• Journal of Digital Convergence
• /
• v.14 no.2
• /
• pp.183-190
• /
• 2016

This paper proposes algorithm to reduce the computing time in a neural network that reduces transmission of data for tracking mobile objects in surveillance networks in terms of detection and communication load. Object Detection can be defined as follows : Given image sequence, which can forom a digitalized image, the goal of object detection is to determine whether or not there is any object in the image, and if present, returns its location, direction, size, and so on. But object in an given image is considerably difficult because location, size, light conditions, obstacle and so on change the overall appearance of objects, thereby making it difficult to detect them rapidly and exactly. Therefore, this paper proposes fast and exact object detection which overcomes some restrictions by using neural network. Proposed system can be object detection irrelevant to obstacle, background and pose rapidly. And neural network calculation time is decreased by reducing input vector size of neural network. Principle Component Analysis can reduce the dimension of data. In the video input in real time from a CCTV was experimented and in case of color segment, the result shows different success rate depending on camera settings. Experimental results show proposed method attains 30% higher recognition performance than the conventional method.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.46 no.2
• /
• pp.40-47
• /
• 2009

This paper proposes a method for vehicle license plate detection using mathematical morphology and symmetry. In general, the shape, color, size, and position of license plate are regulated by authorities for a better recognition by human. Among them, the relatively big intensity difference between the letter and the background region of the license plate and the symmetry about the plate are major discriminating factors for the detection. For the first, the opened image is subtracted from the closed image to intensify the region of plate using the rectangular structuring element which has the width of the distance between two characters. Second the subtraction image is average filtered with the mask size of the plate. Third, the column maximum graph of the average filtered image is acquired and the symmetry of the graph is measured at every position. Fourth, the peaks of the average filtered image are searched. Finally, the plate is assumed to be positioned around the one of local maxima nearest to the point of the highest symmetry. About 1,000 images taken by speed regulation camera are used for the experiment. The experimental result shows that the plate detection rate is about 93%.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.42 no.6
• /
• pp.133-140
• /
• 2005

This paper presents a rapid face shape acquisition system. The system is composed of two cameras and one projector. The technique works by projecting a pattern on the object and capturing two images with two cameras. We use a 'one shot' system which provides 3D data acquired by single image per camera. The system is good for rapid data acquisition as our purpose. We use the 'absolutely coded pattern' using the hue and saturation of pattern lines. In this 'absolutely coded pattern' all patterns have absolute identification numbers. We solve the correspondence problem between the two images by using epipolar geometry and absolute identification numbers. In comparison to the 'relatively coded pattern' which uses relative identification numbers, the 'absolutely coded pattern' helps obtain rapid 3D data by one to one point matching on an epipolar line. Because we use two cameras, we obtain two images which have similar hue and saturation. This enables us to have the same absolute identification numbers in both images, and we can use the absolutely coded pattern for solving the correspondence problem. The proposed technique is applied to face data and the total time for shape acquisition is estimated.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.10 no.6
• /
• pp.609-616
• /
• 2017

In this paper, we propose an algorithm to obtain more stable and high recognition rate by using left and right rotation information of input image in order to obtain a stable recognition rate in face recognition. The proposed algorithm uses the facial image as the input information in the web camera environment to reduce the size of the image and normalize the information about the brightness and color to obtain the improved recognition rate. We apply Principal Component Analysis (PCA) to the detected candidate regions to obtain feature vectors and classify faces. Also, In order to reduce the error rate range of the recognition rate, a set of data with the left and right $45^{\circ}$ rotation information is constructed considering the directionality of the input face image, and each feature vector is obtained with PCA. In order to obtain a stable recognition rate with the obtained feature vector, it is after scattered in the eigenspace and the final face is recognized by comparing euclidean distant distances to each feature. The PCA-based feature vector is low-dimensional data, but there is no problem in expressing the face, and the recognition speed can be fast because of the small amount of calculation. The method proposed in this paper can improve the safety and accuracy of recognition and recognition rate faster than other algorithms, and can be used for real-time recognition system.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.16 no.9
• /
• pp.6227-6235
• /
• 2015

The HUD has recently been downsized due to the development of micro display and LED technology as a see through information display device, gradually expands the application areas. In this paper, using a DLP micro display device designed a compact head-up display(HUD) optical system for biocular observation of the image exhibition area 5 inches. It was analyzed for each design element of the optical system in order to design a compacted HUD. DLP, projection optical system and concave image combiner were discussed the design approach and the characteristics. Through a connection structure analysis of each optical system, detailed design specifications were set up and designed the optical system in detail. Put a folded configuration in the form of a white diffuse reflector between the projection lens and concave image combiner was designed to be independent, respectively. Distance of the projected image is adjustable up to approximately 2m ~ infinity and observation distance is 1m. Resolution could be recognized by 1 ~ 2pixels in HD($1,280{\times}720pixels$) class, various characters and symbols could be read. In addition, color navigation map, daytime video camera and thermal imaging cameras can be displayed.

• Journal of Animal Environmental Science
• /
• v.15 no.2
• /
• pp.131-138
• /
• 2009

This study was conducted to find ways to control environment with the difference between body temperature and background temperature based on swine activity, and to apply to the environment control system of swine barns based on the findings. Following are the results. 1. Swine activity related to background temperature was achieved as color images and swine activity status was categorized into cold, comfortable, and hot periods with visualization system (thermal image system). 2. Thermal image system consisted of an infrared CCD camera, an image processing board - DIF (TH3100), an main computer (400Hz, 128M, 586 Pentium model) with C++ program installed. 3. Thermal image system categorizing temperatures into cold, comfortable, and hot was applicable to the environment control system of swine barns 4. Feed intake was higher in cold temperature, and finishing weight and weight gain per day in cold temperature were lower than others (p<0.05).

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.4
• /
• pp.358-365
• /
• 2017

In this paper, we propose an object recognition method using image information to improve the efficiency of visual servoingfor industrial manipulators in industry. This is an image-processing method for real-time responses to an abnormal situation or to external environment change in a work object by utilizing camera-image information of an industrial manipulator. The object recognition method proposed in this paper uses the Otsu method, a thresholding technique based on separation of the V channel containing color information and the S channel, in which it is easy to separate the background from the HSV channel in order to improve the recognition rate of the existing Harris Corner algorithm. Through this study, when the work object is not placed in the correct position due to external factors or from being twisted,the position is calculated and provided to the industrial manipulator.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.2
• /
• pp.127-133
• /
• 2021

A recent study of people physically falling focused on analyzing the motions of the falls using a recurrent neural network (RNN) and a deep learning approach to get good results from detecting 2D human poses from a single color image. In this paper, we investigate a detection method for estimating the position of the head and shoulder keypoints and the acceleration of positional change using the skeletal keypoints information extracted using PoseNet from an image obtained with a low-cost 2D RGB camera, increasing the accuracy of judgments about the falls. In particular, we propose a fall detection method based on the characteristics of post-fall posture in the fall motion-analysis method. A public data set was used to extract human skeletal features, and as a result of an experiment to find a feature extraction method that can achieve high classification accuracy, the proposed method showed a 99.8% success rate in detecting falls more effectively than a conventional, primitive skeletal data-use method.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_1
• /
• pp.1515-1526
• /
• 2022

Image-based 3D reconstruction is to restore the shape and color of real-world objects, and image sensors mounted on mobile platforms are used for positioning and mapping purposes in indoor and outdoor environments. Due to the increase in accidents in underground space, the location accuracy problem of underground spatial information has been raised. Image-based location estimation studies have been conducted with the advantage of being able to determine the 3D location and simultaneously identify internal damage from image data acquired from the inside of pipeline-type underground facilities. In this study, we studied 3D reconstruction based on the images acquired inside the pipe-type underground facility and reference data. An unmanned mobile system equipped with a stereo camera was used to acquire data and image data within a pipe-type underground facility where reference data were placed at the entrance and exit. Using the acquired image and reference data, the pipe-type underground facility is reconstructed to a geo-referenced 3D shape. The accuracy of the 3D reconstruction result was verified by location and length. It was confirmed that the location was determined with an accuracy of 20 to 60 cm and the length was estimated with an accuracy of about 20 cm. Using the image-based 3D reconstruction method, the position and line-shape of the pipe-type underground facility will be effectively updated.

• Journal of Advanced Information Technology and Convergence
• /
• v.9 no.1
• /
• pp.115-125
• /
• 2019

In this paper, the image is received from the camera and the lane is sensed. There are various ways to detect lanes. Generally, the method of detecting edges uses a lot of the Sobel edge detection and the Canny edge detection. The minimum use of multiplication and division is used when designing for the hardware configuration. The images are tested using a black box image mounted on the vehicle. Because the top of the image of the used the black box is mostly background, the calculation process is excluded. Also, to speed up, YCbCr is calculated from the image and only the data for the desired color, white and yellow lane, is obtained to detect the lane. The median filter is used to remove noise from images. Intermediate filters excel at noise rejection, but they generally take a long time to compare all values. In this paper, by using addition, the time can be shortened by obtaining and using the result value of the median filter. In case of the Sobel edge detection, the speed is faster and noise sensitive compared to the Canny edge detection. These shortcomings are constructed using complementary algorithms. It also organizes and processes data into parallel processing pipelines. To reduce the size of memory, the system does not use memory to store all data at each step, but stores it using four line buffers. Three line buffers perform mask operations, and one line buffer stores new data at the same time as the operation. Through this work, memory can use six times faster the processing speed and about 33% greater quantity than other methods presented in this paper. The target operating frequency is designed so that the system operates at 50MHz. It is possible to use 2157fps for the images of 640by360 size based on the target operating frequency, 540fps for the HD images and 240fps for the Full HD images, which can be used for most images with 30fps as well as 60fps for the images with 60fps. The maximum operating frequency can be used for larger amounts of the frame processing.