• The Journal of Korea Robotics Society
• /
• v.16 no.1
• /
• pp.49-55
• /
• 2021

Recently, a smart farm technology is drawing attention as an alternative to the decline of farm labor population problems due to the aging society. Especially, there is an increasing demand for automatic harvesting system that can be commercialized in the market. Pre-harvest crop detection is the most important issue for the harvesting robot system in a real-world environment. In this paper, we proposed a real-time tomato instance tracking algorithm by using deep learning and probability models. In general, It is hard to keep track of the same tomato instance between successive frames, because the tomato growing environment is disturbed by the change of lighting condition and a background clutter without a stochastic approach. Therefore, this work suggests that individual tomato object detection for each frame is conducted by YOLOv3 model, and the continuous instance tracking between frames is performed by Kalman filter and probability model. We have verified the performance of the proposed method, an experiment was shown a good result in real-world test data.

• Journal of Digital Contents Society
• /
• v.12 no.3
• /
• pp.279-289
• /
• 2011

The latest hardware and software techniques are combined to give safe walking guidance and convenient service of realtime walking assistance system for visually impaired person. This system consists of obstacle detection and perception, place recognition, and sign recognition for pedestrian can safely walking to arrive at their destination. In this paper, we exploit the sign object detection system in subway station for sign recognition that one of the important factors of walking assistance system. This paper suggest the adaptive feature map that can be robustly extract the sign object region from complexed environment with light and noise. And recognize a sign using fast zernike moment features which is invariant under translation, rotation and scale of object during walking. We considered three types of signs as arrow, restroom, and exit number and perform the training and recognizing steps through adaboost classifier. The experimental results prove that our method can be suitable and stable for real-time system through yields on the average 87.16% stable detection rate and 20 frame/sec of operation time for three types of signs in 5000 images of sign database.

• Journal of the HCI Society of Korea
• /
• v.1 no.1
• /
• pp.45-52
• /
• 2006

This paper presents an image-space algorithm to real-time collision detection, which is run completely by GPU. For a single object or for multiple objects with no collision, the front and back faces appear alternately along the view direction. However, such alternation is violated when objects collide. Based on these observations, the algorithm propose the depth peeling method which renders the minimal surface of objects, not whole surface, to find colliding. The Depth peeling method utilizes the state-of-the-art functionalities of GPU such as framebuffer object, vertexbuffer object, and occlusion query. Combining these functions, multi-pass rendering and context switch can be done with low overhead. Therefore proposed approach has less rendering times and rendering overhead than previous image-space collision detection. The algorithm can handle deformable objects and complex objects, and its precision is governed by the resolution of the render-target-texture. The experimental results show the feasibility of GPU-based collision detection and its performance gain in real-time applications such as 3D games.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.9
• /
• pp.1330-1339
• /
• 2022

3D object detection generally aims to detect relatively large data such as automobiles, buses, persons, furniture, etc, so it is vulnerable to small object detection. In addition, in an environment with limited resources such as embedded devices, it is difficult to apply the model because of the huge amount of computation. In this paper, the accuracy of small object detection was improved by focusing on local features using only one layer, and the inference speed was improved through the proposed knowledge distillation method from large pre-trained network to small network and adaptive quantization method according to the parameter size. The proposed model was evaluated using SUN RGB-D Val and self-made apple tree data set. Finally, it achieved the accuracy performance of 62.04% at mAP@0.25 and 47.1% at mAP@0.5, and the inference speed was 120.5 scenes per sec, showing a fast real-time processing speed.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.10 no.2
• /
• pp.13-20
• /
• 2014

In this paper, we implemented the object scanning with nxtOSEK which is an open source platform. nxtOSEK consists of device driver of leJOS NXJ C/Assembly source code, TOPPERS/ATK(Automotive real time Kernel) and TOPPERS/JSP Real-Time Operating System source code that includes ARM7 specific porting part, and glue code make them work together. nxtOSEK can provide ANSI C by using GCC tool chain and C API and apply for real-time multi tasking features. We experimented the 3D scanning with ultra sonic and laser sensor which are made directly by laser module diode and experimented the measurement of scanning the object by knowing x, y, and z coordinates for every points that it scans. In this paper, the laser module is the dimension of $6{\times}10[mm]$ requiring 5volts/5[mW], and used the laser light of wavelength in the 650[nm] range. For detecting the object, we used the beacon detection algorithm and as the laser light swept the objects, the photodiode monitored the ambient light at interval of 10[ms] which is called a real time. We communicated the 3D scanning platform via bluetooth protocol with host platform and the results are displayed via DPlot graphic tool. And therefore we enhanced the functionality of the 3D scanner for identifying the image scanning with laser sensor modules compared to ultra sonic sensor.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2005.11a
• /
• pp.209-212
• /
• 2005

This paper describes detection and tracking of a moving object for unmanned visual surveillance. security systems. Using images obtained from camera it detects and tracks a moving object and displays bounding box enclosing the moving object. The algorithm for detection and tracking is tested using a personal computer, and then implemented on EMPOS II embedded system. Simulation results show that the tracking of a moving object based on embedded system is working well. However it needs to improve image acquisition time for real time implementation to apply security systems.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.2
• /
• pp.25-33
• /
• 2019

In this paper, we propose an intelligent CCTV technology which is applied to a recent attracted attention real-time object detection technology in a disaster alarm system. Natural disasters are rapidly increasing due to climate change (global warming). Various disaster alarm systems have been developed and operated to solve this problem. In this paper, we detect object through Neuron Network algorithm and test the difference from existing SVM classifier. Experimental results show that the proposed algorithm overcomes the limitations of existing object detection techniques and achieves higher detection performance by about 15%.

• The Journal of Bigdata
• /
• v.7 no.2
• /
• pp.31-41
• /
• 2022

Steel is one of the most fundamental components to mechanical industry. However, the quality of products are greatly impacted by the surface defects in the steel. Thus, researchers pay attention to the need for surface defects detector and the deep learning methods are the current trend of object detector. There are still limitations and rooms for improvements, for example, related works focus on developing the models but don't take into account real-time application with practical implication on industrial settings. In this paper, a real-time application of steel surface defects detection based on YOLOv4 is proposed. Firstly, as the aim of this work to deploying model on real-time application, we studied related works on this field, particularly focusing on one-stage detector and YOLO algorithm, which is one of the most famous algorithm for real-time object detectors. Secondly, using pre-trained Yolov4-Darknet platform models and transfer learning, we trained and test on the hot rolled steel defects open-source dataset NEU-DET. In our study, we applied our application with 4 types of typical defects of a steel surface, namely patches, pitted surface, inclusion and scratches. Thirdly, we evaluated YOLOv4 trained model real-time performance to deploying our system with accuracy of 87.1 % mAP@0.5 and over 60 fps with GPU processing.

• Proceedings of the Korean Vacuum Society Conference
• /
• 2011.02a
• /
• pp.32-32
• /
• 2011

Plasma etching is used in microelectronic processing for patterning of micro- and nano-scale devices. Commonly, optical emission spectroscopy (OES) is widely used for real-time endpoint detection for plasma etching. However, if the viewport for optical-emission monitoring becomes blurred by polymer film due to prolonged use of the etching system, optical-emission monitoring becomes impossible. In addition, when the exposed area ratio on the wafer is small, changes in the optical emission are so slight that it is almost impossible to detect the endpoint of etching. For this reason, as a simple method of detecting variations in plasma without contamination of the reaction chamber at low cost, a method of measuring plasma impedance is being examined. The object in this research is to investigate the suitability of using plasma impedance monitoring (PIM) with statistical approach for real-time endpoint detection of $SiO_2$ etching. The endpoint was determined by impedance signal variation from I-V monitor (VI probe). However, the signal variation at the endpoint is too weak to determine endpoint when $SiO_2$ film on Si wafer is etched by fluorocarbon plasma on inductive coupled plasma (ICP) etcher. Therefore, modified principal component analysis (mPCA) is applied to them for increasing sensitivity. For verifying this method, detected endpoint from impedance analysis is compared with optical emission spectroscopy (OES). From impedance data, we tried to analyze physical properties of plasma, and real-time endpoint detection can be achieved.

• Journal of Korea Multimedia Society
• /
• v.17 no.1
• /
• pp.15-25
• /
• 2014

In this paper, we propose a loitering detection using trajectory probability distribution and local direction descriptor for intelligent surveillance system. We use a background modeling method for detecting moving object and extract the motion features from each moving object for making feature vectors. After that, we detect the loitering behavior person using K-Nearest Neighbor classifier. We test the proposed method in real world environment and it can achieve real time and robust detection results.