• Current Optics and Photonics
• /
• v.6 no.5
• /
• pp.463-472
• /
• 2022

At certain wavelengths, single-pixel imaging is considered to be a solution that can achieve high quality imaging and also reduce costs. However, achieving imaging of complex scenes is an overhead-intensive process for single-pixel imaging systems, so low efficiency and high consumption are the biggest obstacles to their practical application. Improving efficiency to reduce overhead is the solution to this problem. Salient object detection is usually used as a pre-processing step in computer vision tasks, mimicking human functions in complex natural scenes, to reduce overhead and improve efficiency by focusing on regions with a large amount of information. Therefore, in this paper, we explore the implementation of salient object detection based on single-pixel imaging after a single pixel, and propose a scheme to reconstruct images based on Fourier bases and use U²Net models for salient object detection.

• Journal of Information Processing Systems
• /
• v.18 no.4
• /
• pp.524-534
• /
• 2022

In this paper, we produce Trash Object Detection (TOD) dataset to solve trash detection problems. A well-organized dataset of sufficient size is essential to train object detection models and apply them to specific tasks. However, existing trash datasets have only a few hundred images, which are not sufficient to train deep neural networks. Most datasets are classification datasets that simply classify categories without location information. In addition, existing datasets differ from the actual guidelines for separating and discharging recyclables because the category definition is primarily the shape of the object. To address these issues, we build and experiment with trash datasets larger than conventional trash datasets and have more than twice the resolution. It was intended for general household goods. And annotated based on guidelines for separating and discharging recyclables from the Ministry of Environment. Our dataset has 10 categories, and around 33K objects were annotated for around 5K images with 1280×720 resolution. The dataset, as well as the pre-trained models, have been released at https://github.com/jms0923/tod.

• Journal of Information Processing Systems
• /
• v.18 no.4
• /
• pp.587-598
• /
• 2022

To increase building change recognition accuracy, we present a deep learning-based building change detection using remote sensing images. In the proposed approach, by merging pixel-level and object-level information of multitemporal remote sensing images, we create the difference image (DI), and the frequency-domain significance technique is used to generate the DI saliency map. The fuzzy C-means clustering technique pre-classifies the coarse change detection map by defining the DI saliency map threshold. We then extract the neighborhood features of the unchanged pixels and the changed (buildings) from pixel-level and object-level feature images, which are then used as valid deep neural network (DNN) training samples. The trained DNNs are then utilized to identify changes in DI. The suggested strategy was evaluated and compared to current detection methods using two datasets. The results suggest that our proposed technique can detect more building change information and improve change detection accuracy.

• Bulletin of the Korean Chemical Society
• /
• v.34 no.7
• /
• pp.1967-1971
• /
• 2013

Aim of our study is finding adsorbents suitable for pre-concentration of chemical warfare agents (CWAs). We considered Tenax, bare silica and polydimethylsiloxane (PDMS)-coated silica as adsorbents for dimethyl methylphosphonate (DMMP) and dipropylene glycol methyl ether (DPGME). Tenax showed lower thermal stability, and therefore, desorption of CWA simulants and decomposition of Tenax took place simultaneously. Silica-based adsorbents showed higher thermal stabilities than Tenax. A drawback of silica was that adsorption of CWA simulant (DMMP) was significantly reduced by pre-treatment of the adsorbents with humid air. In the case of PDMS-coated silica, influence of humidity for CWA simulant adsorption was less pronounced due to the hydrophobic nature of PDMS-coating. We propose that PDMS-coated silica can be of potential importance as adsorbent of CWAs for their pre-concentration, which can facilitate detection of these CWAs.

• Journal of Urban Science
• /
• v.11 no.2
• /
• pp.1-8
• /
• 2022

This study proposed how to identify window defects by using photos uploaded by occupants during the pre-handover inspection of mulch-family housing. A total of 1168 door images were acquired to generate training data and validation data. Subsequently, through the proposed algorithms, every pixel in images labeled a door was binarized using the OTSU threshold, and then dark pixels were identified as defects. Experimental results demonstrated that our computer vision-based defects identification method detects the door with a recall of 57.9%, and door defects with 63.6%. Although it is still a challenge to automatically identify building defects because of the distortion and brightness of photos, this study has the potential to support better defects management. Ultimately, the improved pre-handover inspection may lead to increased customer satisfaction.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.14 no.6
• /
• pp.1002-1008
• /
• 2011

The mine-detection system, which is one of the various mission equipments for Ground Vehicle System, detects mine under the ground. The mine detection sensors comprised of Metal Detection(MD) sensor and Ground Penetration Radar(GPR) are attached on the end of the multi-DOF manipulator. The manipulator moves the sensor to sweep mine areas keeping the pre-determined distance between the sensor and ground to enhance mine detection performance. The detection system can be operated automatically, semi-automatically and manually. When the detection system is operated automatically, the sensor should avoid collisions with unexpected obstacles which may exist on the ground. Two types of ultra-sonic sensors were developed for the mine detection sensor system to keep the appropriate gap between sensor and the ground to avoid the obstacles. Also, mine place marking device was developed.

• Journal of Korea Multimedia Society
• /
• v.19 no.8
• /
• pp.1345-1360
• /
• 2016

In this paper, we propose a new real-time human detection under omni-directional cameras for visual surveillance purpose, based on CNN with unified detection and AGMM. Compared to CNN-based state-of-the-art object detection methods. YOLO model-based object detection method boasts of very fast object detection, but with less accuracy. The proposed method adapts the unified detecting CNN of YOLO model so as to be intensified by the additional foreground contextual information obtained from pre-stage AGMM. Increased computational time incurred by additional AGMM processing is compensated by speed-up gain obtained from utilizing 2-D input data consisting of grey-level image data and foreground context information instead of 3-D color input data. Through various experiments, it is shown that the proposed method performs better with respect to accuracy and more robust to environment changes than YOLO model-based human detection method, but with the similar processing speeds to that of YOLO model-based one. Thus, it can be successfully employed for embedded surveillance application.

• Proceedings of the IEEK Conference
• /
• 2002.06b
• /
• pp.273-276
• /
• 2002

In this paper, we propose a bias random vector generator which can verify functions of microprocessor effectively. This generator is a pre-processor of assembly program, and defines pre-processor instructions which create random vector only in the pall which the designer wants to verify. Therefore, this generator shows higher detection ration than any other generators. And, we can cut down design costs because of shortening a Period for verifying function.

• Proceedings of the IEEK Conference
• /
• 2002.06b
• /
• pp.121-124
• /
• 2002

In this paper, we propose a bias random vector generator which can verify functions of microprocessor effectively. This generator is a pre-processor of assembly program, and defines pre-processor instructions which create random vector only in the part which the designer wants to verify. Therefore, this generator shows higher detection ration than any other generators. And, we can cut down design costs because of shortening a period for verifying function.

• Journal of the Korean Data and Information Science Society
• /
• v.18 no.3
• /
• pp.619-628
• /
• 2007

This study is devoted to suggesting the norm of detection abnormal users who are inferior to the other users in the recommender system compared with estimation accuracy. To select the abnormal users, we propose the pre-filtering method by using the preference ratings to the item rated by users. In this study, the experimental result shows the possibility of detecting the abnormal users before the process of preference estimation through the prediction algorithm. And It will be possible to improve the performance of the recommender system by using this detecting norm.