• Journal of IKEEE
• /
• v.25 no.2
• /
• pp.337-343
• /
• 2021

Deep reinforcement learning is an artificial intelligence algorithm that enables learners to select optimal behavior based on raw and, high-dimensional input data. A lot of research using this is being conducted to create an optimal movement path of a mobile robot in an environment in which obstacles exist. In this paper, we selected the Dueling Double DQN (D3QN) algorithm that uses the prioritized experience replay to create the moving path of mobile robot from the image of the complex surrounding environment. The virtual environment is implemented using Webots, a robot simulator, and through simulation, it is confirmed that the mobile robot grasped the position of the obstacle in real time and avoided it to reach the destination.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.47 no.6
• /
• pp.86-96
• /
• 2010

In this paper, we propose stereo vision-based obstacle detection and vehicle verification methods using U-disparity map and bird's-eye view mapping. First, we extract a road feature using maximum frequent values in each row and column. And we extract obstacle areas on the road using the extracted road feature. To extract obstacle areas exactly we utilize U-disparity map. We can extract obstacle areas exactly on the U-disparity map using threshold value which consists of disparity value and camera parameter. But there are still multiple obstacles in the extracted obstacle areas. Thus, we perform another processing, namely segmentation. We convert the extracted obstacle areas into a bird's-eye view using camera modeling and parameters. We can segment obstacle areas on the bird's-eye view robustly because obstacles are represented on it according to ranges. Finally, we verify the obstacles whether those are vehicles or not using various vehicle features, namely road contacting, constant horizontal length, aspect ratio and texture information. We conduct experiments to prove the performance of our proposed algorithms in real traffic situations.

• Journal of the Korean Society for information Management
• /
• v.22 no.3 s.57
• /
• pp.37-53
• /
• 2005

The terminology management is absolutely necessary for maintaining the efficiency of thesaurus. This is because the creating, differentiating, disappearing, and other processes of the descriptor become accomplished dynamically, making effective management of thesaurus a very difficult task. Therefore, a device is required for accomplishing methods to construct and maintain the thesaurus. This study proposes the methods to construct the thesaurus management using the basic elements of a topic map which are topic, occurrence, and association. Second, the study proposes the methods to represent the basic and specific instances using the systematic mapping algorithm and merging algorithm. Also, using a hub document as a standard, this study gives the methods to expand and subsitute the descriptors using the topic type. The new method applying fixed concept for double layer management on terms is developed, too. The purpose of this method is to fix the conceptual term which represents independent concept of time and space, and to select the descriptor freely by external information circumstance.

• Journal of KIISE:Computer Systems and Theory
• /
• v.32 no.1
• /
• pp.1-8
• /
• 2005

Image morphing to generate 2D transitions between images may be difficult even to express simple 3D transformations. In addition, previous view morphing method requires control points for postwarping, and is much affected by self- occlusion. This paper presents a new morphing algorithm that can generate automatically in-between scenes from un-calibrated images. Our algorithm rectifies input images based on the fundamental matrix, which is followed by linear interpolation with bilinear disparity map. In final, we generate in-between views by inverse mapping of homography between the rectified images. The proposed method nay be applied to photographs and drawings, because neither knowledge of 3D shape nor camera calibration, which is complex process generally, is required. The generated in-between views can be used in various application areas such as simulation system of virtual environment and image communication.

• Journal of KIISE:Software and Applications
• /
• v.35 no.12
• /
• pp.789-799
• /
• 2008

For the communication between human and computer in an interactive computing environment, the gesture recognition has been studied vigorously. The algorithms which use the 2D features for the feature extraction and the feature comparison are faster, but there are some environmental limitations for the accurate recognition. The algorithms which use the 2.5D features provide higher accuracy than 2D features, but these are influenced by rotation of objects. And the algorithms which use the 3D features are slow for the recognition, because these algorithms need the 3d object reconstruction as the preprocessing for the feature extraction. In this paper, we propose a method to extract the 3D features combined with the 3D object reconstruction in real-time. This method generates three kinds of 3D projection maps using the modified GPU-based visual hull generation algorithm. This process only executes data generation parts only for the gesture recognition and calculates the Hu-moment which is corresponding to each projection map. In the section of experimental results, we compare the computational time of the proposed method with the previous methods. And the result shows that the proposed method can apply to real time gesture recognition environment.

• Journal of KIISE:Computer Systems and Theory
• /
• v.32 no.1
• /
• pp.9-20
• /
• 2005

Recently, the MPEG-7 standard a multimedia content description standard is wide]y used for content based image/video retrieval systems. However, since the descriptors standardized in MPEG-7 are usually multidimensional and the problem called 'Curse of dimensionality', previously proposed indexing methods(for example, multidimensional indexing methods, dimensionality reduction methods, filtering methods, and so on) could not be used to effectively index the multimedia database represented in MPEG-7. This paper proposes an efficient multimedia data indexing mechanism reflecting the characteristics of MPEG-7 visual descriptors. In the proposed indexing mechanism, the descriptor is transformed into a histogram of some attributes. By representing the value of each bin as a binary number, the histogram itself that is a visual descriptor for the object in multimedia database could be represented as a bit string. Bit strings for all objects in multimedia database are collected to form an index file, bitmap index, in the proposed indexing mechanism. By XORing them with the descriptors for query object, the candidate solutions for similarity search could be computed easily and they are checked again with query object to precisely compute the similarity with exact metric such as Ll-norm. These indexing and searching mechanisms are efficient because the filtering process is performed by simple bit-operation and it reduces the search space dramatically. Upon experimental results with more than 100,000 real images, the proposed indexing and searching mechanisms are about IS times faster than the sequential searching with more than 90% accuracy.

• Journal of Korea Multimedia Society
• /
• v.10 no.2
• /
• pp.269-277
• /
• 2007

Network clustering has been proposed to provide that sensor nodes minimize energy and maximize a network lifetime by configuring clusters, Although dynamic clustering brings extra overhead like as head changing, head advertisement, it may diminish the gain in energy consumption to report attribute tasks by using cluster heads. Therefore, this paper proposes a new routing algorithm which configures cluster to reduce the number of messages when establishing paths and reports to the sink by way of cluster heads when responding sens ing tasks. All sensor nodes only broadcast bitmap once and maintain a bitmap table expressed by bits, allowing them to reduce node energy and to prolong the network lifetime. After broadcasting, each node only updates the bitmap without propagation when the adjacent nodes broad cast same query messages, This mechanism makes nodes to have abundant paths. By modifying the query which requests sensing tasks, the size of cluster is designed dynamically, We try to divide cluster by considering the number of nodes. Then, all nodes in a certain cluster must report to the sub- sink node, The proposed routing protocol finds easily an appropriate path to report tasks and reduces the number of required messages for the routing establishment, which sensor nodes minimize energy and maximize a network lifetime.

• The Journal of the Acoustical Society of Korea
• /
• v.39 no.1
• /
• pp.38-46
• /
• 2020

LOw Frequency Analysis Recording (LOFAR) and Demodulation of Envelop Modulation On Noise (DEMON) grams are bearing-time-frequency plots of underwater acoustic signals, to visualize features for passive sonar. Those grams are characterized by tonal components, for which conventional data coding methods are not suitable. In this work, a novel LOFAR/DEMON gram compression algorithm based on binary map and prediction methods is proposed. We first generate a binary map, from which prediction for each frequency bin is determined, and then divide a frame into several macro blocks. For each macro block, we apply intra and inter prediction modes and compute residuals. Then, we perform the prediction of available bins in the binary map and quantize residuals for entropy coding. By transmitting the binary map and prediction modes, the decoder can reconstructs grams using the same process. Simulation results show that the proposed algorithm provides significantly better compression performance on LOFAR and DEMON grams than conventional data coding methods.

• The KIPS Transactions:PartA
• /
• v.18A no.2
• /
• pp.75-80
• /
• 2011

Recently, many cleaning robots have been made with various algorithms for efficient cleaning. One of them is a DmaxCoverage algorithm which efficiently clean for the situation when the robot has a time limit. This algorithm uses Rectangle Tiling method for finding the biggest rectangle that doesn't have any obstacle. When the robot uses grid map, Rectangle Tiling method can find the optimal value. Rectangle Tiling method is to find all of the rectangles in the grid map. But when the grid map is big, it has a problem that spends a lot of times because of the large numbers of rectangles. In this paper, we propose Four Direction Rectangle Scanning(FDRS) method that has similar accuracy but faster than Rectangle Tiling method. FDRS method is not to find all of the rectangle, but to search the obstacle's all directions. We will show the FDRS method's performance by comparing of FDRS and Rectangle Tiling methods.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.6
• /
• pp.8-17
• /
• 2011

Recently, fusion camera systems that consist of depth sensors and color cameras have been widely developed with the advent of a new type of sensor, time-of-flight (TOF) depth sensor. The physical limitation of depth sensors usually generates low resolution images compared to corresponding color images. Therefore, the pre-processing module, such as camera calibration, three dimensional warping, and hole filling, is necessary to generate the high resolution depth map that is placed in the image plane of the color image. However, the result of the pre-processing step is usually inaccurate due to errors from the camera calibration and the depth measurement. Therefore, in this paper, we present a depth map upsampling method robust these errors. First, the confidence of the measured depth value is estimated by the interrelation between the color image and the pre-upsampled depth map. Then, the detailed depth map can be generated by the modified kernel regression method which exclude depth values having low confidence. Our proposed algorithm guarantees the high quality result in the presence of the camera calibration errors. Experimental comparison with other data fusion techniques shows the superiority of our proposed method.