• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.43 no.1
• /
• pp.16-25
• /
• 2020

Vegetation segmentation in a field color image is a process of distinguishing vegetation objects of interests like crops and weeds from a background of soil and/or other residues. The performance of the process is crucial in automatic precision agriculture which includes weed control and crop status monitoring. To facilitate the segmentation, color indices have predominantly been used to transform the color image into its gray-scale image. A thresholding technique like the Otsu method is then applied to distinguish vegetation parts from the background. An obvious demerit of the thresholding based segmentation will be that classification of each pixel into vegetation or background is carried out solely by using the color feature of the pixel itself without taking into account color features of its neighboring pixels. This paper presents a new pixel-based segmentation method which employs a multi-layer perceptron neural network to classify the gray-scale image into vegetation and nonvegetation pixels. The input data of the neural network for each pixel are 2-dimensional gray-level values surrounding the pixel. To generate a gray-scale image from a raw RGB color image, a well-known color index called Excess Green minus Excess Red Index was used. Experimental results using 80 field images of 4 vegetation species demonstrate the superiority of the neural network to existing threshold-based segmentation methods in terms of accuracy, precision, recall, and harmonic mean.

• Proceedings of the KSRS Conference
• /
• 1998.09a
• /
• pp.218-224
• /
• 1998

The coefficients of variation obtained from three typical vegetation indices of eight levels of multi-spatial resolution images in urban areas were employed to identify the optimum spatial resolution in terms of maintaining information quality. These multi-spatial resolution images were prepared by degrading 1 meter simulated, 16 meter ADEOS/AVNIR, and 30 meter Landsat-TM images. Normalized Difference Vegetation Index (NDVI), Perpendicular Vegetation Index (PVI) and Soil Adjusted Ratio Vegetation Index (SARVI) were applied to reduce data redundancy and compare the characteristics of multi-spatial resolution image of vegetation indices. The threshold point on the curve of the coefficient of variation was defined as the optimum resolution level for the analysis with multi-spatial resolution image sets. Also, the results from the image segmentation approach of region growing to extract man-made features were compared with these multi-spatial resolution image sets.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.153-155
• /
• 2003

Laser scanning has become a viable technique for the collection of a large amount of accurate 3D point data densely distributed on the scanned object surface. The inherent 3D nature of the sub-randomly distributed point cloud provides abundant spatial information. To explore valuable spatial information from laser scanned data becomes an active research topic, for instance extracting digital elevation model, building models, and vegetation volumes. The sub-randomly distributed point cloud should be segmented and classified before the extraction of spatial information. This paper investigates some exist segmentation methods, and then proposes an octree-based split-and-merge segmentation method to divide lidar data into clusters belonging to 3D planes. Therefore, the classification of lidar data can be performed based on the derived attributes of extracted 3D planes. The test results of both ground and airborne lidar data show the potential of applying this method to extract spatial features from lidar data.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.2
• /
• pp.99-110
• /
• 2023

In this paper, we propose a system termed ForestLi that can accurately estimate the diameter at breast height (DBH) and tree height using LiDAR point cloud data. The ForestLi system processes LiDAR point cloud data through the following steps: downsampling, outlier removal, ground segmentation, ground height normalization, stem extraction, individual tree segmentation, and DBH and tree height measurement. A commercial system, such as LiDAR360, for processing LiDAR point cloud data requires the user to directly correct errors in lower vegetation and individual tree segmentation. In contrast, the ForestLi system can automatically remove LiDAR point cloud data that correspond to lower vegetation in order to improve the accuracy of estimating DBH and tree height. This enables the ForestLi system to reduce the total processing time as well as enhance the accuracy of accuracy of measuring DBH and tree height compared to the LiDAR360 system. We performed an empirical study to confirm that the ForestLi system outperforms the LiDAR360 system in terms of the total processing time and accuracy of measuring DBH and tree height.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.26 no.6
• /
• pp.85-96
• /
• 2023

This study proposes a method for forest vegetation monitoring using high-resolution aerial imagery captured by unmanned aerial vehicles(UAV) and deep learning technology. The research site was selected in the forested area of Mountain Dogo, Asan City, Chungcheongnam-do, and the target species for monitoring included Pinus densiflora, Quercus mongolica, and Quercus acutissima. To classify vegetation species at the pixel level in UAV imagery based on characteristics such as leaf shape, size, and color, the study employed the semantic segmentation method using the prominent U-net deep learning model. The research results indicated that it was possible to visually distinguish Pinus densiflora Siebold & Zucc, Quercus mongolica Fisch. ex Ledeb, and Quercus acutissima Carruth in 135 aerial images captured by UAV. Out of these, 104 images were used as training data for the deep learning model, while 31 images were used for inference. The optimization of the deep learning model resulted in an overall average pixel accuracy of 92.60, with mIoU at 0.80 and FIoU at 0.82, demonstrating the successful construction of a reliable deep learning model. This study is significant as a pilot case for the application of UAV and deep learning to monitor and manage representative species among climate-vulnerable vegetation, including Pinus densiflora, Quercus mongolica, and Quercus acutissima. It is expected that in the future, UAV and deep learning models can be applied to a variety of vegetation species to better address forest management.

• Journal of Advanced Navigation Technology
• /
• v.28 no.2
• /
• pp.238-245
• /
• 2024

In this paper, we propose a framework for improving the performance of semantic segmentation of agricultural multispectral image using feature fusion techniques. Most of the semantic segmentation models being studied in the field of smart farms are trained on RGB images and focus on increasing the depth and complexity of the model to improve performance. In this study, we go beyond the conventional approach and optimize and design a model with multispectral and attention mechanisms. The proposed method fuses features from multiple channels collected from a UAV along with a single RGB image to increase feature extraction performance and recognize complementary features to increase the learning effect. We study the model structure to focus on feature fusion and compare its performance with other models by experimenting with favorable channels and combinations for crop images. The experimental results show that the model combining RGB and NDVI performs better than combinations with other channels.

• Korean Journal of Remote Sensing
• /
• v.39 no.2
• /
• pp.223-232
• /
• 2023

A widely used method for monitoring land cover using high-resolution satellite images is to classify the images based on the colors of the objects of interest. In urban areas, not only major objects such as buildings and roads but also vegetation such as trees frequently appear in high-resolution satellite images. However, the colors of vegetation objects often resemble those of other objects such as buildings, roads, and shadows, making it difficult to accurately classify objects based solely on color information. In this study, we propose a method that can accurately classify not only objects with various colors such as buildings but also vegetation objects. The proposed method uses the normalized difference vegetation index (NDVI) image, which is useful for detecting vegetation objects, along with the RGB image and classifies objects into subclasses. The subclass classification results are fused, and the final classification result is generated by combining them with the image segmentation results. In experiments using Compact Advanced Satellite 500-1 imagery, the proposed method, which applies the NDVI and subclass classification together, showed an overall accuracy of 87.42%, while the overall accuracy of the subchannel classification technique without using the NDVI and the subclass classification technique alone were 73.18% and 81.79%, respectively.

• Journal of Environmental Impact Assessment
• /
• v.18 no.6
• /
• pp.387-392
• /
• 2009

As Our society's environmental awareness and concern the significant increases, the importance of the legal system for environmental conservation such as the Prior Environmental Review System, Environmental Impact Assessment is growing increasingly. but, still critical issues are present such as reliability. Though there could be various causes such as the system or procedures etc. Above all, basically the environmental data problem is the critical cause. Therefore, this study was trying to improve the environmental data accuracy using the high-resolution color aerial photography, LiDAR data and Object Oriented Classification method. And in this study, classification based on coverage percentage of a particular species was attempted through the multi-resolution segmentation and multi-level classification method. The classification result was verified by comparison with 11 points local survey data. All 11 points were classified correctly. And even though the exact coverage percentage of the particular species did not be measured, It was confirmed that the species was occupied similar portion. It is important that the environmental data which can be used for the conservation value assessment could be acquired.

• Korean Journal of Remote Sensing
• /
• v.16 no.1
• /
• pp.1-11
• /
• 2000

Multi-temporal data have been used frequently for analyzing dynamic characteristics of ecological environment. Little research, however, shows the characteristics and problems of the analysis of continental- or global-scale, multi-temporal satellite data. This research investigated the characteristics of large-area, multi-temporal data analysis and the problems of phenological difference of ground vegetation and scarcity of training data for a long term period. This research suggested a latitudinal image segmentation method and an invariant pixel method. As an application, the image segmentation and invariant pixel methods were applied to a set of AVHRR data covering most part of Asia from 1982 to 1993. Fuzzy classification results showed the decrease of forests and the increase of croplands at densely populated areas, however an opposite trend was detected at sparsely populated or depopulated areas.

• Korean Journal of Remote Sensing
• /
• v.37 no.6_1
• /
• pp.1573-1587
• /
• 2021

A Drone image is an ultra-high-resolution image that is several or tens of times higher in spatial resolution than a satellite or aerial image. Therefore, drone image-based remote sensing is different from traditional remote sensing in terms of the level of object to be extracted from the image and the amount of data to be processed. In addition, the optimal scale and size of data used for model training is different depending on the characteristics of the applied deep learning model. However, moststudies do not consider the size of the object to be found in the image, the spatial resolution of the image that reflects the scale, and in many cases, the data specification used in the model is applied as it is before. In this study, the effect ofspatial resolution and image size of drone image on the accuracy and training time of the semantic segmentation deep learning model of six wintering vegetables was quantitatively analyzed through experiments. As a result of the experiment, it was found that the average accuracy of dividing six wintering vegetablesincreases asthe spatial resolution increases, but the increase rate and convergence section are different for each crop, and there is a big difference in accuracy and time depending on the size of the image at the same resolution. In particular, it wasfound that the optimal resolution and image size were different from each crop. The research results can be utilized as data for getting the efficiency of drone images acquisition and production of training data when developing a winter vegetable segmentation model using drone images.