• Journal of IKEEE
• /
• v.24 no.1
• /
• pp.147-153
• /
• 2020

Conventional lane detection algorithms have problems in that the detection rate is lowered in road environments having a large change in curvature and illumination. The probabilistic Hough transform method has low lane detection rate since it exploits edges and restrictive angles. On the other hand, the method using a sliding window can detect a curved lane as the lane is detected by dividing the image into windows. However, the detection rate of this method is affected by road slopes because it uses affine transformation. In order to detect lanes robustly and avoid obstacles, we propose driving assist system using semantic segmentation based on deep learning. The architecture for segmentation is SegNet based on VGG-16. The semantic image segmentation feature can be used to calculate safety space and predict collisions so that we control a vehicle using adaptive-MPC to avoid objects and keep lanes. Simulation results with CARLA show that the proposed algorithm detects lanes robustly and avoids unknown obstacles in front of vehicle.

• KIPS Transactions on Software and Data Engineering
• /
• v.3 no.9
• /
• pp.375-380
• /
• 2014

Under controlled environment, such as fixed viewpoints or consistent illumination, the performance of face recognition is usually high enough to be acceptable nowadays. Face recognition is, however, a still challenging task in real world. SIFT(Scale Invariant Feature Transformation) algorithm is scale and rotation invariant, which is powerful only in the case of small viewpoint changes. However, it often fails when viewpoint of faces changes in wide range. In this paper, we use Affine SIFT (Scale Invariant Feature Transformation; ASIFT) to detect affine invariant local descriptors for face recognition under wide viewpoint changes. The ASIFT is an extension of SIFT algorithm to solve this weakness. In our scheme, ASIFT is applied only to gallery face, while SIFT algorithm is applied to probe face. ASIFT generates a series of different viewpoints using affine transformation. Therefore, the ASIFT allows viewpoint differences between gallery face and probe face. Experiment results showed our framework achieved higher recognition accuracy than the original SIFT algorithm on FERET database.

• Macromolecular Research
• /
• v.11 no.5
• /
• pp.297-302
• /
• 2003

The imidization and cure reaction of a thermosetting phenylethynyl-terminated amic acid (LaRC PETI-5) in film form have been monitored as a function of temperature by means of a steady-state fluorescence technique using a front-face illumination method. The variation of the fluorescence emission spectra of LaRC PETI-5 can be divided into four temperature regions; Region I: below 15$0^{\circ}C$, Region II: 150-25$0^{\circ}C$, Region III: 250-35$0^{\circ}C$, and Region IV: above 35$0^{\circ}C$. The fluorescence spectra in Region I are largely influenced by residual N-methyl-2pyrrolidinone in the polymer and also slightly by partial imidization of the polymer. There is a combined effect of imidization and solvent removal on the fluorescence behavior in Region II. The spectra in Regions III and IV are due significantly to the cure reaction of LaRC PETI-5 and to a post-cure effect of the polyimide, respectively. This spectroscopic evidence indicating the transformation of the amic acid imide oligomer into the corresponding polyimide via imidization and cure, agrees well with thermal analysis results obtained previously. The intermediate stage of cure in the range of 250-30$0^{\circ}C$ predominantly influences the change of the fluorescence intensity. The later stage above 30$0^{\circ}C$ significantly influences the position of the spectrum. This fluorescence study also supports the mechanism proposed in earlier work that the crosslinking reaction takes place at the reaction sites in the conjugated polyene and the phenylethynyl end group in the polyimide chain.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.12
• /
• pp.71-82
• /
• 2012

In this paper, we propose a license plate detection method with improved Adaboost learning and MCT (Modified Census Transform). The MCT represents the local structure patterns as integer numbered feature values which has robustness to illumination change and memory efficiency. However, since these integer values are discrete, a lookup table is needed to design a weak classifier for Adaboost learning. Some previous research efforts have focused on minimization of exponential criterion for Adaboost optimization. In this paper, a method that uses MCT and improved Adaboost learning based on Newton's optimization to exponential criterion is proposed for license plate detection. Experimental results on license patch images and field images demonstrate that the proposed method yields higher performance of detection rates with low false positives than the conventional method using the original Adaboost learning.

• Korean Journal of Materials Research
• /
• v.10 no.4
• /
• pp.264-269
• /
• 2000

TiO$_2$thin films were prepared on the glass by a conventional spin coating method with $TiO_2$ sol(30wt%, anatase). The thickness of the thin films were controlled by the number of coating cycles: one cycle is composed of spin coating, drying, and heating process. The reaction rate of the film was obtained by the photodecomposition of gaseous benzene under 0.44 and 2.0mW/$\textrm{cm}^2$ UV light on the film surface. For an incident UV light intensity of 0.44mW/$\textrm{cm}^2$, the reaction rate was increased with the thickness of the film, caused by extent of surface area, but there was no change over the thickness of about 4$\mu\textrm{m}$. The porous $TiO_2$ thin film has comparatively vast effective surface area, which under relatively high-intensity UV illumination causes the reaction rate to be controlled by the film thickness.

• Journal of Sensor Science and Technology
• /
• v.5 no.3
• /
• pp.65-73
• /
• 1996

One of the important factor in drug stuffs to a patient is to inject exact amount with stable flow rates. Since improper injection amount and flow rates would cause bad effect to recovery of a patient, the detecting sensors with high sensitivity is required for an injection pump systems' performance improvement. In this study, the three sensors, piezo film sensor, photo transistor and photo array, were compared to find best one for an injection pump monitoring system. Using suggested data processing technique and photo array sensors, we could minimize the effect of interference, disturbance, illumination, and sensitivity change caused by sensor's position. According to the experiments, the photo array showed the higher reliance than any other the three types of sensors.

• Smart Media Journal
• /
• v.5 no.1
• /
• pp.24-29
• /
• 2016

To satisfy the needs of high-level intelligent surveillance system, it shall be able to extract objects and classify to identify precise information on the object. The representative method to identify one's identity is face recognition that is caused a change in the recognition rate according to environmental factors such as illumination, background and angle of camera. In this paper, we analyze the robust face recognition of face image by changing the distance through a variety of experiments. The experiment was conducted by real face images of 1m to 5m. The method of face recognition based on Linear Discriminant Analysis show the best performance in average 75.4% when a large number of face images per one person is used for training. However, face recognition based on Convolution Neural Network show the best performance in average 69.8% when the number of face images per one person is less than five. In addition, rate of low resolution face recognition decrease rapidly when the size of the face image is smaller than $15{\times}15$.

• Restorative Dentistry and Endodontics
• /
• v.17 no.1
• /
• pp.36-54
• /
• 1992

The purpose of this study was to compare the shear bond strengths to ground dentin surfaces of four dentinal bonding agents in 193 teeth. Various dentin surfaces treated with four dentin bonding agents were attached with two restorative composite resins. The effectiveness of the bonding were tested by the monitoring the shear bond strength. The shear bond strengths were measured after 2 hours and 24 hours after surface conditioning with four dentin bonding agents. Effects of EDTA, the additive illumination, and sealer treatments without primer on bond strength to dentin surfaces were assessed. In addition the effects of the thickness of specimens ranging from 0.65 mm to 1.95 mm and the ratio of catalyst and base paste on the bond strength of chemical cure composite resin were estimated. The shear bond strength was determined by testing specimens in the Instron universal testing machine (Model No. 1122) at a crosshead speed of 1.0 mm/min. Following condusions were drawn: 1. The highest mean shear bond strengths of chemical cure composite resin to dentin conditioning with dentin bonding agents aged 2 hours were obtained, and then that was decreased with time followed by EDTA treatment. 2. In light cure composite resin, the shear bond strength was increased following dentin conditioning with bonding agents with time, irradiation time and EDTA treatment except in SB group. 3. The thicker the composite resin specimen was, the less the shear bond strength in chemical cure composite resin was. 4. In light cure composite resin, there was a little change in shear bond strength following dentin conditioning with bonding agents. 5. In chemical cure composite resin, the shear bond strength was the highest in the ratio of 1/1 of catalyst and base part. 6. Without a dentin primer, shear bond strength to dentin conditioned only with UB sealer was the highest among four sealers in light cure composite resin.

• International Journal of Highway Engineering
• /
• v.15 no.5
• /
• pp.111-122
• /
• 2013

PURPOSES : The purpose of this system (Rear Lighting System) is to provide illumination for the driver to operate the commercial vehicle safely after dark in highway, to increase the conspicuity of the vehicle, and especially be suggesting the finest observable improvement method, depending on color and pattern of rear lighting system of truck for midnight highway traffic. METHODS : Rear lightning system as an improving way for forward commercial vehicles lighting the securing sight from human factors and the surrounding environment in midnight driving. For this one, basic materials were collected from the data analysis about many types of problems, and filed investigation for establishing Driving Simulator. also taking statistic test to human volunteers after finding recognizable distance of them. RESULTS : As a result, color with the highest visuality is amber followed by green-red-blue as in order for all road types. Especially almost no difference is found between red and green, also when the light is turn off, recognizable distances is wide difference compared to turn on the light. One more thing about study per pattern, upper and entire lighting have similar recognizable distances, but under lighting shows short distance with difficulty securing sight from medians. And straight section shows similar recognizable distances. By finding visuality improvement method depending on color and pattern of supplement taillight, it is expected to suggest quantitative judgement standard for introducing regulation and improvement of supplement taillight. CONCLUSIONS : Night time vehicle conspicuity to the rear is provided by rear position lamps. this study is showed that the color of light ramp is not important to be safe driving, most important is to turn on the light, recognizable distances is big different compared to turn off the rear light, so when the drivng dark in highway, have to turn on the light for reducing risk.

• Conservation Science in Museum
• /
• v.18
• /
• pp.65-76
• /
• 2017

Following advances in technology and with the growing need for renewable energy, fluorescent and halogen lamps are being replaced by LED lighting in museum systems. This paper researched the setting of standards for the diverse lighting systems in addition to the LED lighting that are expected to be introduced in museums in the future. Contrary to previous belief, LEDs were shown to only barely emit in the ultraviolet region, but the visible rays were confirmed to produce discoloration depending on illuminance-hours. When the color change by LED lamps at the color temperature of 2800K, or warm white, was compared with 5500K, or white, the emission spectrum analysis confirmed that the blue spike increased at a higher color temperature and caused more discoloration. This suggests that in addition to illumination, color temperature should be considered by including the emission spectrum when museums set lighting environment standards.