• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.12 no.4
• /
• pp.620-626
• /
• 2008

We propose a feature map method to detect a collision for a motion-based game. The feature map can be made an optimally reduced motion data using subtraction image and virtual ball images according to image size and condition. And we calculate the overlapped ratio between moving image data and objects. This ratio is an invariant for detection even though image size is changed. And we compare this ration with collision detection constant, the feature map can detect fast collisions as well as the collided direction. To evaluate the method, we implemented a motion-base game that consists of a web cam, a player, an enemy, and some virtual balls, and we obtained some valid results for our method for the collision detection. The results demonstrated that the proposed approach is robust, and they can be used as a basic collide detection algorithm for a motion-based game where the size and the position of characters are continuously changing.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.38C no.12
• /
• pp.1114-1125
• /
• 2013

License Plate Detection (LPD) is a key component in automatic license plate recognition system. Despite the success of License Plate Recognition (LPR) methods in the past decades, the problem is quite a challenge due to the diversity of plate formats and multiform outdoor illumination conditions during image acquisition. This paper aims at automatical detection of car license plates via image processing techniques. In this paper, we proposed a real-time and robust method for license plate detection using Heuristic Energy Map(HEM). In the vehicle image, the region of license plate contains many components or edges. We obtain the edge energy values of an image by using the box filter and search for the license plate region with high energy values. Using this energy value information or Heuristic Energy Map(HEM), we can easily detect the license plate region from vehicle image with a very high possibilities. The proposed method consists two main steps: Region of Interest (ROI) Detection and License Plate Detection. This method has better performance in speed and accuracy than the most of existing methods used for license plate detection. The proposed method can detect a license plate within 130 milliseconds and its detection rate is 99.2% on a 3.10-GHz Intel Core i3-2100(with 4.00 GB of RAM) personal computer.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.4
• /
• pp.1989-2011
• /
• 2019

Vehicle detection based on aerial images is an interesting and challenging research topic. Most of the traditional vehicle detection methods are based on the sliding window search algorithm, but these methods are not sufficient for the extraction of object features, and accompanied with heavy computational costs. Recent studies have shown that convolutional neural network algorithm has made a significant progress in computer vision, especially Faster R-CNN. However, this algorithm mainly detects objects in natural scenes, it is not suitable for detecting small object in aerial view. In this paper, an accurate and effective vehicle detection algorithm based on Faster R-CNN is proposed. Our method fuse a hyperactive feature map network with Eltwise model and Concat model, which is more conducive to the extraction of small object features. Moreover, setting suitable anchor boxes based on the size of the object is used in our model, which also effectively improves the performance of the detection. We evaluate the detection performance of our method on the Munich dataset and our collected dataset, with improvements in accuracy and effectivity compared with other methods. Our model achieves 82.2% in recall rate and 90.2% accuracy rate on Munich dataset, which has increased by 2.5 and 1.3 percentage points respectively over the state-of-the-art methods.

• Journal of the Korea Society of Computer and Information
• /
• v.8 no.2
• /
• pp.31-36
• /
• 2003

This paper proposes an acceleration method of PCA(Principal Component Analysis) based feature detection. The feature detection method makes decision whether the target feature is included in a given image, and if included, calculates the position and extent of the target feature. The position and scale of the target feature or face is not known previously, all the possible locations should be tested for various scales to detect the target. This is a search Problem in huge search space. This Paper proposes a fast face and feature detection method by reducing the search space using the multi-stage prediction map and contour Prediction map. A Proposed method compared to the existing whole search way, and it was able to reduce a computational complexity below 10％ by experiment.

• Journal of Auto-vehicle Safety Association
• /
• v.12 no.2
• /
• pp.33-39
• /
• 2020

This paper presents an Around View Monitoring (AVM) stop-line detection based longitudinal position correction algorithm for automated driving on urban roads. Poor positioning accuracy of low-cost GPS has many problems for precise path tracking. Therefore, this study aims to improve the longitudinal positioning accuracy of low-cost GPS. The algorithm has three main processes. The first process is a stop-line detection. In this process, the stop-line is detected using Hough Transform from the AVM camera. The second process is a map matching. In the map matching process, to find the corrected vehicle position, the detected line is matched to the stop-line of the HD map using the Iterative Closest Point (ICP) method. Third, longitudinal position of low-cost GPS is updated using a corrected vehicle position with Kalman Filter. The proposed algorithm is implemented in the Robot Operating System (ROS) environment and verified on the actual urban road driving data. Compared to low-cost GPS only, Test results show the longitudinal localization performance was improved.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.47-49
• /
• 2003

Automatic land use and land cover change (LUCC) detection via remotely sensed imagery has a wide application in the area of LUCC research, nature resource and environment monitoring and protection. Under the condition that one time (T1) data is existed land use and land cover maps, and another time (T2) data is remotely sensed imagery, how to detect change automatically is still an unresolved issue. This paper developed a land use and land cover class knowledge guided method for automatic change detection under this situation. Firstly, the land use and land cover map in T1 and remote sensing images in T2 were registered and superimposed precisely. Secondly, the remotely sensed knowledge database of all land use and land cover classes was constructed based on the unchanged parcels in T1 map. Thirdly, guided by T1 land use and land cover map, feature statistics for each parcel or pixel in RS images were extracted. Finally, land use and land cover changes were found and the change class was recognized through the automatic matching between the knowledge database of remote sensing information of land use & land cover classes and the extracted statistics in that parcel or pixel. Experimental results and some actual applications show the efficiency of this method.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.68 no.3
• /
• pp.471-479
• /
• 2019

This research proposes a indoor magnetic map matching algorithm that improves the position accuracy by employing multiple magnetic sensors and probabilistic candidate weighting function. Since the magnetic field is easily distorted by the surrounding environment, the distorted magnetic field can be used for position mapping, and multiple sensor configuration is useful to improve mapping accuracy. Nevertheless, the position error is likely to increase because the external magnetic disturbances have repeated pattern in indoor environment and several points have similar magnetic field distortion characteristics. Those errors cause large position error, which reduces the accuracy of the position detection. In order to solve this problem, we propose a method to reduce the error using multiple sensors and likelihood boundaries that uses human walking characteristics. Also, to reduce the maximum position error, we propose an algorithm that weights according to their importance. We performed indoor walking tests to evaluate the performance of the algorithm and analyzed the position detection error rate and maximum distance error. From the results we can confirm that the accuracy of position detection is greatly improved.

• Proceedings of the KSRS Conference
• /
• v.1
• /
• pp.368-371
• /
• 2006

A coastline is the boundary between land and ocean masses. Knowledge of coastline is essential for autonomous navigation, geographical exploration, coastal erosion monitoring and modelling, water line change, etc. Many methods have been researched to extract coastlines from the synthetic aperture radar (SAR) and optic images. Most methods were based on the intensity contrast between land and sea regions. However, in these methods, a coastline detection task was very difficult because of insufficient intensity contrast and the ambiguity in distinguishing coastline from other object line. In this paper, we propose an efficient method for the delineation of coastline using interferometric coherence values estimated from ERS tandem pair. The proposed method uses the facts that a tandem pair of ERS is acquired from a time interval of an accurate day and that the coherent and incoherent values in coherence map are land and water, respectively. The coherence map was generated from ERS tandem pair, filtered by MAP filter, and divided into land and water by the determination of threshold value that is based on the bimodality of the histogram. Finally, a coastline was detected by delineating the boundary pixels. There was a good visual match between the detected coastline and the manually contoured line. The interferometric coherence map will be helpful to identify land and water regions easily, and can be used to many applications that are related with a coastline.

• Journal of Veterinary Science
• /
• v.24 no.5
• /
• pp.70.1-70.14
• /
• 2023

Background: Mycobacterium avium subspecies paratuberculosis (MAP) causes a chronic and progressive granulomatous enteritis and economic losses in dairy cattle in subclinical stages. Subclinical infection in cattle can be detected using serum MAP antibody enzyme-linked immunosorbent assay (ELISA) and fecal polymerase chain reaction (PCR) tests. Objectives: To investigate the differences in blood parameters, according to the detection of MAP using serum antibody ELISA and fecal PCR tests. Methods: We divided 33 subclinically infected adult cattle into three groups: seronegative and fecal-positive (SNFP, n = 5), seropositive and fecal-negative (SPFN, n = 10), and seropositive and fecal-positive (SPFP, n = 18). Hematological and serum biochemical analyses were performed. Results: Although the cows were clinically healthy without any manifestations, the SNFP and SPFP groups had higher platelet counts, mean platelet volumes, plateletcrit, lactate dehydrogenase levels, lactate levels, and calcium levels but lower mean corpuscular volume concentration than the SPFN group (p < 0.017). The red blood cell count, hematocrit, monocyte count, glucose level, and calprotectin level were different according to the detection method (p < 0.05). The SNFP and SPFP groups had higher red blood cell counts, hematocrit and calprotectin levels, but lower monocyte counts and glucose levels than the SPFN group, although there were no significant differences (p > 0.017). Conclusions: The cows with fecal-positive MAP status had different blood parameters from those with fecal-negative MAP status, although they were subclinically infected. These findings provide new insights into understanding the mechanism of MAP infection in subclinically infected cattle.

• Transactions on Electrical and Electronic Materials
• /
• v.17 no.6
• /
• pp.363-368
• /
• 2016

Rectangular shape detection plays an important role in many image recognition systems. However, it requires continued research for its improved performance. In this study, we propose a strong rectangular shape detection algorithm, which combines the canny edge and line detection algorithms based on the perpendicularity and parallelism of a rectangle. First, we use the canny edge detection algorithm in order to obtain an image edge map. We then find the edge of the contour by using the connected component and find each edge contour from the edge map by using a DP (douglas-peucker) algorithm, and convert the contour into a polyline segment by using a DP algorithm. Each of the segments is compared with each other to calculate parallelism, whether or not the segment intersects the perpendicularity intersecting corner necessary to detect the rectangular shape. Using the perpendicularity and the parallelism, the four best line segments are selected and whether a determined the rectangular shape about the combination. According to the result of the experiment, the proposed rectangular shape detection algorithm strongly showed the size, location, direction, and color of the various objects. In addition, the proposed algorithm is applied to the license plate detecting and it wants to show the strength of the results.