• IEMEK Journal of Embedded Systems and Applications
• /
• v.19 no.2
• /
• pp.73-81
• /
• 2024

Recently, mobile manipulators have been utilized in agriculture industry for weed removal and harvest automation. This paper proposes a domain adaptive fruit detection method for harvest automation, by utilizing OWL-ViT model which is an open-vocabulary object detection model. The vision-language model can detect objects based on text prompt, and therefore, it can be extended to detect objects of undefined categories. In the development of deep learning models for real-world problems, constructing a large-scale labeled dataset is a time-consuming task and heavily relies on human effort. To reduce the labor-intensive workload, we utilized a large-scale public dataset as a source domain data and employed a domain adaptation method. Adversarial learning was conducted between a domain discriminator and feature extractor to reduce the gap between the distribution of feature vectors from the source domain and our target domain data. We collected a target domain dataset in a real-like environment and conducted experiments to demonstrate the effectiveness of the proposed method. In experiments, the domain adaptation method improved the AP50 metric from 38.88% to 78.59% for detecting objects within the range of 2m, and we achieved 81.7% of manipulation success rate.

• The Journal of Korean Institute of Information Technology
• /
• v.17 no.6
• /
• pp.103-114
• /
• 2019

Moving-target detection using frequency-modulated continuous-wave (FMCW) radar systems has recently attracted attention. Detection tasks are more challenging with noise resulting from signals reflected from strong static objects or small moving objects(clutter) within radar range. Robust Principal Component Analysis (RPCA) approach for FMCW radar to detect moving objects in noisy environments is employed in this paper. In detail, compensation and calibration are first applied to raw input signals. Then, RPCA via Gradient Descents (RPCA-GD) is adopted to model the low-rank noisy background. A novel update algorithm for RPCA is proposed to reduce the computation cost. Finally, moving-targets are localized using an Automatic Multiscale-based Peak Detection (AMPD) method. All processing steps are based on a sliding window approach. The proposed scheme shows impressive results in both processing time and accuracy in comparison to other RPCA-based approaches on various experimental scenarios.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.25 no.6
• /
• pp.679-689
• /
• 2014

In this paper, an analysis of the effect of time-variant reflected impedance and its detection method on wireless power transfer(WPT) systems are presented. The reflected resistance at WPT systems is very important parameter as it indicates how well matched antenna is and will exhibit high efficiency. Proposed detection method is based on transmitter current variation analysis with respect to frequency sweep. Using the proposed design method, a wireless power transfer system operating at the frequency of 125 kHz, is design and detect reflected impedance variation. The proposed design method provides good agreements between measured and simulated results. Therefore, The proposed detecting method provides a nonintrusive method to detect harmful object in WPT system.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.8 no.3
• /
• pp.92-99
• /
• 1999

The inspection unit which is developed and used in this study, is processed the shape data from the CCD camera to seek welding bite section shape, and then calculated as a real dimension from measuring the value of each inspection item. The reason of measuring with the real in this study is came out from the image method which used for a long time, which is extricated the characteristic as the dimension of pixel by recognize pixel. The measurement method of the section shape is that we decide the thresholding value after we drew the histogram to binarizate the object. After that, we make flat the object to get rid of the noise and measure the shape of welded part through the boundarization of the object. The shape measurement is that measure the value of the welding part to adapt the actual operation program from using the ratio between the actual dimension of the standard specimen and the dimension of image, to measure the ratio between the actual product and the camera image. The inspection algorithm which estimates the quality of welded product is developed and also, the software GUI(Graphic User Interface) which processes the automatic test function of the inspection system is developed. We make the foundation of the inspection automatic system and we will help to apply other welding machine.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.18 no.4
• /
• pp.1-11
• /
• 2022

Recently, research on license plate recognition, which is a core technology of an intelligent transportation system(ITS), is being actively conducted. In this paper, we propose a method to extract numbers and characters from low-quality license plate images by applying the YOLOv4 algorithm. YOLOv4 is a one-stage object detection method using convolution neural network including BACKBONE, NECK, and HEAD parts. It is a method of detecting objects in real time rather than the previous two-stage object detection method such as the faster R-CNN. In this paper, we studied a method to directly extract number and character regions from low-quality license plate images without additional edge detection and image segmentation processes. In order to evaluate the performance of the proposed method we experimented with 500 license plate images. In this experiment, 350 images were used for training and the remaining 150 images were used for the testing process. Computer simulations show that the mean average precision of detecting number and character regions on vehicle license plates was about 93.8%.

• Geomechanics and Engineering
• /
• v.33 no.2
• /
• pp.203-209
• /
• 2023

One major advantage of ground penetrating radar (GPR) over other field test methods is its ability to obtain subsurface images of roads in an efficient and non-intrusive manner. Not only can the strata of pavement structure be retrieved from the GPR scan images, but also various irregularities, such as cracks and internal cavities. This article introduces a deep learning-based approach, focusing on detecting subsurface cracks by recognizing their distinctive hyperbolic signatures in the GPR scan images. Given the limited road sections that contain target features, two data augmentation methods, i.e., feature insertion and generation, are implemented, resulting in 9,174 GPR scan images. One of the most popular real-time object detection models, You Only Learn One Representation (YOLOR), is trained for detecting the target features for two types of subsurface cracks: bottom cracks and full cracks from the GPR scan images. The former represents partial cracks initiated from the bottom of the asphalt layer or base layers, while the latter includes extended cracks that penetrate these layers. Our experiments show the test average precisions of 0.769, 0.803 and 0.735 for all cracks, bottom cracks, and full cracks, respectively. This demonstrates the practicality of deep learning-based methods in detecting subsurface cracks from GPR scan images.

• International Journal of Computer Science & Network Security
• /
• v.23 no.11
• /
• pp.67-72
• /
• 2023

In the past decade, Autonomous Vehicle Systems (AVS) have advanced at an exponential rate, particularly due to improvements in artificial intelligence, which have had a significant impact on social as well as road safety and the future of transportation systems. The fusion of light detection and ranging (LiDAR) and camera data in real-time is known to be a crucial process in many applications, such as in autonomous driving, industrial automation and robotics. Especially in the case of autonomous vehicles, the efficient fusion of data from these two types of sensors is important to enabling the depth of objects as well as the classification of objects at short and long distances. This paper presents classification of objects using CNN based vision and Light Detection and Ranging (LIDAR) fusion in autonomous vehicles in the environment. This method is based on convolutional neural network (CNN) and image up sampling theory. By creating a point cloud of LIDAR data up sampling and converting into pixel-level depth information, depth information is connected with Red Green Blue data and fed into a deep CNN. The proposed method can obtain informative feature representation for object classification in autonomous vehicle environment using the integrated vision and LIDAR data. This method is adopted to guarantee both object classification accuracy and minimal loss. Experimental results show the effectiveness and efficiency of presented approach for objects classification.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.47 no.2
• /
• pp.10-20
• /
• 2024

In recent automated manufacturing systems, compressed air-based pneumatic cylinders have been widely used for basic perpetration including picking up and moving a target object. They are relatively categorized as small machines, but many linear or rotary cylinders play an important role in discrete manufacturing systems. Therefore, sudden operation stop or interruption due to a fault occurrence in pneumatic cylinders leads to a decrease in repair costs and production and even threatens the safety of workers. In this regard, this study proposed a fault detection technique by developing a time-variant deep learning model from multivariate sensor data analysis for estimating a current health state as four levels. In addition, it aims to establish a real-time fault detection system that allows workers to immediately identify and manage the cylinder's status in either an actual shop floor or a remote management situation. To validate and verify the performance of the proposed system, we collected multivariate sensor signals from a rotary cylinder and it was successful in detecting the health state of the pneumatic cylinder with four severity levels. Furthermore, the optimal sensor location and signal type were analyzed through statistical inferences.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.400-403
• /
• 2021

Algorithms for predicting the optimal route of vehicles are being actively sudied with the recent development of autonomous driving technology. Companies such as SK, Kakao, and Naver provide services that navigate the optimal route. They predicts the optimal path with information from the users in real time. However, they can predict the optimal route, but not optimal lane route. We proposes a system that navigates the optimal lane path with coordinates data from vehicles using Lidar sensor. The proposed method is a system that guides smooth lanes by acquiring time series coordinate data of a vehicle after performing the Lidar-based object detection method. we demonstrates the performance using actual acquired data from the experimental results.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 1996.06b
• /
• pp.83-87
• /
• 1996

A virtual reality system using video image is designed and implemented. A participant having 2{{{{ { 1} over { 2} }}}}DOF can interact with the computer-generated virtual object using her/his full body posture and gesture in the 3D virtual environment. The system extracts the necessary participant-related information by video-based sensing, and simulates the realistic interaction such as collision detection in the virtual environment. The resulting scene obtained by compositing video image of the participant and virtual environment is updated in near real time.