• Korean Journal of Remote Sensing
• /
• v.37 no.5_1
• /
• pp.1095-1109
• /
• 2021

The technology used to recognize the location and surroundings of autonomous vehicles is called SLAM. SLAM standsfor Simultaneously Localization and Mapping and hasrecently been actively utilized in research on autonomous vehicles,starting with robotic research. Expensive GPS, INS, LiDAR, RADAR, and Wheel Odometry allow precise magnetic positioning and mapping in centimeters. However, if it can secure similar accuracy as using cheaper Cameras and GPS data, it will contribute to advancing the era of autonomous driving. In this paper, we present a method for converging monocular camera with RTK-enabled GPS data to perform RMSE 33.7 cm localization and mapping on the urban road.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.19 no.8
• /
• pp.1453-1463
• /
• 1994

Recently many robot manipulators are used for various areas of industriesand factories. It has been frequently observed that the robot manipulator fails to complete the function when the object changes its original position, Due to the unexpected impacts and vibrations the center and direction of the object would be shifted in many real application. In this study, a visual sensing algorithm for the robot manipulator is proposed. The algorithm consists of two parts : Detection of the object migration and adjustments of the orobot manipulators Tool Coordinate System. The image filtering technique with visual sensor is applied for the first part of the algorithm. The change of illumination intensity indicates the object migration. Once the object migration is detected, the second part of the algorithm calculates the current position of the object. Then it adjusts the robot manipulators Tool Coordinate System. The robot manipulator and the Visual sensor communicate each other using interrupt technique via proposed algorithm. It has been observed that the proposed algorithm reduces the malfunction of a robot manipulator significantly. Thus it can provide better line balance-up of the manufacturing processes and prevent industrial accidents efficiently.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.4
• /
• pp.173-180
• /
• 2014

Compressive sensing is a new signal acquisition paradigm that enables sparse/compressible signal to be sampled under the Nyquist-rate. To fully benefit from its much simplified acquisition process, huge efforts have been made on improving the performance of compressive sensing recovery. However, concerning color images, compressive sensing recovery lacks in addressing image characteristics like energy distribution or human visual system. In order to overcome the problem, this paper proposes a new group-sparsity hard thresholding process by preserving some RGB-grouped coefficients important in both terms of energy and perceptual sensitivity. Moreover, a smoothed group-sparsity iterative hard thresholding algorithm for compressive sensing of color images is proposed by incorporating a frame-based filter with group-sparsity hard thresholding process. In this way, our proposed method not only pursues sparsity of image in transform domain but also pursues smoothness of image in spatial domain. Experimental results show average PSNR gains up to 2.7dB over the state-of-the-art group-sparsity smoothed recovery method.

• Korean Journal of Remote Sensing
• /
• v.30 no.1
• /
• pp.1-12
• /
• 2014

The purpose of this paper is to provide a compact overview of the state-of-art image mosaic algorithms in commercial softwares and to propose objective assessment method of that. Among them, several algorithms, widely used and high quality, result in the mosaic image by applying to seven different kinds of seasons of KOMPSAT-2 images and then consequently each result is analyzed visually. Moreover, quality index is suggested to assess the similarity with colors regarding adjacency images and then it is performed by comparing and analyzing the visual and quantitative results. Consequently, we found out the suggested quality index is feasible.

• Journal of Astronomy and Space Sciences
• /
• v.32 no.2
• /
• pp.161-166
• /
• 2015

Analysis of lunar samples returned by the US Apollo missions revealed that the lunar highlands consist of anorthosite, plagioclase, pyroxene, and olivine; also, the lunar maria are composed of materials such as basalt and ilmenite. More recently, the remote sensing approach has enabled reduction of the time required to investigate the entire lunar surface, compared to the approach of returning samples. Moreover, remote sensing has also made it possible to determine the existence of specific minerals and to examine wide areas. In this paper, an investigation was performed on the reflectance distribution and its trend. The results were applied to the example of the double ray stretched in parallel lines from the Tycho crater to the third-quadrant of Mare Nubium. Basic research and background information for the investigation of lunar surface characteristics is also presented. For this research, resources aboard the SELenological and ENgineering Explorer (SELENE), a Japanese lunar probe, were used. These included the Multiband Imager (MI) in the Lunar Imager/Spectrometer (LISM). The data of these instruments were edited through the toolkit, an image editing and analysis tool, Exelis Visual Information Solution (ENVI).

• Journal of Forest and Environmental Science
• /
• v.31 no.3
• /
• pp.225-234
• /
• 2015

Mangroves are important coastal ecosystems and are located at the inter-tidal zones of tropical and sub-tropical belts. The global mangrove forests are declining dramatically because of the conversion of forests to shrimp farming, over-exploitation, pollution and freshwater diversion. The Bangladesh Forest Department initiated mangrove afforestation throughout the coastal belts of Bangladesh in 1966 to provide better protection for the coastal communities. Up to 1990, 120,000 ha of mangroves had been planted and it is one of the largest coastal afforestaton programs in the world. The objective of this study is to exploit the spatial extent of mangrove plantation and their dynamics of changes over the last two decades using multispectral Landsat imagery. The study area covers the coastal areas of Bangladesh that is extended over the eastern part of Sundarbans up to Teknaf, the southern tip of mainland Bangladesh. Mangrove plantations were interpreted visually on computer screen and interactive delineation of forest boundary was done. The mangrove plantation area has been estimated as 32,725, 47,636 and 43,166 ha for the year of 1989, 2000 and 2010, respectively. Mangrove deforestation by human activity has increased almost six times in the recent decade in comparison to the previous one. The mangrove forest loss due to coastal erosion has slightly declined in the 2000s. Mangroves have been lost primarily because of agricultural expansion. The result of this investigation will be helpful to understand the dynamics of mangrove plantation and the main drivers of changes in this coastal ecosystem.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2003.06a
• /
• pp.1727-1730
• /
• 2003

A windshield wiper system plays a key part in assurance of driver's safety at rainfall. However, because quantity of rain and snow vary irregularly according to time and velocity of automotive, a driver changes speed and operation period of a wiper from time to time in order to secure enough visual field in the traditional windshield wiper system. Because a manual operation of windshield wiper distracts driver's sensitivity and causes inadvertent driving, this is becoming direct cause of traffic accident. Therefore, this paper presents the basic architecture of vision-based smart windshield wiper system and the rain sensing algorithm that regulate speed and operation period of windshield wiper automatically according to quantity of rain or snow. Also, this paper introduces the fuzzy wiper control algorithm based on human's expertise, and evaluates performance of suggested algorithm in simulator model. In especial, the vision sensor can measure wide area relatively than the optical rain sensor. hence, this grasp rainfall state more exactly in case disturbance occurs.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2003.06a
• /
• pp.237-240
• /
• 2003

In biological cell manipulation, manual thrust or penetration of an injection pipette into an embryo cell is currently performed by a skilled operator, relying on visual feedback information only. Accurately measuring cellular forces is a requirement for minimally invasive cell injections. Moreover, the cellular farce sensing is essential in investigating the biophysical properties for cell injury and membrane modeling studies. This paper presents cellular force measurements for the force feedback-based biomanipulation. Cellular force measurement system using piezoelectric polymer sensor is implemented to measure the penetration force of a zebrafish egg cell. First, measurement system setup and calibration are described. Second, the force feedback-based biomanipulation is experimentally carried out. Experimental results show that it successfully supplies real-time cellular force feedback to the operator at several tens of uN and thus plays a main role in improving the reliability of biological cell injection tasks.

• Korean Journal of Remote Sensing
• /
• v.28 no.6
• /
• pp.623-632
• /
• 2012

In this paper, we analyzed the effect of wavelet decomposition levels in feature extraction for anomaly detection from hyperspectral imagery. After wavelet analysis, anomaly detection was experimentally performed using the RX detector algorithm to analyze the detecting capabilities. From the experiment for anomaly detection using CASI imagery, the characteristics of extracted features and the changes of their patterns showed that radiance curves were simplified as wavelet transform progresses and H bands did not show significant differences between target anomaly and background in the previous levels. The results of anomaly detection and their ROC curves showed the best performance when using the appropriate sub-band decided from the visual interpretation of wavelet analysis which was L band at the decomposition level where the overall shape of profile was preserved. The results of this study would be used as fundamental information or guidelines when applying wavelet transform to feature extraction and selection from hyperspectral imagery. However, further researches for various anomaly targets and the quantitative selection of optimal decomposition levels are needed for generalization.

• 제어로봇시스템학회:학술대회논문집
• /
• 1998.10a
• /
• pp.30-34
• /
• 1998

Path Planning is one of the important fields in robot technologies. Local path planning may be done in on-line modes while recognizing an environment of robot by itself. In dynamic environments to obtain fluent information for environments vision system as a sensing equipment is a one of the most necessary devices for safe and effective guidance of robots. If there is a predictor that tells what future sensing outputs will be, robot can respond to anticipated environmental changes in advance. The tracking of obstacles has a deep relationship to the prediction for safe navigation. We tried to deal with active contours, that is snakes, to find out the possibilities of stable tracking of objects in image plane. Snakes are defined based on energy functions, and can be deformed to a certain contour form which would converge to the minimum energy states by the forces produced from energy differences. By using point algorithm we could have more speedy convergence time because the Brent's method gives the solution to find the local minima fast. The snake algorithm may be applied to sequential image frames to track objects in the images by these characteristics of speedy convergence and robust edge detection ability.