• International conference on construction engineering and project management
• /
• 2015.10a
• /
• pp.671-672
• /
• 2015

Due to harsh conditions of disaster areas, understanding of current feature of collapsed buildings, terrain, and other infrastructures is critical issue for disaster managers. However, because of difficulties in acquiring the geographical information of the disaster site such as large disaster site and limited capability of rescue workers, comprehensive site investigation of current location of survivors buried under the remains of the building is not an easy task for disaster managers. To overcome these circumstances of disaster site, this study makes use of an unmanned aerial vehicle, commonly known as a drone to effectively acquire current image data from the large disaster areas. The framework of 3D model reconstruction of disaster site using aerial imagery acquired by drones was also presented. The proposed methodology is expected to assist rescue workers and disaster managers in achieving a rapid and accurate identification of survivors under the collapsed building.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.8
• /
• pp.2068-2082
• /
• 2023

With the rapid development of deep learning, Depth Map Super-Resolution (DMSR) method has achieved more advanced performances. However, when the upsampling rate is very large, it is difficult to capture the structural consistency between color features and depth features by these DMSR methods. Therefore, we propose a color-image guided DMSR method based on iterative depth feature enhancement. Considering the feature difference between high-quality color features and low-quality depth features, we propose to decompose the depth features into High-Frequency (HF) and Low-Frequency (LF) components. Due to structural homogeneity of depth HF components and HF color features, only HF color features are used to enhance the depth HF features without using the LF color features. Before the HF and LF depth feature decomposition, the LF component of the previous depth decomposition and the updated HF component are combined together. After decomposing and reorganizing recursively-updated features, we combine all the depth LF features with the final updated depth HF features to obtain the enhanced-depth features. Next, the enhanced-depth features are input into the multistage depth map fusion reconstruction block, in which the cross enhancement module is introduced into the reconstruction block to fully mine the spatial correlation of depth map by interleaving various features between different convolution groups. Experimental results can show that the two objective assessments of root mean square error and mean absolute deviation of the proposed method are superior to those of many latest DMSR methods.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2012.10a
• /
• pp.527-528
• /
• 2012

• Journal of Broadcast Engineering
• /
• v.27 no.3
• /
• pp.283-294
• /
• 2022

The feature map used in the network for deep learning generally has larger data than the image and a higher compression rate than the image compression rate is required to transmit the feature map. This paper proposes a method for transmitting a pyramid feature map with high compression rate, which is used in a network with an FPN structure that has robustness to object size in deep learning-based image processing. In order to efficiently compress the pyramid feature map, this paper proposes a structure that predicts a pyramid feature map of a level that is not transmitted with pyramid feature map of some levels that transmitted through the proposed prediction network to efficiently compress the pyramid feature map and restores compression damage through the proposed reconstruction network. Suggested mAP, the performance of object detection for the COCO data set 2017 Train images of the proposed method, showed a performance improvement of 31.25% in BD-rate compared to the result of compressing the feature map through VTM12.0 in the rate-precision graph, and compared to the method of performing compression through PCA and DeepCABAC, the BD-rate improved by 57.79%.

• Journal of the Korea Computer Graphics Society
• /
• v.27 no.3
• /
• pp.65-74
• /
• 2021

3D reconstruction means that reconstructing the 3D shape of the object in an image and a video. We proposed a progressive occupancy network architecture that can recover not only the overall shape of the object but also the local details. Unlike the original occupancy network, which uses a feature vector embedding information of the whole image, we extract and utilize the different levels of image features depending on the receptive field size. We also propose a novel network architecture that applies the image features sequentially to the decoder blocks in the decoder and improves the quality of the reconstructed 3D shape progressively. In addition, we design a novel decoder block structure that combines the different levels of image features properly and uses them for updating the input point feature. We trained our progressive occupancy network with ShapeNet. We compare its representation power with two prior methods, including prior occupancy network(ONet) and the recent work(DISN) that used different levels of image features like ours. From the perspective of evaluation metrics, our network shows better performance than ONet for all the metrics, and it achieved a little better or a compatible score with DISN. For visualization results, we found that our method successfully reconstructs the local details that ONet misses. Also, compare with DISN that fails to reconstruct the thin parts or occluded parts of the object, our progressive occupancy network successfully catches the parts. These results validate the usefulness of the proposed network architecture.

• Journal of the Korea Computer Industry Society
• /
• v.2 no.8
• /
• pp.1045-1054
• /
• 2001

To improve classification accuracy in this paper, we proposed an algorithm for the chromosome image reconstruction in the image preprocessing part and also proposed the pattern classification method using the hierarchical multilayer neural network(HMNN) to classify the chromosome karyotype. It reconstructed chromosome images for twenty normal human chromosome by the image reconstruction algorithm. The four morphological and ten density feature parameters were extracted from the 920 reconstructed chromosome images. The each combined feature parameters of ten human chromosome images were used to learn HMNN and the rest of them were used to classify the chromosome images. The experimental results in this paper were composed to optimized HMNN and also obtained about 98.26％ to recognition ratio.

• Journal of Information Display
• /
• v.6 no.4
• /
• pp.26-34
• /
• 2005

In this paper, a new rectification scheme to transform the uncalibrated stereo image pair into the calibrated one is suggested and its performance is analyzed by applying this scheme to the reconstruction of the intermediate views for multi-view stereoscopic display. In the proposed method, feature points are extracted from the stereo image pair by detecting the comers and similarities between each pixel of the stereo image pair. These detected feature points, are then used to extract moving vectors between the stereo image pair and the epipolar line. Finally, the input stereo image pair is rectified by matching the extracted epipolar line between the stereo image pair in the horizontal direction. Based on some experiments done on the synthesis of the intermediate views by using the calibrated stereo image pairs through the proposed rectification algorithm and the uncalibrated ones for three kinds of stereo image pairs; 'Man', 'Face' and 'Car', it is found that PSNRs of the intermediate views reconstructed from the calibrated images improved by about 2.5${\sim}$3.26 dB than those of the uncalibrated ones.

• Journal of Multimedia Information System
• /
• v.6 no.1
• /
• pp.15-22
• /
• 2019

There are many ways to perform face recognition. The first step of face recognition is the face detection step. If the face is not found in the first step, the face recognition fails. Face detection research has many difficulties because it can be varied according to face size change, left and right rotation and up and down rotation, side face and front face, facial expression, and light condition. In this study, facial features are extracted and the extracted features are geometrically reconstructed in order to improve face recognition rate in extracted face region. Also, it is aimed to adjust face angle using reconstructed facial feature vector, and to improve recognition rate for each face angle. In the recognition attempt using the result after the geometric reconstruction, both the up and down and the left and right facial angles have improved recognition performance.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.3
• /
• pp.1464-1480
• /
• 2019

Robust tracking of infrared (IR) pedestrian targets with various backgrounds, e.g. appearance changes, illumination variations, and background disturbances, is a great challenge in the infrared image processing field. In the paper, we address a new tracking method for IR pedestrian targets via multi-feature local sparse representation (SR), which consists of three important modules. In the first module, a multi-feature local SR model is constructed. Considering the characterization of infrared pedestrian targets, the gray and edge features are first extracted from all target templates, and then fused into the model learning process. In the second module, an effective tracker is proposed via the learned model. To improve the computational efficiency, a sliding window mechanism with multiple scales is first used to scan the current frame to sample the target candidates. Then, the candidates are recognized via sparse reconstruction residual analysis. In the third module, an adaptive dictionary update approach is designed to further improve the tracking performance. The results demonstrate that our method outperforms several classical methods for infrared pedestrian tracking.

• Korean Journal of Cognitive Science
• /
• v.11 no.2
• /
• pp.53-58
• /
• 2000

This paper reconstructs local region of a facial expression image from extracted feature points of facial expression image using FCM(Fuzzy C-Meang) clustering algorithm with Gabor wavelets. The feature extraction in a face is two steps. In the first step, we accomplish the edge extraction of main components of face using average value of 2-D Gabor wavelets coefficient histogram of image and in the next step, extract final feature points from the extracted edge information using FCM clustering algorithm. This study presents that the principal components of facial expression images can be reconstructed with only a few feature points extracted from FCM clustering algorithm. It can also be applied to objects recognition as well as facial expressions recognition.