• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.1
• /
• pp.41-49
• /
• 2022

This paper proposes a novel lane detection algorithm based on inverse perspective transformation and machine learning in lightweight embedded system. The inverse perspective transformation method is presented for obtaining a bird's-eye view of the scene from a perspective image to remove perspective effects. This method requires only the internal and external parameters of the camera without a homography matrix with 8 degrees of freedom (DoF) that maps the points in one image to the corresponding points in the other image. To improve the accuracy and speed of lane detection in complex road environments, machine learning algorithm that has passed the first classifier is used. Before using machine learning, we apply a meaningful first classifier to the lane detection to improve the detection speed. The first classifier is applied in the bird's-eye view image to determine lane regions. A lane region passed the first classifier is detected more accurately through machine learning. The system has been tested through the driving video of the vehicle in embedded system. The experimental results show that the proposed method works well in various road environments and meet the real-time requirements. As a result, its lane detection speed is about 3.85 times faster than edge-based lane detection, and its detection accuracy is better than edge-based lane detection.

• Current Optics and Photonics
• /
• v.7 no.5
• /
• pp.485-495
• /
• 2023

The pixel size in high-resolution complementary metal-oxide-semiconductor (CMOS) image sensors continues to shrink due to chip size limitations. However, the pixel pitch's miniaturization causes deterioration of optical performance. As one solution, a quad color filter (CF) array with pixel binning has been developed to enhance sensitivity. For high sensitivity, the microlens structure also needs to be optimized as the CF arrays change. In this paper, the covered microlens, which consist of four microlenses covered by one large microlens, are proposed for the quad CF array in the backside illumination pixel structure. To evaluate the optical performance, the suggested microlens structure was simulated from 0.5 ㎛ to 1.0 ㎛ pixels at the center and edge of the sensors. Moreover, all pixel structures were compared with and without in-pixel deep trench isolation (DTI), which works to distribute incident light uniformly into each photodiode. The suggested structure was evaluated with an optical simulation using the finite-difference time-domain method for numerical analysis of the optical characteristics. Compared to the conventional microlens, the suggested microlens show 29.1% and 33.9% maximum enhancement of sensitivity at the center and edge of the sensor, respectively. Therefore, the covered microlens demonstrated the highly sensitive image sensor with a quad CF array.

• Journal of the Institute of Convergence Signal Processing
• /
• v.17 no.1
• /
• pp.18-25
• /
• 2016

As more people have cars, the threat of traffic accidents is posed on men and women of all ages. The main culprit of traffic accidents is driving while intoxicated or drowsy. The method to recognize and prevent the cause of traffic accidents is to use lane detection. In this study, a total of 4,000 frames (day image: 2,900 frames, night image: 1,100 frames) were used to test lane detection. According to the test, in the case of day image, when the threshold of Sobel edge detection technique was detected with second-order differential equation, there was the highest candidate lane detection rate which was 86.1%. In the threshold of Canny edge detection technique, the highest detection rate of 88.0% was found at Low=50, and High=300. In the case of night image, the threshold of Sobel edge detection technique, when horizontal calculation and vertical calculation had second-order differential equation, and when horizontal-vertical calculation had 1.5th-order differential equation, there was the highest detection rate which was 83.1%. In the threshold of Canny edge detection technique, the highest detection rate of 89.9% was found at Low=50, and High=300.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.347-347
• /
• 2000

Nowadays, the Laser image is used to realize multi-media show for events, an advertising media and 3D simulation, realization of video image and so on. It is a hot issue to realize the laser image like computer graphic image. The image used in laser projector is vector graphic image that is described by linking point to point. A computer makes this continuous vector graphic images so that the image shows as an animation. A control signal converted by a computer makes the laser projector draw image. Two motors and universal joint are used to realize 2D laser image in this study. Developing a controller applied Look-ahead algorithm and software to interface with personal computer, This study is the chief aim of improving difference of moving velocity that is appeared from edge of vector graphic image and disparity of graphic density.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.23 no.3
• /
• pp.249-255
• /
• 2013

In this paper, we propose an algorithm to detect scale invariant object from IR image obtained in the sea environment. We create horizontal edge (HL), vertical edge (LH), diagonal edge (HH) of images through 2-D discrete Haar wavelet transform (DHWT) technique after noise reduction using morphology operations. Considering the sea environment, Gaussian blurring to the horizontal and vertical edge images at each level of wavelet is performed and then saliency map is generated by multiplying the blurred horizontal and vertical edges and combining into one image. Then we extract object candidate region by performing a binarization to saliency map. A small area in the object candidate region are removed to produce final result. Experiment results show the feasibility of the proposed algorithm.

• The Journal of the Korea Contents Association
• /
• v.13 no.10
• /
• pp.46-53
• /
• 2013

An inspection of nuclear fuel rods should be performed at remoteness from risks of high level radioactivity, and accuracy is required. Currently, inspection of the nuclear fuel rods is operated to monitor the video that recording an original nuclear fuel rods at remoteness because of the risks of radioactivity. In this paper, it is an implementation of the system was carried out in the process according to the image processing inspection of the nuclear fuel rods. The nuclear fuel rods are configured to use a bundle of plurality, in the image processing technology to verify this, the edge detection method is useful. We suggest to DoG technique to add threshold for the nuclear fuel rod edge detections. This is the new technique that optimized DoG. It is to deal with DoG and threshold to dual process. In this way, after detecting an edge of the nuclear fuel rods, by running a nuclear fuel rod inspection algorithm to determine the status of nuclear fuel rods. We applied the system using the new algorithm, and confirmed an excellent characteristic. In this study, it is considered to be able to be carried out more easily and securely inspect of nuclear fuel rods.

• Journal of Broadcast Engineering
• /
• v.18 no.1
• /
• pp.10-20
• /
• 2013

Nowadays, video technology has been successfully improved creating tremendous results. As video technology improve, multimedia devices and demands from users are diversified. Therefore, a video codec used in these devices should support various displays with different resolutions. The technology to generate a higher resolution image from the associated low-resolution image is called interpolation. Interpolation is generally performed in either the spatial domain or the DCT domain. To use the advantages of both domains, we have proposed the new adaptive interpolation algorithm based on edge direction, which adaptively exploits the advantages of both domains. The experimental results demonstrate that our algorithm performs well in terms of PSNR and reduces the blocking artifacts.

• The Journal of the Korea Contents Association
• /
• v.5 no.3
• /
• pp.123-131
• /
• 2005

Among the digital halftoning, the error diffusion halftoning gives better subjective quality than other halftoning techniques. But it also makes edges of objects blurred. To overcome the defect, this paper proposes the modified error diffusion halftoning algorithm to enhance the edges using the spatial perceptual properties of the human visual system. Using the properties that the human eyes perceive not the pixel's luminance itself but the local average luminance and the information that human eyes perceive spatial variation, the proposed method computes information of edge enhancement(IEE). The IEE is added to the quantizer's input pixel and feeds into the halftoning quantizer. The quantizer produces the halftone image having the enhanced edge. Also this paper proposes the technique that the coefficients of the error diffusion filter are adapted according to the correlation among color components. The computer simulation results show that the proposed method produces finer halftoning images than conventional methods due to the enhanced edges. And the proposed method also preserves similar in edges to original image and reduces some defects such as color impulse and false contours.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.4
• /
• pp.494-499
• /
• 2012

In this paper, a new method for detecting various objects that can be risks to safety navigation in sea environment is proposed. By analysing Infrared(IR) images obtained from various sea environments, we could find out that object regions include both horizontal and vertical direction edges while background regions of sea surface mainly include vertical direction edges. Therefore, we present an approach to detecting object regions considering horizontal and vertical edges. To this end, in the first step, image enhancement is performed by suppressing noises such as sea glint and complex clutters using a statistical filter. In the second step, a horizontal edge map and a vertical edge map are generated by 1-D Discrete Cosine Transform technique. Then, a combined map integrating the horizontal and the vertical edge maps is generated. In the third step, candidate object regions are detected by a adaptive thresholding method. Finally, exact object regions are extracted by eliminating background and clutter regions based on morphological operation.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.20 no.1
• /
• pp.63-71
• /
• 1983

A dye-edge tracking algorithm was used to determine the corresponding points in the two images(anterior-posterior and lateral) of the digital subtraction biplane angiography. This correspondence was used to reconstruct three dimensional images of cerebral artery in a dog experiment. The method was tested by comparing the measured image of oblique view with the computed reconstructed image. For the present study, we have developed three new algorithms. The first algorithm is to determine the corresponding dye-edge points using the fact the dye density at the moving edge avows the same changing pattern in the two projection views. This moving pattern of dye-edge density is computed using a matching method of cross-correlation for the two sequential frames' dye density. The second algorithm is for simplified perspective transformation, and the third one is to identify the specific corresponding points on the small vessels. The present method can be applied to compute the blood velocity using the dye-edge displacement and the three- dimensional distance data.