• The Journal of Korea Robotics Society
• /
• v.6 no.3
• /
• pp.247-254
• /
• 2011

This paper presents a method of sonar grid map matching for topological place recognition. The proposed method provides an effective rotation invariant grid map matching method. A template grid map is firstly extracted for reliable grid map matching by filtering noisy data in local grid map. Using the template grid map, the rotation invariant grid map matching is performed by Ring Projection Transformation. The rotation invariant grid map matching selects candidate locations which are regarded as representative point for each node. Then, the topological place recognition is achieved by calculating matching probability based on the candidate location. The matching probability is acquired by using both rotation invariant grid map matching and the matching of distance and angle vectors. The proposed method can provide a successful matching even under rotation changes between grid maps. Moreover, the matching probability gives a reliable result for topological place recognition. The performance of the proposed method is verified by experimental results in a real home environment.

• Journal of the Korean housing association
• /
• v.23 no.5
• /
• pp.19-29
• /
• 2012

It is very necessary to know about child recognition of residential environment to plan and design an environment proper for children's growth and development. The research method using Cognitive Map, which may be defined as "an overall mental image of representation of the space and layout of a setting" can be a good tool for studying child recognition of residential environment. This study analyzed the child recognition of the size of home range, the number of residential environment elements, the types of Cognitive Map and the levels of Cognitive Map to understand the contents of child recognition about their residential environment. Subjects were 206 children in age6, 8 and 10 in Gwanju and Jeonnam area. As the result of the study, we found that 70% of child recognized 100~500 M as the size of home range, and that the number of the elements of residential environment was 7, average. And we also found that sequential map was more popular than spatial map in child's Cognitive Map type and that almost 60% of child respondents drew the Cognitive Map of level 1 complexity type. As the result of this study, we could know that the research method using Cognitive Map was very useful for understanding the child recognition of residential environment.

• Journal of Institute of Control, Robotics and Systems
• /
• v.17 no.1
• /
• pp.47-53
• /
• 2011

To enable the efficient operation of ITS, it is necessary to collect location data for vehicles on the road. In the case of futuristic transportation systems like ubiquitous transportation and smart highway, a method of data collection that is advanced enough to incorporate road lane recognition is required. To meet this requirement, technology based on radio frequency identification (RFID) has been researched. However, RFID may fail to yield accurate location information during high-speed driving because of the time required for communication between the tag and the reader. Moreover, installing tags across all roads necessarily incurs an enormous cost. One cost-saving alternative currently being researched is to utilize GNSS (global navigation satellite system) carrierbased location information where available. For lane recognition using GNSS, a precise digital map for determining vehicle position by lane is needed in addition to the carrier-based GNSS location data. A "precise digital map" is a map containing the location information of each road lane to enable lane recognition. At present, precise digital maps are being created for lane recognition experiments by measuring the lanes in the test area. However, such work is being carried out through comparison with vehicle driving information, without definitions being established for detailed performance specifications. Therefore, this study analyzes the performance requirements of a precise digital map capable of lane recognition based on the accuracy of GNSS location information and the accuracy of the precise digital map. To analyze the performance of the precise digital map, simulations are carried out. The results show that to have high performance of this system, we need under 0.5m accuracy of the precise digital map.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1994.06a
• /
• pp.1052-1057
• /
• 1994

Dynamically localized self-organizing map model (DLSMM) is a new speech recognition model based on the well-known self-organizing map algorithm and dynamic programming technique. The DLSMM can efficiently normalize the temporal and spatial characteristics of speech signal at the same time. Especially, the proposed can use contextual information of speech. As experimental results on ten Korean digits recognition task, the DLSMM with contextual information has shown higher recognition rate than predictive neural network models.

• International Journal of Internet, Broadcasting and Communication
• /
• v.9 no.1
• /
• pp.9-17
• /
• 2017

This paper describes a process of developing commercial real time image recognition system with company. In this paper we will make a system that is combining an empirical kernel map method and conjugate least squares support vector machine in order to represent images in a low-dimensional subspace for real time image recognition. In the traditional approach calculating these eigenspace models, known as traditional PCA method, model must capture all the images needed to build the internal representation. Updating of the existing eigenspace is only possible when all the images must be kept in order to update the eigenspace, requiring a lot of storage capability. Proposed method allows discarding the acquired images immediately after the update. By experimental results we can show that empirical kernel map has similar accuracy compare to traditional batch way eigenspace method and more efficient in memory requirement than traditional one. This experimental result shows that proposed model is suitable for commercial real time image recognition system.

• The Journal of Korea Robotics Society
• /
• v.3 no.1
• /
• pp.33-41
• /
• 2008

Based on object recognition technology, we present a new global localization method for robot navigation. For doing this, we model any indoor environment using the following visual cues with a stereo camera; view-based image features for object recognition and those 3D positions for object pose estimation. Also, we use the depth information at the horizontal centerline in image where optical axis passes through, which is similar to the data of the 2D laser range finder. Therefore, we can build a hybrid local node for a topological map that is composed of an indoor environment metric map and an object location map. Based on such modeling, we suggest a coarse-to-fine strategy for estimating the global localization of a mobile robot. The coarse pose is obtained by means of object recognition and SVD based least-squares fitting, and then its refined pose is estimated with a particle filtering algorithm. With real experiments, we show that the proposed method can be an effective vision- based global localization algorithm.

• Journal of the Institute of Convergence Signal Processing
• /
• v.4 no.3
• /
• pp.15-20
• /
• 2003

For some applications such as teleconference or telecommunication systems using a distant-talking hands-free microphone, the near-end speech signals to be transmitted is disturbed by an ambient noise and by an echo which is due to the coupling between the microphone and the loudspeaker. Furthermore, the environmental noise including channel distortion or additive noise is assumed to affect the original input speech. In the present paper, a new approach using echo canceller and maximum a posteriori(MAP) estimation is introduced to improve the accuracy of hands-free speech recognition. In this approach, it was shown that the proposed system was effective for hands-free speech recognition in ambient noise environment including echo. The experimental results also showed that the combination system between echo canceller and MAP environmental adaptation technique were well adapted to echo and noise environment.

• Spatial Information Research
• /
• v.2 no.2
• /
• pp.197-205
• /
• 1994

In this paper, we present a vectorization algorithm for finding a vector image from a raster image of the land registered map which is used as the base map for various applications, and an automatic region creation algorithm for generating every re¬gion automatically from the vector image. We describe an ARM (automatic geographical entity recognition and modeling software) which carries out the recognition and process¬ing of geographical entities automatically using those algorithms.

• ETRI Journal
• /
• v.37 no.6
• /
• pp.1220-1230
• /
• 2015

An autonomous valet parking (AVP) system is designed to locate a vacant parking space and park the vehicle in which it resides on behalf of the driver, once the driver has left the vehicle. In addition, the AVP is able to direct the vehicle to a location desired by the driver when requested. In this paper, for an AVP system, we introduce technology to recognize a parking space using image sensors. The proposed technology is mainly divided into three parts. First, spatial analysis is carried out using a height map that is based on dense motion stereo. Second, modelling of road markings is conducted using a probability map with a new salient-line feature extractor. Finally, parking space recognition is based on a Bayesian classifier. The experimental results show an execution time of up to 10 ms and a recognition rate of over 99%. Also, the performance and properties of the proposed technology were evaluated with a variety of data. Our algorithms, which are part of the proposed technology, are expected to apply to various research areas regarding autonomous vehicles, such as map generation, road marking recognition, localization, and environment recognition.

• Journal of the Korean Geophysical Society
• /
• v.9 no.2
• /
• pp.99-103
• /
• 2006

3D object recognition independent of translation and rotation using an ultrasonic sensor array, invariant moment vectors and SOFM(Self Organizing Feature Map) neural networks is presented. Using invariant moment vectors of the acquired 16×8 pixel data of square, rectangular, cylindric and regular triangular blocks, 3D objects could be classified by SOFM neural networks. Invariant moment vectors are constant independent of translation and rotation. The recognition rates for the training and testing data were 95.91% and 92.13%, respectively.