• Proceedings of the Korea Contents Association Conference
• /
• 2003.11a
• /
• pp.281-284
• /
• 2003

In this study, we have proposed the method of moving area detection as the preprocessing step of moving object tracking system. First, we catch the two frames which are different at time in image sequence. We obtain the moving area by using their binary differential image. In differential image, the object area of previous and current frame is present. In the tracking system, the background is changed by camera motion. So, in this case we have to decide which moving area of object is current at time. We obtain the binary edge image of current frame by applying a threshold to the output of an edge detector. Then we performed logical AND operation between the edge image and differential image. As a result of this work moving area of object can be detected.

• Annual Conference of KIPS
• /
• 2020.11a
• /
• pp.967-970
• /
• 2020

In a previous work we have done, we presented a monitoring system to automatically detect some dogs' behaviors from videos. However, the input video data used by that system was pre-trimmed to ensure it contained a dog only. In a real-life situation, the monitoring system would continuously receive video data, including frames that are empty and ones that contain people. In this paper, we propose a YOLOv4-based system for automatic object detection and trimming of dog videos. Sequences of frames trimmed from the video data received from the camera are analyzed to detect dogs and people frame by frame using a YOLOv4 model, and then records of the occurrences of dogs and people are generated. The records of each sequence are then analyzed through a rule-based decision tree to classify the sequence, forward it if it contains a dog only or ignore it otherwise. The results of the experiments on long untrimmed videos show that our proposed method manages an excellent detection performance reaching 0.97 in average of precision, recall and f-1 score at a detection rate of approximately 30 fps, guaranteeing with that real-time processing.

• Journal of Korea Multimedia Society
• /
• v.19 no.5
• /
• pp.865-873
• /
• 2016

In recent years, Tracking-Learning-Detection(TLD) system has been widely used as a detection and tracking algorithm for vision sensors. While conventional algorithms are vulnerable to occlusion, and changes in illumination and appearances, TLD system is capable of robust tracking by conducting tracking, detection, and learning in real time. However, the detection and tracking algorithms of TLD system utilize rotation-variant features, and the margin of tracking error becomes greater when an object makes a full out-of-plane rotation. Thus, we propose a rotation-invariant TLD system(RI-TLD). we propose a simplified average orientation histogram and rotation matrix for a rotation inference algorithm. Experimental results with various tracking tests demonstrate the robustness and efficiency of the proposed system.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.10 no.1
• /
• pp.158-164
• /
• 2009

The real time security system using web camera shall correspond in commensurate with it in real time through classifying moving object and analyzing the behavior. But, as to the detection of moving object in real time image through a camera, it is difficult to detect movement correctly according to the change of unnecessary noises, lighting conditions and screened phenomenon. This paper proposes real time security system by dual camera and ultrasonic sensor, a method of advanced detection in order to detect correct movement of specific object. That is, we could improve the tracing characteristics by using ultrasonic sensor as measurement factor of changed position and verify through experiments that the information interchanged between camera upwards and in front of it have effect on tracing a specific object continuously. The results of the experiment show that recognition rate of object was 97.4% and the correct tracing could be done lastingly in a phenomena of screening object.

• Proceedings of the KIEE Conference
• /
• 2003.11c
• /
• pp.400-403
• /
• 2003

This paper presents the signal processing of the panoramic thermal warning system that detects the small target such as aircraft and helicopter from afar. We develope the all round looking thermal imaging system which can scan all the way. This system acquires the panoramic images to reconstruct the IR images by revolving head of sensor typed line sensor at high speed. For detection, where the object of interest may be small, it is sometimes difficult to specify from object and background by conventional contrast enhancement methods. Therefore we use the adaptive plateau equalization algorithm each region to improve the contrast and make the hardware system which consists of the signal processing board for real-time display. We can verify the proposed method by the computer simulation and the hardware implementation.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.1
• /
• pp.91-99
• /
• 2020

For the shadow removal technology that is the base technology of the image detection system, real-time image processing has a problem that the processing speed is reduced due to the calculation complexity and it is also sensitive to illumination or light because shadows are removed only by the difference in brightness. Therefore, in this paper, we improved real-time performance by reducing the calculation complexity through the removal of the weighting part in order to solve the problem of the conventional system. In addition, we designed and evaluated an image detection system based on a shadow removal algorithm that could improve the shadow recognition rate using a vertical histogram. The evaluation results confirmed that the average speed increased by approximately 5.6ms and the detection rate improved by approximately 5.5%p compared to the conventional image detection system.

• Journal of Multimedia Information System
• /
• v.7 no.3
• /
• pp.205-214
• /
• 2020

Crime has become one of the major problems in modern society. Even though visual surveillances through closed-circuit television (CCTV) is extensively used for solving crime, the number of crimes has not decreased. This is because there is insufficient workforce for performing 24-hour surveillance. In addition, CCTV surveillance by humans is not efficient for detecting dangerous situations owing to accuracy issues. In this paper, we propose the autonomous detection of dangerous situations in CCTV scenes using a deep learning model with relational inference. The main feature of the proposed method is that it can simultaneously perform object detection and relational inference to determine the danger of the situations captured by CCTV. This enables us to efficiently classify dangerous situations by inferring the relationship between detected objects (i.e., distance and position). Experimental results demonstrate that the proposed method outperforms existing methods in terms of the accuracy of image classification and the false alarm rate even when object detection accuracy is low.

• Annual Conference of KIPS
• /
• 2023.05a
• /
• pp.461-463
• /
• 2023

본 연구는 실시간 MOT(Multiple-Object-Tracking)의 성능을 향상시키기 위해 다양한 기법을 적용한 MOT 모델을 설계한다. 연구에서 사용하는 Backbone 모델은 TBD(Tracking-by-Detection) 기반의 Tracking 모델을 사용한다. Heatmap Detection을 통해 객체를 검출하고 Transformer 기반의 Feature를 연결하여 Tracking 한다. 제안하는 방법은 Anchor 기반의 Detection의 장시간 문제와 추적 객체 정보 전달손실을 감소하여 실시간 객체 추적에 도움이 될 것으로 사료된다.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.26 no.2
• /
• pp.129-152
• /
• 2024

In the application of deep learning object detection via CCTV in tunnels, a large number of false positive detections occur due to the poor environmental conditions of tunnels, such as low illumination and severe perspective effect. This problem directly impacts the reliability of the tunnel CCTV-based accident detection system reliant on object detection performance. Hence, it is necessary to reduce the number of false positive detections while also enhancing the number of true positive detections. Based on a deep learning object detection model, this paper proposes a false positive data training method that not only reduces false positives but also improves true positive detection performance through retraining of false positive data. This paper's false positive data training method is based on the following steps: initial training of a training dataset - inference of a validation dataset - correction of false positive data and dataset composition - addition to the training dataset and retraining. In this paper, experiments were conducted to verify the performance of this method. First, the optimal hyperparameters of the deep learning object detection model to be applied in this experiment were determined through previous experiments. Then, in this experiment, training image format was determined, and experiments were conducted sequentially to check the long-term performance improvement through retraining of repeated false detection datasets. As a result, in the first experiment, it was found that the inclusion of the background in the inferred image was more advantageous for object detection performance than the removal of the background excluding the object. In the second experiment, it was found that retraining by accumulating false positives from each level of retraining was more advantageous than retraining independently for each level of retraining in terms of continuous improvement of object detection performance. After retraining the false positive data with the method determined in the two experiments, the car object class showed excellent inference performance with an AP value of 0.95 or higher after the first retraining, and by the fifth retraining, the inference performance was improved by about 1.06 times compared to the initial inference. And the person object class continued to improve its inference performance as retraining progressed, and by the 18th retraining, it showed that it could self-improve its inference performance by more than 2.3 times compared to the initial inference.

• Journal of Industrial Technology
• /
• v.38 no.1
• /
• pp.41-52
• /
• 2018

Recently, object detection is a critical function for any system that uses computer vision and is widely used in various fields such as video surveillance and self-driving cars. However, the conventional methods can not detect the objects clearly because of the dynamic background change in the beach. In this paper, we propose a new technique to detect humans correctly in the dynamic videos like shores. A new background modeling method that combines spatial GMM (Gaussian Mixture Model) and temporal GMM is proposed to make more correct background image. Also, the proposed method improve the accuracy of people detection by using SVM (Support Vector Machine) to classify people from the objects and KCF (Kernelized Correlation Filter) Tracker to track people continuously in the complicated environment. The experimental result shows that our method can work well for detection and tracking of objects in videos containing dynamic factors and situations.