• 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.

• KIPS Transactions on Software and Data Engineering
• /
• v.6 no.6
• /
• pp.315-320
• /
• 2017

Estimating the correct pose of augmented objects on the real camera view efficiently is one of the most important questions in image tracking area. In computer vision, Homography is used for camera pose estimation in augmented reality system with markerless. To estimating Homography, several algorithm like SURF features which extracted from images are used. Based on extracted features, Homography is estimated. For this purpose, RANSAC algorithm is well used to estimate homography and DCS-RANSAC algorithm is researched which apply constraints dynamically based on Constraint Satisfaction Problem to improve performance. In DCS-RANSAC, however, the dataset is based on pattern of feature distribution of images manually, so this algorithm cannot classify the input image, pattern of feature distribution is not recognized in DCS-RANSAC algorithm, which lead to reduce it's performance. To improve this problem, we suggest the KCS-RANSAC algorithm using K-means clustering in CS-RANSAC to cluster the images automatically based on pattern of feature distribution and apply constraints to each image groups. The suggested algorithm cluster the images automatically and apply the constraints to each clustered image groups. The experiment result shows that our KCS-RANSAC algorithm outperformed the DCS-RANSAC algorithm in terms of speed, accuracy, and inlier rate.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.47 no.4
• /
• pp.34-43
• /
• 2010

Texture information plays an important role in object recognition and classification. To perform an accurate classification, the texture feature used in the classification must be highly discriminative. This paper presents a novel texture descriptor for texture-based image retrieval and its application in Computer-Aided Diagnosis (CAD) system for Emphysema classification. The texture descriptor is based on the combination of local surrounding neighborhood difference and centralized neighborhood difference and is named as Combined Neighborhood Difference (CND). The local differences of surrounding neighborhood difference and centralized neighborhood difference between pixels are compared and converted into binary codewords. Then binomial factor is assigned to the codewords in order to convert them into high discriminative unique values. The distribution of these unique values is computed and used as the texture feature vectors. The texture classification accuracies using Outex and Brodatz dataset show that CND achieves an average of 92.5%, whereas LBP, LND and Gabor filter achieve 89.3%, 90.7% and 83.6%, respectively. The implementations of CND in the computer-aided diagnosis of Emphysema is also presented in this paper.

• Journal of the Institute of Convergence Signal Processing
• /
• v.23 no.3
• /
• pp.166-172
• /
• 2022

In this study, we photograph driving obstacle objects such as crosswalks, side spheres, manholes, braille blocks, partial ramps, temporary safety barriers, stairs, and inclined curb that hinder or cause inconvenience to the movement of the vulnerable using electric mobility aids. We develop an optimal AI model that classifies photographed objects and automatically recognizes them, and implement an algorithm that can efficiently determine obstacles in front of electric mobility aids. In order to enable object detection to be AI learning with high probability, the labeling form is labeled as a polygon form when building a dataset. It was developed using a Mask R-CNN model in Detectron2 framework that can detect objects labeled in the form of polygons. Image acquisition was conducted by dividing it into two groups: the general public and the transportation weak, and image information obtained in two areas of the test bed was secured. As for the parameter setting of the Mask R-CNN learning result, it was confirmed that the model learned with IMAGES_PER_BATCH: 2, BASE_LEARNING_RATE 0.001, MAX_ITERATION: 10,000 showed the highest performance at 68.532, so that the user can quickly and accurately recognize driving risks and obstacles.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.38 no.6
• /
• pp.648-656
• /
• 2001

In this paper, we propose a new feature-based vehicle tracking system using trajectory matching for intelligent traffic surveillance. The proposed system consists of three parts: feature extraction, feature tracking, and feature grouping using trajectory matching. For feature extraction and feature tracking, features of vehicles are selected based on the measure of cornerness and are tracked using linear Kalman filtering. We then group features from the same vehicle in the grouping step. We suggest a new grouping algorithm using the spatial information of features and trajectory matching to solve the over-grouping Problems of the feature-based tracking method. Finally, our proposed tracking system demonstrates good performance for typical traffic scenes with partial occlusion and neighboring conditions.

• Korean Journal of Remote Sensing
• /
• v.35 no.6_3
• /
• pp.1273-1283
• /
• 2019

This paper proposes an advanced crop classification model that combines a procedure for weighted combination of spatial features extracted from multi-scale input images with a conventional convolutional neural network (CNN) structure. The proposed model first extracts spatial features from patches with different sizes in convolution layers, and then assigns different weights to the extracted spatial features by considering feature-specific importance using squeeze-and-excitation block sets. The novelty of the model lies in its ability to extract spatial features useful for classification and account for their relative importance. A case study of crop classification with multi-temporal Landsat-8 OLI images in Illinois, USA was carried out to evaluate the classification performance of the proposed model. The impact of patch sizes on crop classification was first assessed in a single-patch model to find useful patch sizes. The classification performance of the proposed model was then compared with those of conventional two CNN models including the single-patch model and a multi-patch model without considering feature-specific weights. From the results of comparison experiments, the proposed model could alleviate misclassification patterns by considering the spatial characteristics of different crops in the study area, achieving the best classification accuracy compared to the other models. Based on the case study results, the proposed model, which can account for the relative importance of spatial features, would be effectively applied to classification of objects with different spatial characteristics, as well as crops.

• Proceedings of the KSRS Conference
• /
• 2007.03a
• /
• pp.113-119
• /
• 2007

This article deals mainly with two objectives viz, 1) the potentiality of very high-resolution(VHR) multi-spectral and pan chromatic QuickBird satellite data in resources mapping over moderate resolution satellite data (IRS LISS III) and 2) the advantages of using object oriented classification method of eCognition software in land use and land cover analysis over the ISODATA classification method. These VHR data offers widely acceptable metric characteristics for cartographic updating and increase our ability to map land use in geometric detail and improve accuracy of local scale investigations. This study has been carried out in the Sukkalampatti mini-watershed, which is situated in the Eastern Ghats of Tamil Nadu, India. The eCognition object oriented classification method succeeded in most cases to achieve a high percentage of right land cover class assignment and it showed better results than the ISODATA pixel based one, as far as the discrimination of land cover classes and boundary depiction is concerned.

• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.17 no.3
• /
• pp.181-188
• /
• 2012

Despite the ecological importance of seagrass beds, their distributional information in Korean coastal waters is insufficient. Therefore, we used hydroacoustic system to collect accurate bathymetry and classification of seagrass, and Kompsat-2 (4 m spatial resolution) image for detection of seagrass beds at Deukryang Bay, Korea. The accuracy of Kompsat-2 image classification was evaluated using hydracoustic survey result using error matrix and Kappa value. The total area of seagrass beds from satellite image classification was underestimated compared to the hydroacoustic survey, estimated 3.9 and $4.5km^2$ from satellite image and hydroacoustic data, respectively. Nonetheless, the accuracy of Kompsat-2 image classification over hydroacoustic-based method showing 90% (Kappa=0.85) for the three class maps (seagrass, unvegetated seawater and aquaculture). The agreement between the satellite image classification and the hydroacoustic result was 77.1% (the seagrass presence/absence map). From our result of satellite image classification, Kompsat-2 image is suitable for mapping seagrass beds with high accuracy and non-destructive method. For more accurate information, more researches with a variety of high-resolution satellite image will be preceded.

• Korean Journal of Remote Sensing
• /
• v.35 no.2
• /
• pp.265-278
• /
• 2019

Visible Infrared Imaging Radiometer Suite (VIIRS) Day/Night Band (DNB) data help to enable rapid emergency responses through detection of the artificial and natural disasters occurring at night. The DNB data without correction of lunar irradiance effect distributed by Korea Ocean Science Center (KOSC) has advantage for rapid change detection because of direct receiving. In this study, radiance differences according to the phase of the moon was analyzed for urban and mountain areas in Korean Peninsula using the DNB data directly receiving to KOSC. Lunar irradiance correction algorithm was proposed for the change detection. Relative correction was performed by regression analysis between the selected pixels considering the land cover classification in the reference DNB image during the new moon and the input DNB image. As a result of daily difference image analysis, the brightness value change in urban area and mountain area was ${\pm}30$ radiance and below ${\pm}1$ radiance respectively. The object based change detection was performed after the extraction of the main object of interest based on the average image of time series data in order to reduce the matching and geometric error between DNB images. The changes in brightness occurring in mountainous areas were effectively detected after the calibration of lunar irradiance effect, and it showed that the developed technology could be used for real time change detection.

• Korean Journal of Remote Sensing
• /
• v.39 no.5_3
• /
• pp.967-978
• /
• 2023

This study proposed and validated a combined segmentation network (CSN) designed to effectively train on multiple drone image datasets and enhance the accuracy of semantic segmentation. CSN shares the entire encoding domain to accommodate the diversity of three drone datasets, while the decoding domains are trained independently. During training, the segmentation accuracy of CSN was lower compared to U-Net and the pyramid scene parsing network (PSPNet) on single datasets because it considers loss values for all dataset simultaneously. However, when applied to domestic autonomous drone images, CSN demonstrated the ability to classify pixels into appropriate classes without requiring additional training, outperforming PSPNet. This research suggests that CSN can serve as a valuable tool for effectively training on diverse drone image datasets and improving object recognition accuracy in new regions.