• Journal of Institute of Control, Robotics and Systems
• /
• v.21 no.7
• /
• pp.634-640
• /
• 2015

This paper proposes a novel three-dimensional mapping algorithm in Omni-Directional Vision SLAM based on a fisheye image and laser scanner data. The performance of SLAM has been improved by various estimation methods, sensors with multiple functions, or sensor fusion. Conventional 3D SLAM approaches which mainly employed RGB-D cameras to obtain depth information are not suitable for mobile robot applications because RGB-D camera system with multiple cameras have a greater size and slow processing time for the calculation of the depth information for omni-directional images. In this paper, we used a fisheye camera installed facing downwards and a two-dimensional laser scanner separate from the camera at a constant distance. We calculated fusion points from the plane coordinates of obstacles obtained by the information of the two-dimensional laser scanner and the outline of obstacles obtained by the omni-directional image sensor that can acquire surround view at the same time. The effectiveness of the proposed method is confirmed through comparison between maps obtained using the proposed algorithm and real maps.

• Journal of Korea Multimedia Society
• /
• v.22 no.2
• /
• pp.128-135
• /
• 2019

This paper presents a deep learning-based object detection method for recognizing vehicles in images acquired through cameras installed on ceiling of underground parking lot. First, we present an image enhancement method, which improves vehicle detection performance under dark lighting environment. Second, we present a new CNN-based multiscale classifiers for detecting vehicles in images acquired through cameras with fisheye lens. Experiments show that the presented vehicle detector has better performance than the conventional ones.

• Journal of Korea Multimedia Society
• /
• v.20 no.5
• /
• pp.769-781
• /
• 2017

Deep learning networks like Convolutional Neural Networks (CNNs) show successful performances in many computer vision applications such as image classification, object detection, and so on. For implementation of deep learning networks in embedded system with limited processing power and memory, deep learning network may need to be simplified. However, simplified deep learning network cannot learn every possible scene. One realistic strategy for embedded deep learning network is to construct a simplified deep learning network model optimized for the scene images of the installation place. Then, automatic training will be necessitated for commercialization. In this paper, as an intermediate step toward automatic training under fisheye camera environments, we study more precise human localization in fisheye images, and propose an accurate human localization method, Automatic Ground-Truth Labelling Method (AGTLM). AGTLM first localizes candidate human object bounding boxes by utilizing GoogLeNet-LSTM approach, and after reassurance process by GoogLeNet-based CNN network, finally refines them more correctly and precisely(tightly) by applying saliency object detection technique. The performance improvement of the proposed human localization method, AGTLM with respect to accuracy and tightness is shown through several experiments.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.11 no.11
• /
• pp.2116-2120
• /
• 2007

A realization for image distortion correction processing system with DSP processor is presented in this paper. The image distortion correcting algorithm is realized by DSP processor for focusing on more real time processing than image quality. The lens and camera distortion coefficients are processed by the Lookup Tables and the correcting algorithm is applied to reverse mapping method for geometrical transform. The system experimentation results in the processing time about 31.3 msec $720{\times}480$ wide range image, and the image is stable and spontaneous to be about 8.3% average PSNR variation with changing a wide angle.

• Korean Journal of Optics and Photonics
• /
• v.23 no.5
• /
• pp.179-188
• /
• 2012

Lenses with an ultra wide angle of view are usually called fisheye lenses since a fish can see an ultra wide panoramic view under water. As the angle of view for these kinds of lenses reaches a wide angle, the illumination on an image sensor is reduced by a rapid drop. In this paper, we discuss the causes and the ways to correct for a rapid drop. First, it is treated for the sign convention of directional cosine vectors and normal vectors on the curved surface by means of analytic geometry. And, from the fundamental discussion for these vectors, the rapid illumination drop is numerically analyzed for various kinds of causes by utilizing geometrical optics and radiometry as well as Fresnel equations derived from electromagnetic boundary conditions. As a result, we are able to get the full understanding for the rapid illumination drop and to propose ways to correct effects due to an wide angle of view.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.30 no.1
• /
• pp.14-20
• /
• 2016

The accurate analysis of the outside sky conditions is necessary to increase the efficiency of blind PV system. To conduct the accurate analysis, this paper suggested a method to analyze the sky condition using a specific image processing technique. While a fisheye lens has a wide field-of-views, it causes a large distortion to the sky images. Therefore, this paper calculated the exchange ratio of sky images to consider a lens distortion. As results of the study, there was a difference of 7% to cloud area ratio F4 and F11. Also, it had a different result depending on the position of the cloud.

• Proceedings of the Optical Society of Korea Conference
• /
• 2008.02a
• /
• pp.133-134
• /
• 2008

• Journal of Institute of Control, Robotics and Systems
• /
• v.20 no.8
• /
• pp.868-874
• /
• 2014

This paper proposes a novel mapping algorithm in Omni-directional Vision SLAM based on an obstacle's feature extraction using Lucas-Kanade Optical Flow motion detection and images obtained through fish-eye lenses mounted on robots. Omni-directional image sensors have distortion problems because they use a fish-eye lens or mirror, but it is possible in real time image processing for mobile robots because it measured all information around the robot at one time. In previous Omni-Directional Vision SLAM research, feature points in corrected fisheye images were used but the proposed algorithm corrected only the feature point of the obstacle. We obtained faster processing than previous systems through this process. The core of the proposed algorithm may be summarized as follows: First, we capture instantaneous $360^{\circ}$ panoramic images around a robot through fish-eye lenses which are mounted in the bottom direction. Second, we remove the feature points of the floor surface using a histogram filter, and label the candidates of the obstacle extracted. Third, we estimate the location of obstacles based on motion vectors using LKOF. Finally, it estimates the robot position using an Extended Kalman Filter based on the obstacle position obtained by LKOF and creates a map. We will confirm the reliability of the mapping algorithm using motion estimation based on fisheye images through the comparison between maps obtained using the proposed algorithm and real maps.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.10 no.2
• /
• pp.177-182
• /
• 2015

General method for correcting the distortion caused by the characteristic of the fish-eye lens may be classified in two ways. The first method is a calibration method using a mathematical model taking into account the characteristics of the lens, the second method is a method using only the distortion correction image, regardless of the lens. When considering the characteristics of the lens, calibration equation can be calculated geometrically from the relationship between the three-dimensional real-world coordinates and two-dimensional image coordinates and the parameters of lens. However, it is not suitable for ellipsoid type lens, because of existing research papers have been corrected on the spherical-type fisheye lens. In this paper, we propose a method for correcting geometrically using fish-eye lens as an ellipsoid model. Through a calibration picture, it can be seen that the proposed method is valid.

• Journal of Institute of Control, Robotics and Systems
• /
• v.21 no.8
• /
• pp.766-772
• /
• 2015

This paper proposes an object detection method based on motion estimation using background subtraction in the fisheye images obtained through omni-directional camera mounted on the vehicle. Recently, most of the vehicles installed with rear camera as a standard option, as well as various camera systems for safety. However, differently from the conventional object detection using the image obtained from the camera, the embedded system installed in the vehicle is difficult to apply a complicated algorithm because of its inherent low processing performance. In general, the embedded system needs system-dependent algorithm because it has lower processing performance than the computer. In this paper, the location of object is estimated from the information of object's motion obtained by applying a background subtraction method which compares the previous frames with the current ones. The real-time detection performance of the proposed method for object detection is verified experimentally on embedded board by comparing the proposed algorithm with the object detection based on LKOF (Lucas-Kanade optical flow).