• The Journal of the Korea Contents Association
• /
• v.21 no.3
• /
• pp.23-32
• /
• 2021

Semantic image segmentation technology in the field of computer vision is a technology that classifies an image by dividing it into pixels. This technique is also rapidly improving performance using a machine learning method, and a high possibility of utilizing information in units of pixels is drawing attention. However, this technology has been raised from the early days until recently for 'lack of detailed segmentation' problem. Since this problem was caused by increasing the size of the label map, it was expected that the label map could be improved by using the edge map of the original image with detailed edge information. Therefore, in this paper, we propose a post-processing algorithm that maintains semantic image segmentation based on learning, but modifies the resulting label map based on the edge map of the original image. After applying the algorithm to the existing method, when comparing similar applications before and after, approximately 1.74% pixels and 1.35% IoU (Intersection of Union) were applied, and when analyzing the results, the precise targeting fine segmentation function was improved.

• Journal of Biosystems Engineering
• /
• v.35 no.2
• /
• pp.132-137
• /
• 2010

Site-specific N application for corn is one of the precision crop management. To implement the site-specific N application, various nitrogen stress sensing methods, including aerial image, tissue analysis, soil sampling analysis, and SPAD meter readings, have been used. Use of side-dressing, an efficient nitrogen application method than a uniform application in either late fall or early spring, relies mainly on the capability of nitrogen deficiency detection. This paper presents map-based variable rate nitrogen application based using a multi-spectral corn nitrogen deficiency(CND) sensor. This sensor assess the nitrogen stress by means of the estimated SPAD reading calculated from the corn leave reflectance. The estimated SPAD value from the CND sensor system and location information form DGPS of each field block was combined into the field map using a ArcView program. Then this map was converted into a raster file for a map-based variable rate application software. The relative SPAD (RSPAD = SPAD over reference SPAD) was investigated 2 weeks after the treatments. The results showed that the map-based variable rate application system was feasible.

• Ocean Systems Engineering
• /
• v.11 no.4
• /
• pp.331-351
• /
• 2021

Underwater images are very much different from images taken on land, due to the presence of a higher disturbance ratio caused by the presence of water medium between the camera and the target object. These distortions and noises result in unclear details and reduced quality of the output image. An underwater image restoration method is proposed in this paper, which uses blurriness information, background light neutralization information, and red-light intensity to estimate depth. The transmission map is then estimated using the derived depth map, by considering separate attenuation coefficients for direct and backscattered signals. The estimated transmission map and estimated background light are then used to recover the scene radiance. Qualitative and quantitative analysis have been used to compare the performance of the proposed method against other state-of-the-art restoration methods. It has been shown that the proposed method can yield good quality restored underwater images. The proposed method has also been evaluated using different qualitative metrics, and results have shown that method is highly capable of restoring underwater images with different conditions. The results are significant and show the applicability of the proposed method for underwater image restoration work.

• Aerospace Engineering and Technology
• /
• v.11 no.2
• /
• pp.140-148
• /
• 2012

For autonomous navigation, map, pose tracking, and finding the shortest path are required. Because there is no GPS signal in indoor environment, the current position should be recognized in the 3D map by using image processing or something. In this paper, we explain 3D map creation technology by using depth camera like Kinect and pose tracking in 3D map by using 2D image taking from camera. In addition, the mechanism of avoiding obstacles is discussed.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2004.11a
• /
• pp.519-522
• /
• 2004

The purpose of this research is to design a road using digital photogrammatry method to generate DEM(digital elevation model) and digital ortho image based on GSIS which was applied to the road simulation. The example study area was the suburbs of Jeju city. To this study, 1/5,000 digital map and GSIS technique were used for optimum road design of the island based on Arc View software. Using this software we can Set an overlay map by combination of hill shade map, slope map, aspect map, and building buffer map. Based on this overlap map, we designed the best road line and along this line we performed three dimensional road simulation using Microstation CAD and Inroads road design programs. From the results, we found that the DEM and digital ortho image acquired from stereoairphoto using digital photogrammatry was satisfied for choosing the best roadline and the developed three dimensional road simulation technique using GSIS technique was very useful to estimate the reasonable road design before the real road construction works.

• Journal of Korean Society for Geospatial Information Science
• /
• v.15 no.4
• /
• pp.31-39
• /
• 2007

As the availability of images from airborne digital camera with high resolution is expanded, a lot of concern are shown about the production of orthoimage and digital map. This study presents the method of updating digital map using orthoimage from airborne digital camera image. Images were georectified using GPS surveying data. For the generation of orthoimage, Lidar DEM was used. The absolute positional accuracy of orthoimage was evaluated using GPS surveying data. And that of the building layer of digital map was estimated using the existed digital map at the scale of 1:1,000. The absolute positional accuracy of orthoimage was as followed: RMSE in X and Y were ${\pm}0.076m$ and ${\pm}0.294m$. The RMSE of the building layer were ${\pm}0.250m$ and ${\pm}0.210m$ in X and Y directions, respectively. The RMSE of the digital map using orthoimage from Aerial Digital Camera image fell within allowable error range established by NGII. Consequently, updating digital map using orthoimage from Aerial Digital Camera image can be applied to various fields including the construction of the framework data and the GIS of local government.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2006.05a
• /
• pp.925-928
• /
• 2006

본 논문에서는 영상에 워터마크를 삽입하고 추출하는 동시에 원영상을 복원하는 리버서블 워터마킹 알고리즘을 제안한다. 제안한 알고리즘의 핵심은 워터마크가 삽입된 영상에 변하지 않는 위치정보를 전달하는 것이다. 본 논문에서는 우선 원영상을 odd image와 even image로 분리한 다음odd image에 interpolation 기법을 이용하여 resizing시키고 resizing 된 영상(odd_resize_image)에서 기수항은 그대로 두고 우수항은 기수항과 우수항의 차이값으로 채우는 방법으로 location map을 얻는다. 이 location map 에 의해 워터마크를 삽입위치를 선택하면 추출과정에서도 같은 location map을 이용할 수 있기에 워터마크 삽입위치를 정확하게 판단하여 추출할 수 있고 동시에 원본 영상을 복원할 수 있다. 본 알고리즘은 영상에 변화를 적게 주었기 때문에 높은 비가시성을 보인다. 실험 결과 $256{\times}256$ 영상에서 PSNR이 평균 53.07dB의 우수한 비가시성을 보였다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2010.07a
• /
• pp.241-243
• /
• 2010

Previous approaches to the 2D to 3D conversion problem require heavy computation or considerable amount of user input. In this paper, we propose a rather simple method in estimating the depth map from a single image using a monocular depth cue: haze. Using the haze imaging model, we obtain the distance information and estimate a reliable depth map from a single scenery image. Using the depth map, we also suggest an algorithm that converts the single image to 3D stereoscopic images. We determine a disparity value for each pixel from the original 'left' image and generate a corresponding 'right' image. Results show that the algorithm gives well refined depth maps despite the simplicity of the approach.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.32B no.3
• /
• pp.57-65
• /
• 1995

This paper presents a new classified vector quantization (VQ) technique using a neural network model in the transform domain. Prior to designing a codebook, the proposed approach extracts class features from a set of images using self-organizing feature map (SOFM) that has the pattern recognition characteristics and the same as VQ objective. Since we extract the class features from the training images unlike previous approaches, the reconstructed image quality is improved. Moreover, exploiting the adaptivity of the neural network model makes our approach be easily applied to designing a new vector quantizer when the processed image characteristics are changed. After the generalized BFOS algorithm allocates the given bits to each class, codebooks of each class are also generated using SOFM for the maximal reconstructed image quality. In experimental results using monochromatic images, we obtained a good visual quality in the reconstructed image. Also, PSNR is comparable to that of other classified VQ technique and is higher than that of JPEG baseline system.

• The Journal of the Society of Korean Medicine Diagnostics
• /
• v.20 no.1
• /
• pp.37-44
• /
• 2016

Ultrasonic imaging is the most widely modality among modern imaging device for medical diagnosis. Nevertheless, medical ultrasound images suffer from speckle noise and low contrast. In this paper, we propose probabilistic edge map for ultrasound image edge enhancement using automatic alien algorithm. The proposed method used applied speckle reduced ultrasound imaging for edge improvement using sequentially acquired ultrasound imaging. To evaluate the performance of method, the similarity between the reference and edge enhanced image was measured by quantity analysis. The experimental results show that the proposed method considerably improves the image quality with region edge enhancement.