of a magma ocean and its spectra through a steam atmosphere depends on the orbital distance of the planet from the host star. For a type-I planet, which is formed beyond a certain critical distance from the host star, the thermal emission declines on a timescale shorter than approximately $10^6$ years. Therefore, young stars should be targets when searching for molten planets in this orbital region. In contrast, a type-II planet, which is formed inside the critical distance, will emit significant thermal radiation from near-infrared atmospheric windows during the entire lifetime of the magma ocean. The Ks and L bands will be favorable for future direct imaging because the planet-to-star contrasts of these bands are higher than approximately 10$^{-7}$-10$^{-8}$. Our model predicts that, in the type-II orbital region, molten planets would be present over the main sequence of the G-type host star if the initial bulk content of water exceeds approximately 1 wt%. In visible atmospheric windows, the contrasts of the thermal emission drop below $10^{-10}$ in less than $10^5$ years, whereas those of the reflected light remain $10^{-10}$ for both types of planets. Since the contrast level is comparable to those of reflected light from Earth-sized planets in the habitable zone, the visible reflected light from molten planets also provides a promising target for direct imaging with future ground- and space-based telescopes.

astro-ph.EP↗