• Journal of Korea Multimedia Society
• /
• v.24 no.11
• /
• pp.1508-1517
• /
• 2021

In CCTV environments, a lot of learning image data is required to monitor illegal dumping of garbage with a typical image-based object detection using deep learning method. In this paper, we propose a system to monitor unauthorized dumping of garbage by learning the articular points of the person using only a small number of images without immediate use of the image for deep learning. In experiment, the proposed system showed 74.97% of garbage dumping detection performance with only a relatively small amount of image data in CCTV environments.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.53 no.2
• /
• pp.62-69
• /
• 2016

This paper proposes to select Measure of Performance(MOP) for object attainment in the counterfire operation and deduce the reasonable combination of blue force's hitting resources satisfying MOP's optimal value and regression equation for the object achievement time. Also, in the study-methodological perspective, a series of procedures for drawing the regression equation from the real world is presented. Firstly the model was made by simplifying the weapon-system information of red force and blue force, then the time for object attainment was derived from its simulation. Simulating the model for the counterfire operation was divided into three phases-detection, decision and hitting. The probability method by applying the random numbers were used for detection, fixed constant numbers for decision and hitting. The simulation was repeatedly performed to get the minimum time for the object attainment against the fixed enemy, and it was estimated as the optimal value of simulation. From this result, the optimum combination of blue force's weapon system against the red force and finally, the regression equation were obtained by using the response surface analyzing method in MINITAB. Thereafter this equation was completely verified by using 'the 2-sample t-test.' As a result, the regression equation is suitable.

• Journal of Broadcast Engineering
• /
• v.25 no.6
• /
• pp.944-953
• /
• 2020

Object detection plays a crucial role in a self-driving system. With the advances of image recognition based on deep convolutional neural networks, researches on object detection have been actively explored. In this paper, we proposed a lightweight model of the mask R-CNN, which has been most widely used for object detection, to efficiently predict location and shape of various objects on the road environment. Furthermore, feature maps are adaptively re-calibrated to improve the detection performance by applying an attention module to the neural network layer that plays different roles within the mask R-CNN. Various experimental results for real driving scenes demonstrate that the proposed method is able to maintain the high detection performance with significantly reduced network parameters.

• International conference on construction engineering and project management
• /
• 2024.07a
• /
• pp.311-318
• /
• 2024

Quality control in construction projects necessitates the detection of defects during construction. Currently, this task is performed manually by site supervisors. This manual process is inefficient, labor-intensive, and prone to human error, potentially leading to decreased productivity. To address this issue, research has been conducted to automate defect detection using computer vision-based object detection technologies. However, these studies often suffer from a lack of data for training deep learning models, resulting in inadequate accuracy. This study proposes a method to improve the accuracy of deep learning models through the use of virtual image data. The target building is created as a 3D model and finished with materials similar to actual components. Subsequently, a virtual defect texture is produced by layering three types of images: defect information, area information, and material information images, to fabricate materials with defects. Images are generated by rendering the 3D model and the defect, and annotations are created for segmentation. This approach creates a hybrid dataset by combining virtual data with actual site image data, which is then used to train the deep learning model. This research was conducted on the tile process of finishing construction projects, focusing on cracks and falls as the target defects. The training results of the deep learning model show that the F1-Score increased by 12.08% for falls and cracks when using the hybrid dataset compared to the real image dataset alone, validating the hybrid data approach. This study contributes not only to unmanned and automated smart construction management but also to enhancing safety on construction sites. To establish an integrated smart quality management system, it is necessary to detect various defects simultaneously with high accuracy. Utilizing this method for automatic defect detection in other types of construction can potentially expand the possibilities for implementing an integrated smart quality management system.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.2337-2341
• /
• 2005

This paper presents the target detection method using Support Vector Machines(SVMs) and the navigation system using behavior-based fuzzy controller. SVM is a machine-learning method based on the principle of structural risk minimization, which performs well when applied to data outside the training set. We formulate detection of target objects as a supervised-learning problem and apply SVM to detect at each location in the image whether a target object is present or not. The behavior-based fuzzy controller is implemented as an individual priority behavior: the highest level behavior is target-seeking, the middle level behavior is obstacle-avoidance, the lowest level is an emergency behavior. We have implemented and tested the proposed method in our mobile robot "Pioneer2-AT". Comparing with a neural-network based detection method, a SVM illustrate the excellence of the proposed method.

• Proceedings of the Korean Institute Of Construction Engineering and Management
• /
• 2008.11a
• /
• pp.364-367
• /
• 2008

Earthwork is very equipment-intensive task and researches related to automated excavation have been conducted. There is an issue to secure the safety for an automated excavating system. Therefore, this paper focuses on how to improve safety for semi- or fully-automated backhoe excavation. The primary objective of this research is to develop object detection algorithm for automated safety system in excavation work. In order to satisfy the research objective, a diverse sensing technologies are investigated and analysed in terms of functions, durability, and reliability and verified its performance by several tests. The authors developed the objects detecting algorithm for user interface program using laser sensor. The results of this study would be the basis for developing the automated object detection system.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.1
• /
• pp.146-151
• /
• 2021

Currently, the demand for vehicles from one family is increasing in many countries at home and abroad, reducing the number of people on the vehicle and increasing the number of vehicles on the road. The multi-passenger lane system, which is available to solve the problem of traffic congestion, is being implemented. The system allows police to monitor fast-moving vehicles with their own eyes to crack down on illegal vehicles, which is less accurate and accompanied by the risk of accidents. To address these problems, applying deep learning object recognition techniques using images from road sites will solve the aforementioned problems. Therefore, in this paper, we compare and analyze the performance of existing deep learning models, select a deep learning model that can identify real-time vehicle occupants through video, and propose a vehicle occupancy detection algorithm that complements the object-ident model's problems.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2003.06a
• /
• pp.1055-1058
• /
• 2003

The robustness and reliability of vision algorithms is the key issue in robotic research and industrial applications. In this paper robust real time visual tracking in complex scene is considered. A common approach to increase robustness of a tracking system is the use of different model (CAD model etc.) known a priori. Also fusion or multiple features facilitates robust detection and tracking of objects in scenes of realistic complexity. Voting-based fusion of cues is adapted. In voting. a very simple or no model is used for fusion. The approach for this algorithm is tested in a 3D Cartesian robot which tracks a toy vehicle moving along 3D rail, and the Kalman filter is used to estimate the motion parameters. namely the system state vector of moving object with unknown dynamics. Experimental results show that fusion of cues and motion estimation in a tracking system has a robust performance.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2001.04a
• /
• pp.131-136
• /
• 2001

The purpose of this paper is to develop image inspection system endows an automatic operating and measuring that the moment values are invariant with respect to variable object size and rotation. In this paper, using these moment feature vector with Hu s 7 invariant moment is also given. The characteristics of section which is applied in the mechanics used moment descriptor of invariant moment detection algorithm for image inspection system. Corresponding rates between 94% and 96% have been achived for all object tested.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.63 no.6
• /
• pp.810-812
• /
• 2014

In this paper, a hagwon-bus boarding danger warning system based on computer vision is proposed to protect children from an accident causing injuries or death. Three zones are defined and different algorithms are applied to detect moving objects. In zone 1, a block-based entropy value is calculated using the absolute difference image generated by the absolute differential estimation between background image and incoming video frame. In zone 2, an effective and robust motion object tracking algorithm is performed based on the particle filter. Experimental results demonstrate the efficient and effectively of the algorithm for moving object inspection in each zone.