• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.5
• /
• pp.289-296
• /
• 2022

In this paper, we developed a deep learning-based recyclable object detection model. The model is developed based on YOLOv5 that is a one-stage detector. The deep learning model detects and classifies the recyclable object into 7 categories: paper, carton, can, glass, pet, plastic, and vinyl. We propose two methods for recyclable object detection models to solve problems during training. Bounding Box CutMix solved the no-objects training images problem of Mosaic, a data augmentation used in YOLOv5. Standardized Distance-based IoU replaced DIoU using a normalization factor that is not affected by the center point distance of the bounding boxes. The recyclable object detection model showed a final mAP performance of 0.91978 with Bounding Box CutMix and 0.91149 with Standardized Distance-based IoU.

• Journal of Korea Multimedia Society
• /
• v.20 no.6
• /
• pp.893-910
• /
• 2017

In this paper, we propose a simple online multiple object (human) tracking method, LKDeep (Lucas-Kanade feature and Detection based Simple Online Multiple Object Tracker), which can run in fast online enough on CPU core only with acceptable tracking performance for embedded surveillance purpose. The proposed LKDeep is a pragmatic hybrid approach which tracks multiple objects (humans) mainly based on LK features but is compensated by detection on periodic times or on necessity times. Compared to other state-of-the-art multiple object tracking methods based on 'Tracking-By-Detection (TBD)' approach, the proposed LKDeep is faster since it does not have to detect object on every frame and it utilizes simple association rule, but it shows a good object tracking performance. Through experiments in comparison with other multiple object tracking (MOT) methods using the public DPM detector among online state-of-the-art MOT methods reported in MOT challenge [1], it is shown that the proposed simple online MOT method, LKDeep runs faster but with good tracking performance for surveillance purpose. It is further observed through single object tracking (SOT) visual tracker benchmark experiment [2] that LKDeep with an optimized deep learning detector can run in online fast with comparable tracking performance to other state-of-the-art SOT methods.

• Journal of Institute of Control, Robotics and Systems
• /
• v.18 no.1
• /
• pp.35-41
• /
• 2012

This paper proposes a moving object detection algorithm for active camera system that can be applied to mobile robot and intelligent surveillance system. Most of moving object detection algorithms based on a stationary camera system. These algorithms used fixed surveillance system that does not consider the motion of the background or robot tracking system that track pre-learned object. Unlike the stationary camera system, the active camera system has a problem that is difficult to extract the moving object due to the error occurred by the movement of camera. In order to overcome this problem, the motion of the camera was compensated by using SURF and Pseudo Perspective model, and then the moving object is extracted efficiently using stochastic Label Cluster transport model. This method is possible to detect moving object because that minimizes effect of the background movement. Our approach proves robust and effective in terms of moving object detection in active camera system.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.40 no.9
• /
• pp.1828-1836
• /
• 2015

Object tracking algorithms can reduce computational cost by avoiding computation over the whole image through the selection of region of interests based on object detection. So, accurate object detection is an important task for object tracking. The background subtraction algorithm has been widely used in moving object detection using a stationary camera. However, it has the problem of object detection error due to incorrect background modeling, whereas the method of background modeling has been improved by many researches. This paper proposes a new moving object detection algorithm to overcome the drawback of the conventional background subtraction algorithm by combining the background subtraction algorithm with the motion history image algorithm that is usually used in gesture detection. Although the proposed algorithm demands more processing time because of time taken for combining two algorithms, it meet the real-time processing requirement. Moreover, experimental results show that it has higher accuracy compared with the previous two algorithms.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.10
• /
• pp.323-328
• /
• 2020

Recently, new approaches that significantly improve performance in object detection and recognition using deep learning technology have been proposed quickly. Of the various techniques for object detection, especially facial object detection (Faster R-CNN, R-CNN, YOLO, SSD, etc), SSD is superior in accuracy and speed to other techniques. At the same time, multiple object detection networks are also readily available. In this paper, among object detection networks, Mobilenet v2 network is used, models combined with SSDs are trained, and methods for detecting objects at a rate of four times or more than conventional performance are proposed using TensorRT engine, and the performance is verified through experiments. Facial object detector was created as an application to verify the performance of the proposed method, and its behavior and performance were tested in various situations.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.24 no.4
• /
• pp.392-400
• /
• 2021

Unlike optical equipment, SAR(Synthetic Aperture Radar) has the advantage of obtaining images in all weather, and object detection in SAR images is an important issue. Generally, deep learning-based object detection was mainly performed in real-valued network using only amplitude of SAR image. Since the SAR image is complex data consist of amplitude and phase data, a complex-valued network is required. In this paper, a complex-valued ResNet network is proposed. SAR image object detection was performed by combining the ROI transformer detector specialized for aerial image detection and the proposed complex-valued ResNet. It was confirmed that higher accuracy was obtained in complex-valued network than in existing real-valued network.

• Journal of Intelligence and Information Systems
• /
• v.28 no.1
• /
• pp.89-106
• /
• 2022

Recently, the amount of video data collected from smartphones, CCTVs, black boxes, and high-definition cameras has increased rapidly. According to the increasing video data, the requirements for analysis and utilization are increasing. Due to the lack of skilled manpower to analyze videos in many industries, machine learning and artificial intelligence are actively used to assist manpower. In this situation, the demand for various computer vision technologies such as object detection and tracking, action detection, emotion detection, and Re-ID also increased rapidly. However, the object detection and tracking technology has many difficulties that degrade performance, such as re-appearance after the object's departure from the video recording location, and occlusion. Accordingly, action and emotion detection models based on object detection and tracking models also have difficulties in extracting data for each object. In addition, deep learning architectures consist of various models suffer from performance degradation due to bottlenects and lack of optimization. In this study, we propose an video analysis system consists of YOLOv5 based DeepSORT object tracking model, SlowFast based action recognition model, Torchreid based Re-ID model, and AWS Rekognition which is emotion recognition service. Proposed model uses single-linkage hierarchical clustering based Re-ID and some processing method which maximize hardware throughput. It has higher accuracy than the performance of the re-identification model using simple metrics, near real-time processing performance, and prevents tracking failure due to object departure and re-emergence, occlusion, etc. By continuously linking the action and facial emotion detection results of each object to the same object, it is possible to efficiently analyze videos. The re-identification model extracts a feature vector from the bounding box of object image detected by the object tracking model for each frame, and applies the single-linkage hierarchical clustering from the past frame using the extracted feature vectors to identify the same object that failed to track. Through the above process, it is possible to re-track the same object that has failed to tracking in the case of re-appearance or occlusion after leaving the video location. As a result, action and facial emotion detection results of the newly recognized object due to the tracking fails can be linked to those of the object that appeared in the past. On the other hand, as a way to improve processing performance, we introduce Bounding Box Queue by Object and Feature Queue method that can reduce RAM memory requirements while maximizing GPU memory throughput. Also we introduce the IoF(Intersection over Face) algorithm that allows facial emotion recognized through AWS Rekognition to be linked with object tracking information. The academic significance of this study is that the two-stage re-identification model can have real-time performance even in a high-cost environment that performs action and facial emotion detection according to processing techniques without reducing the accuracy by using simple metrics to achieve real-time performance. The practical implication of this study is that in various industrial fields that require action and facial emotion detection but have many difficulties due to the fails in object tracking can analyze videos effectively through proposed model. Proposed model which has high accuracy of retrace and processing performance can be used in various fields such as intelligent monitoring, observation services and behavioral or psychological analysis services where the integration of tracking information and extracted metadata creates greate industrial and business value. In the future, in order to measure the object tracking performance more precisely, there is a need to conduct an experiment using the MOT Challenge dataset, which is data used by many international conferences. We will investigate the problem that the IoF algorithm cannot solve to develop an additional complementary algorithm. In addition, we plan to conduct additional research to apply this model to various fields' dataset related to intelligent video analysis.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.723-726
• /
• 2021

현재 단일 이미지에서 Object Detection 성능은 매우 좋은 편이다. 하지만 동영상에서는 처리 속도가 너무 느리고 임베디드 시스템에서는 real-time이 힘든 상황이다. 연구 논문에서는 하이엔드 GPU에서 다른 기능 없이 YOLO만 구동했을 때 real-time이 가능하다고 하지만 실제 사용자들은 상대적으로 낮은 사양의 GPU를 사용하거나 CPU를 사용하기 때문에 일반적으로는 자연스러운 real-time을 하기가 힘들다. 본 논문에서는 이러한 제한점을 해결하고자 계산량이 많은 Object Detection model 사용을 줄이는 방안은 제시하였다. 현재 Video영상에서 Object Detection을 수행할 때 매 frame마다 YOLO모델을 구동하는 것에서 YOLO 사용을 줄임으로써 계산 효율을 높였다. 본 논문의 알고리즘은 카메라가 움직이거나 배경이 바뀌는 상황에서도 사용이 가능하다. 속도는 최소2배에서 ~10배이상까지 개선되었다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.54-57
• /
• 2022

Korea has a vulnerable environment from the risk of wildfires, which causes great damage every year. To prevent this, a lot of manpower is being used, but the effect is insufficient. If wildfires are detected and extinguished early through artificial intelligence technology, damage to property and people can be prevented. In this paper, we studied the object double detection method with the goal of minimizing the data collection and processing process that occurs in the process of creating an object detection model to minimize the damage of wildfires. In YOLOv5, the original image is primarily detected through a single model trained on a limited image, and the object detected in the original image is cropped through Crop. The possibility of improving the false positive object detection rate was confirmed through the object double detection method that re-detects the cropped image.

• The Bulletin of The Korean Astronomical Society
• /
• v.46 no.2
• /
• pp.46.2-46.2
• /
• 2021

We present solar event auto detection using deep-learning-based object detection algorithms and DeepSDO event dataset. DeepSDO event dataset is a new detection dataset with bounding boxed as ground-truth for three solar event (coronal holes, sunspots and prominences) features using Solar Dynamics Observatory data. To access the reliability of DeepSDO event dataset, we compared to HEK data. We train two representative object detection models, the Single Shot MultiBox Detector (SSD) and the Faster Region-based Convolutional Neural Network (R-CNN) with DeepSDO event dataset. We compared the performance of the two models for three solar events and this study demonstrates that deep learning-based object detection can successfully detect multiple types of solar events. In addition, we provide DeepSDO event dataset for further achievements event detection in solar physics.