• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.8
• /
• pp.3567-3582
• /
• 2020

Human activities are often affected by weather conditions. Automatic weather recognition is meaningful to traffic alerting, driving assistance, and intelligent traffic. With the boost of deep learning and AI, deep convolutional neural networks (CNN) are utilized to identify weather situations. In this paper, a three-channel convolutional neural network (3C-CNN) model is proposed on the basis of ResNet50.The model extracts global weather features from the whole image through the ResNet50 branch, and extracts the sky and ground features from the top and bottom regions by two CNN5 branches. Then the global features and the local features are merged by the Concat function. Finally, the weather image is classified by Softmax classifier and the identification result is output. In addition, a medium-scale dataset containing 6,185 outdoor weather images named WeatherDataset-6 is established. 3C-CNN is used to train and test both on the Two-class Weather Images and WeatherDataset-6. The experimental results show that 3C-CNN achieves best on both datasets, with the average recognition accuracy up to 94.35% and 95.81% respectively, which is superior to other classic convolutional neural networks such as AlexNet, VGG16, and ResNet50. It is prospected that our method can also work well for images taken at night with further improvement.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.5
• /
• pp.2156-2170
• /
• 2020

This paper presents a fire detection algorithm with a minimal false detection rate, intended for a thermal imaging surveillance environment, whose properties vary depending on temporal conditions of day or night and environmental changes. This algorithm was designed to minimize the false detection alarm rate while ensuring a high detection rate, as required in fire detection applications. It was necessary to reduce false fire detections due to non-flame elements occurring when existing fixed threshold-based fire detection methods were applied. To this end, adaptive flame thresholds that varied depending on the characteristics of input images, as well as the center of gravity of the heat-source and hot-source regions, were analyzed in an attempt to minimize such non-flame elements in the phase of selecting flame candidate blocks. Also, to remove any false detection elements caused by camera shaking, one of the most frequently raised issues at outdoor sites, preliminary decision thresholds were adaptively set to the motion pixel ratio of input images to maximize the accuracy of the preliminary decision. Finally, in addition to the preliminary decision results, the texture correlation and intensity of the flame candidate blocks were averaged for a specific period of time and tested for their conformity with the fire decision conditions before making the final decision. To verify the fire detection performance of the proposed algorithm, a total of ten test videos were subjected to computer simulation. As a result, the fire detection accuracy of the proposed algorithm was determined to be 94.24%, with minimum false detection, demonstrating its improved performance and practicality compared to previous fixed threshold-based algorithms.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.9
• /
• pp.77-85
• /
• 2011

In this paper, we propose an region segmentation and texture based feature extraction method which split the pavement and roadway from the camera which equipped to the visually impaired person during a walk. We perform the hough transformation method for detect the boundary between pavement and roadway, and devide the segmented region into 3-level according to perspective. Next step, split into pavement and roadway according to the extracted texture feature of segmented regions. Our walking assistance system use rotation-invariant LBP and GLCM texture features for compare the characteristic of pavement block with various pattern and uniformity roadway. Our proposed method show that can segment two regions with illumination invariant in day and night image, and split there regions rotation and occlution invariant in complexed outdoor image.

• Korean Journal of Cognitive Science
• /
• v.16 no.3
• /
• pp.175-188
• /
• 2005

Recently, Li, Brenner, Cornelissen and Kim (2002) reported that 2D shape perception during pursuit eye movement just reflected the retinal image, and this result implies that the visual system ignored the extra-retinal information. In reality, however, we usually do not experience the perceptual distottion of 2D shape during pursuit eye movement. One Possibility is that the visual system night exploit the fact that the relative location between objects on retinal image is constantly maintained even during pursuit eye movement. The present research examined this possibility. Interestingly, perceptual distortion of 2D shape was observed even in the presence of reference, however, the amount of distortion decreased compared to when the reference does not exist. The distance between the reference and the target affected the perceptual distortion. These results imply that reference information is used in 2D shape perception during pursuit eye movement but it cannot completely explain the stable and accurate representation of 2D shape perception during pursuit eye movement.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.10 no.3
• /
• pp.517-525
• /
• 2006

In this paper, the algorithm which improve the efficiency of surveillance in spite of the change of light is proposed and confirmed by virtue of the experiments. One of the problems for the implementation of visual surveillance system is the image processing technique to overcome with the variations of illumination lights. Some conventional systems are generally not considered the error due to the change of lights because the system use at indoor. In practical, the factors of bad image can be classified to the ghosts due to the reflection of lights and shadows in a scene. Especially weak images and noises at night are decreased the performance of visual surveillance system. In the paper, the filter which improve the images with some change of illumination lights is designed and the gabor filter is used for recognition and tracking of the moving objects. In the results, the system showed that the recognition and tracking were obtained $92\sim100%$ of recognition rate at daytime, but $80\sim90%$ of nighttime.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.34 no.4
• /
• pp.391-402
• /
• 2016

Among the various remote sensing sensors compared to the electro-optical sensors, SAR (Synthetic Aperture Radar) is very suitable for assessing damaged areas induced by disaster events owing to its all-weather day and night acquisition capability and sensitivity to geometric variables. The conventional CD (Change Detection) method that uses two-date data is typically used for mapping damage over extensive areas in a short time, but because data from only two dates are used, the information used in the conventional CD is limited. In this paper, we propose a novel CD method that is extended to use data consisting of two pre-disaster SAR data and one post-disaster SAR data. The proposed CD method detects changes by using a similarity weight image derived from the neighborhood information of a pixel in the data from the three dates. We conducted an experiment using three single polarization ALOS PALSAR (Advanced Land Observing Satellite/Phased Array Type L-Band) data collected over Miyagi, Japan which was seriously damaged by the 2011 east Japan tsunami. The results demonstrated that the mapping accuracy for damaged areas can be improved by about 26% with an increase of the g-mean compared to the conventional CD method. These improved results prove the performance of our proposed CD method and show that the proposed CD method is more suitable than the conventional CD method for detecting damaged areas induced by disaster.

• The Journal of the Korea Contents Association
• /
• v.13 no.10
• /
• pp.19-26
• /
• 2013

In the Malaysian license plates, alphabets and numerals which are made by plastic, are adhered to a frame as embossing style and occasionally characters in horizontal, vertical directions are aligned with narrow space. So the extraction of character stroke information can be hard in the vehicle images of low illumination intensity. In this paper, Malaysian license plate recognition algorithm for low illumination intensity image is proposed. DoG filtering based character stroke generation method is introduced to derive exact connected components of strokes in the vehicle image of low illumination intensity. After localization of plate by connected component analysis, characters are segmented and recognized. Algorithm is experimented for the 6,046 vehicle images captured in Kuala Lumpur by IR camera without using any special light during day and night. The experimental results show that recognition accuracy of plates is 96.1%.

• KIEAE Journal
• /
• v.4 no.2
• /
• pp.29-36
• /
• 2004

Designing outdoor lighting on landmarks has been activated in Korea since 2002 World Cup. And outdoor lighting has been important method to create nighttime activities. Especially, historic buildings which are illuminated by outdoor lighting expresses cultural beauty of the heritages in the region. Therefore, this study aims to analyze the outdoor lighting effect of historic buildings with particular reference to four historic buildings - Namdaemun, Kwanghwamun, Changanmun and Paltalmun. For the purpose, luminance of outdoor lighting are measured. Outdoor lighting of the historic buildings were mainly illuminated by the floodlights. In addition, up-lighting and accent lighting were used for expressing the bracket structure. Basements and rooflines are emphasized by floodlighting, and they represented the night image of historical buildings. For the subjective evaluation on the outdoor lighting of historic buildings, outdoor lighting images of four historic buildings - Namdaemun, Kwanghwamun, Changanmun and Paltalmun were photographed. Questionnaire surveys were conducted by hundred and twenty university students of architectural department And collected papers were statistically analyzed by SPSS. Factors that shows outdoor lighting images of historical buildings are as follows; atmosphere, clearness, intimacy, modelling. On the question of general impression of outdoor lighting, Kwanghwamun has got the most satisfactory responses and the next is Changanmun and Namdaemun, Paltalmun. Major variables which related to the 'general impression' of outdoor lighting for historic buildings have been 'dignity', 'match', 'elegance', 'beauty' in the order.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.45 no.5
• /
• pp.417-428
• /
• 2017

In this paper, we describe the architectural design, unit component hardware design and core software design(Helmet Pose Tracking Software and Terrain Elevation Data Correction Software) of IHDS(Intelligent Helmet Display System), and describe the results of unit test and integration test. According to the trend of the latest helmet display system, the specifications which includes 3D map display, FLIR(Forward Looking Infra-Red) display, hybrid helmet pose tracking, visor reflection type of binocular optical system, NVC(Night Vision Camera) display, lightweight composite helmet shell were applied to the design. Especially, we proposed unique design concepts such as the automatic correction of altitude error of 3D map data, high precision image registration, multi-color lighting optical system, transmissive image emitting surface using diffraction optical element, tracking camera minimizing latency time of helmet pose estimation and air pockets for helmet fixation on head. After completing the prototype of all system components, unit tests and system integration tests were performed to verify the functions and performance.

• Journal of the Institute of Convergence Signal Processing
• /
• v.12 no.1
• /
• pp.13-19
• /
• 2011

In this paper, a visual surveillance system using SOPC based NIOS II embedded processor and C2H compiler was implemented. In this system, the IP is constructed by C2H compiler for the output of the camera images, image processing, serial communication and network communication, then, it is implemented to effectively control each IP based on the SOPC and the NIOS II embedded processor. And, an algorithm which updates the background images for high speed and robust detection of the moving objects is proposed using the Adaptive Gaussian Mixture Model(AGMM). In results, it can detecte the moving objects(pedestrians and vehicles) under day-time and night-time. It is confirmed that the proposed AGMM algorithm has better performance than the Adaptive Threshold Method(ATM) and the Gaussian Mixture Model(GMM) from our experiments.