• Korean Journal of Remote Sensing
• /
• v.37 no.1
• /
• pp.111-122
• /
• 2021

Building footprint extraction is an active topic in the domain of remote sensing, since buildings are a fundamental unit of urban areas. Deep convolutional neural networks successfully perform footprint extraction from optical satellite images. However, semantic segmentation produces coarse results in the output, such as blurred and rounded boundaries, which are caused by the use of convolutional layers with large receptive fields and pooling layers. The objective of this study is to generate visually enhanced building objects by directly extracting the vertices of individual buildings by combining instance segmentation and keypoint detection. The target keypoints in building extraction are defined as points of interest based on the local image gradient direction, that is, the vertices of a building polygon. The proposed framework follows a two-stage, top-down approach that is divided into object detection and keypoint estimation. Keypoints between instances are distinguished by merging the rough segmentation masks and the local features of regions of interest. A building polygon is created by grouping the predicted keypoints through a simple geometric method. Our model achieved an F1-score of 0.650 with an mIoU of 62.6 for building footprint extraction using the OpenCitesAI dataset. The results demonstrated that the proposed framework using keypoint estimation exhibited better segmentation performance when compared with Mask R-CNN in terms of both qualitative and quantitative results.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.40 no.3
• /
• pp.227-237
• /
• 2022

The most critical factors for detecting changes in very high-resolution satellite images are building positional inconsistencies and relief displacements caused by satellite side-view. To resolve the above problems, additional processing using a digital elevation model and deep learning approach have been proposed. Unfortunately, these approaches are not sufficiently effective in solving these problems. This study proposed a change detection method that considers both positional and topology information of buildings. Mask R-CNN (Region-based Convolutional Neural Network) was trained on a SpaceNet building detection v2 dataset, and the central points of each building were extracted as building nodes. Then, triangulated irregular network graphs were created on building nodes from temporal images. To extract the area, where there is a structural difference between two graphs, a change index reflecting the similarity of the graphs and differences in the location of building nodes was proposed. Finally, newly changed or deleted buildings were detected by comparing the two graphs. Three pairs of test sites were selected to evaluate the proposed method's effectiveness, and the results showed that changed buildings were detected in the case of side-view satellite images with building positional inconsistencies.

• Food Engineering Progress
• /
• v.22 no.4
• /
• pp.309-314
• /
• 2018

In recent years, interest in halal authentication from the domestic food and cosmetics field has been growing for advances into the overseas halal market. For halal authentication, the product must not contain haram ingredients derived from pig, dog, human, GMO, etc. In this study, the presence of haram ingredients in plant extracts (carrot, oyster mushroom, and pine needle) treated with papain and bromelain and cosmetics (mask pack and cream) containing these extracts were analyzed by PCR to confirm whether these cosmetics were suitable for halal authentication. Detection limits of the PCR method that specifically detected template DNA of human, pig, dog, and GMO were $1.29{\times}10^3$, $1.14{\times}10^3$, $1.24{\times}10^2$ and $2.02{\times}10^3copies/tube$, respectively. PCR was not inhibited by the plant extracts or cosmetic ingredients. Results of PCR for the plant extracts or cosmetics containing these extracts were all negative. This PCR method could be used to rapidly identify the presence of haram ingredients in raw materials or final products during the manufacturing process of food and cosmetics.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.13 no.5
• /
• pp.1051-1058
• /
• 2018

This paper propose image processing algorithm to prevent safety accidents near by subway platform screen door(PSD). First, edges of the subway PSD images are detected and the boundary line between PSD and subway platform is detected to decide people's approach to the PSD using Hough transform. To do this, we draw the boundary line between the PSD and platform, to detect the boundary line and to decide the people's approach to the detected line is completely connected or not. Generally, edge is the basic characteristic of image; thus, edge detection is very important in image processing applications and computer vision area. The conventional edge detection methods such as Roberts, Sobel, Prewitt, and Laplacian etc, which are using a fixed value of mask, and morphological gradient from the structuring element of view and Canny edge detector are widely used. In this paper, we propose the detection algorithm about the people's approach to the subway PSD to prevent the safety accidents by using Canny edge detector and Hough transform and the computer simulation shows the results.

• Korean Journal of Remote Sensing
• /
• v.38 no.1
• /
• pp.103-110
• /
• 2022

Since satellite images generally include clouds in the atmosphere, it is essential to detect or mask clouds before satellite image processing. Clouds were detected using physical characteristics of clouds in previous research. Cloud detection methods using deep learning techniques such as CNN or the modified U-Net in image segmentation field have been studied recently. Since image segmentation is the process of assigning a label to every pixel in an image, precise pixel-based dataset is required for cloud detection. Obtaining accurate training datasets is more important than a network configuration in image segmentation for cloud detection. Existing deep learning techniques used different training datasets. And test datasets were extracted from intra-dataset which were acquired by same sensor and procedure as training dataset. Different datasets make it difficult to determine which network shows a better overall performance. To verify the effectiveness of the cloud detection network such as Cloud-Net, two types of networks were trained using the cloud dataset from KOMPSAT-3 images provided by the AIHUB site and the L8-Cloud dataset from Landsat8 images which was publicly opened by a Cloud-Net author. Test data from intra-dataset of KOMPSAT-3 cloud dataset were used for validating the network. The simulation results show that the network trained with KOMPSAT-3 cloud dataset shows good performance on the network trained with L8-Cloud dataset. Because Landsat8 and KOMPSAT-3 satellite images have different GSDs, making it difficult to achieve good results from cross-sensor validation. The network could be superior for intra-dataset, but it could be inferior for cross-sensor data. It is necessary to study techniques that show good results in cross-senor validation dataset in the future.

• Korean Journal of Remote Sensing
• /
• v.39 no.1
• /
• pp.77-86
• /
• 2023

Ship detection is widely used in areas such as maritime security, maritime traffic, fisheries management, illegal fishing, and border control, and ship detection is important for rapid response and damage minimization as ship accident rates increase due to recent increases in international maritime traffic. Currently, according to a number of global and national regulations, ships must be equipped with automatic identification system (AIS), which provide information such as the location and speed of the ship periodically at regular intervals. However, most small vessels (less than 300 tons) are not obligated to install the transponder and may not be transmitted intentionally or accidentally. There is even a case of misuse of the ship'slocation information. Therefore, in this study, ship detection was performed using high-resolution optical satellite images that can periodically remotely detect a wide range and detectsmallships. However, optical images can cause false-alarm due to noise on the surface of the sea, such as waves, or factors indicating ship-like brightness, such as clouds and wakes. So, it is important to remove these factors to improve the accuracy of ship detection. In this study, false alarm wasreduced, and the accuracy ofship detection wasimproved by removing wake.As a ship detection method, ship detection was performed using machine learning-based random forest (RF), and convolutional neural network (CNN) techniquesthat have been widely used in object detection fieldsrecently, and ship detection results by the model were compared and analyzed. In addition, in this study, the results of RF and CNN were combined to improve the phenomenon of ship disconnection and the phenomenon of small detection. The ship detection results of thisstudy are significant in that they improved the limitations of each model while maintaining accuracy. In addition, if satellite images with improved spatial resolution are utilized in the future, it is expected that ship and wake simultaneous detection with higher accuracy will be performed.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.3C
• /
• pp.92-101
• /
• 2005

It is difficult to detect the accurate detection which leads the camera it moves follows in change of the noise or illumination and Also, it could be recognized with backgound if the object doesn't move during hours. In this paper, the proposed method is updating changed background image as much as N＊M pixel mask as time goes on after get a difference between imput image and first background image. And checking image pixel can efficiently detect moving by computing fixed distance pixel instead of operate all pixel. Also, set up minimum area of object to use boundary point of object abstracted through checking image pixel and motion detect of object. Therefore motion detection is available as is fast and correct without doing checking image pixel every Dame. From experiment, the designed and implemented system showed high precision ratio in performance assessment more than 90 percents.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.05a
• /
• pp.367-370
• /
• 2015

This paper proposes an improve method of the detection performance of traffic lights for autonomous driving cars. Earlier detection methods used to adopt color thresholding, template matching and based learning maching methods, but its have some problems such as recognition rate decreasing, slow processing time. The proposed method uses both detection mask and morphological preprocessing. Firstly, input color images are converted to YCbCr image in order to strengthen its illumination, and horizontal edge components are extracted in the Y Channel. Secondly, the region of interest is detected according to morphological characteristics of the traffic lights. Finally, the traffic signal is detected based on color distributions. The proposed method showed that the detection rate and processing time improved rather than the conventional algorithm about some surrounding environments.

• 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 Convergence Signal Processing
• /
• v.24 no.2
• /
• pp.119-125
• /
• 2023

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.