• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2012.05a
• /
• pp.155-157
• /
• 2012

In this paper, we propose a nonlinear 3D image correlator using computational reconstruction of 3D images based on integral imaging. In the proposed method, the elemental images for reference 3D object and target 3D object are recorded through the lens array. The recorded elemental images are reconstructed as reference plane image and target plane images using the computational integral imaging reconstruction algorithm and the nonolinear correlation between them is performed for object recognition. To show the usefulness of the proposed method, the preliminary experiments are carried out and the experimental results are presented compared with the conventional results.

• ETRI Journal
• /
• v.34 no.3
• /
• pp.466-469
• /
• 2012

In this letter, we propose a dual autostereoscopic display platform employing a natural interaction method, which will be useful for sharing visual data with users. To provide 3D visualization of a model to users who collaborate with each other, a beamsplitter is used with a pair of autostereoscopic displays, providing a visual illusion of a floating 3D image. To interact with the virtual object, we track the user's hands with a depth camera. The gesture recognition technique we use operates without any initialization process, such as specific poses or gestures, and supports several commands to control virtual objects by gesture recognition. Experiment results show that our system performs well in visualizing 3D models in real-time and handling them under unconstrained conditions, such as complicated backgrounds or a user wearing short sleeves.

• The Journal of Korea Robotics Society
• /
• v.1 no.2
• /
• pp.172-179
• /
• 2006

In this paper, we present a practical place and object recognition method for guiding visitors in building environments. Recognizing places or objects in real world can be a difficult problem due to motion blur and camera noise. In this work, we present a modeling method based on the bidirectional interaction between places and objects for simultaneous reinforcement for the robust recognition. The unification of visual context including scene context, object context, and temporal context is also. The proposed system has been tested to guide visitors in a large scale building environment (10 topological places, 80 3D objects).

• International conference on construction engineering and project management
• /
• 2020.12a
• /
• pp.399-408
• /
• 2020

The construction industry is suffering from aging workers, frequent accidents, as well as low productivity. With the rapid development of information technologies in recent years, automatic construction, especially automatic cranes, is regarded as a promising solution for the above problems and attracting more and more attention. However, in practice, limited by the complexity and dynamics of construction environment, manual inspection which is time-consuming and error-prone is still the only way to recognize the search object for the operation of crane. To solve this problem, an image-processing-based automated object recognition approach is proposed in this paper, which is a fusion of Convolutional-Neutral-Network (CNN)-based and traditional object detections. The search object is firstly extracted from the background by the trained Faster R-CNN. And then through a series of image processing including Canny, Hough and Endpoints clustering analysis, the vertices of the search object can be determined to locate it in 3D space uniquely. Finally, the features (e.g., centroid coordinate, size, and color) of the search object are extracted for further recognition. The approach presented in this paper was implemented in OpenCV, and the prototype was written in Microsoft Visual C++. This proposed approach shows great potential for the automatic operation of crane. Further researches and more extensive field experiments will follow in the future.

• 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 the Korea Society of Computer and Information
• /
• v.11 no.6 s.44
• /
• pp.279-287
• /
• 2006

This paper proposes a method to detect fall action by using stereo images to recognize emergency situation. It uses 3D information to extract the visual information for learning and testing. It uses HMM(Hidden Markov Model) as a recognition algorithm. The proposed system extracts background images from two camera images. It extracts a moving object from input video sequence by using the difference between input image and background image. After that, it finds the bounding rectangle of the moving object and extracts 3D information by using calibration data of the two cameras. We experimented to the recognition rate of fall action with the variation of rectangle width and height and that of 3D location of the rectangle center point. Experimental results show that the variation of 3D location of the center point achieves the higher recognition rate than the variation of width and height.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.12
• /
• pp.509-516
• /
• 2022

Accurate pose prediction of objects in 3D space is an important visual recognition technique widely used in many applications such as scene understanding in both indoor and outdoor environments, robotic object manipulation, autonomous driving, and augmented reality. Most previous works for object pose estimation have the limitation that they require an exact 3D CAD model for each object. Unlike such previous works, this paper proposes a novel neural network model that can predict the poses of unknown objects based on only their RGB color images without the corresponding 3D CAD models. The proposed model can obtain depth maps required for unknown object pose prediction by using an adaptive depth estimator, AdaBins,. In this paper, we evaluate the usefulness and the performance of the proposed model through experiments using benchmark datasets.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.422-424
• /
• 2021

In this paper, it leads the approach of fusing multiple RGB cameras for visual objects recognition based on deep learning with convolution neural network and 3D Light Detection and Ranging (LiDAR) to observe the environment and match into a 3D world in estimating the distance and position in a form of point cloud map. The goal of perception in multiple cameras are to extract the crucial static and dynamic objects around the autonomous vehicle, especially the blind spot which assists the AV to navigate according to the goal. Numerous cameras with object detection might tend slow-going the computer process in real-time. The computer vision convolution neural network algorithm to use for eradicating this problem use must suitable also to the capacity of the hardware. The localization of classified detected objects comes from the bases of a 3D point cloud environment. But first, the LiDAR point cloud data undergo parsing, and the used algorithm is based on the 3D Euclidean clustering method which gives an accurate on localizing the objects. We evaluated the method using our dataset that comes from VLP-16 and multiple cameras and the results show the completion of the method and multi-sensor fusion strategy.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2009.01a
• /
• pp.695-698
• /
• 2009

Three-dimensional (3D) shape recognition and distance recognition methods utilizing monocular camera systems have been required for field of virtual-reality, computer graphics, measurement technology and robot technology. There have been many studies regarding 3D shape and distance recognition based on geometric and optical information, and it is now possible to accurately measure the geometric information of an object at short range distances. However, these methods cannot currently be applied to long range objects. In the field of virtual-reality, all visual objects must be presented at widely varying ranges, even though some objects will be hazed over. In order to achieve distance recognition from a landscape image, we focused on the use of aerial perspective to simulate a type of depth perception and investigated the relationship between distance and color perception. The applicability of our proposed method was demonstrated in experimental results.

• 한국HCI학회:학술대회논문집
• /
• 2006.02b
• /
• pp.633-638
• /
• 2006

We investigated the importance and efficiency of active and passive exploration on the recognition of objects in a variety of virtual environments (VEs). In this study, 54 participants (19 males and 35 females) were randomly allocated into one of two navigation conditions (active and passive navigation). The 3D visual display was presented through HMD and participants used joysticks to navigate VEs. The VEs consisted of exploring four rooms (library, office, lounge, and conference room), each of which had 15 objects. 'Active navigation' was performed by allowing participants to self-pace and control their own navigation within a predetermined time limitation for each room. 'Passive navigation' was conducted by forced navigation of the four rooms in random order. Total navigation duration and objects for both navigations were identical. After navigating VEs, participants were asked to recognize the objects that had been in the four rooms. Recognition for objects was measured by response time and the percentage of correct, false, hit, and miss responses. Those in the active navigation condition had a significantly higher percentage of hit responses (t (52) = 4.000 p < 0.01), and a significantly lower percentage of miss responses (t (52) = -3.763, p < 0.01) in object recognition than those in the passive condition. These results suggest that active navigation plays an important role in spatial cognition as well as providing a better explanation about the efficiency of learning in a 3D-based program.