• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2014.06a
• /
• pp.109-111
• /
• 2014

본 논문에서는 비접촉 동작 인식 기기를 활용한 동영상 콘텐츠 검색 시스템을 소개한다. 제안하는 시스템은 스마트 TV와 같은 인터넷이 가능한 디스플레이의 동영상 콘텐츠를 대상으로 하며, 콘텐츠 자체 또는 콘텐츠 내의 객체에 대한 정보를 검색 결과로 제공한다. 시스템 구현에 앞서 영상 콘텐츠의 검색 요구 사항에 따라 시나리오 및 기능을 수립하고, 각각의 기능은 비접촉 동작 인식 기기인 립모션을 기반으로 손 동작을 지정하였다. 따라서, 제안하는 시스템은 사용자의 손가락 동작에 의해 선택된 영역을 모바일 비주얼 검색 서버에 전송하게 되고, 검색 결과는 모바일 기기를 통해 최종적으로 전달된다. 본 논문에서는 시스템을 실제로 구현하고 다양한 콘텐츠에 대하여 실험하였다. 개발된 시스템을 통해서 사용자는 손을 이용한 간단한 동작에 의해 콘텐츠 정보, 콘텐츠 내 객체의 정보를 실시간으로 모바일을 통해 제공받을 수 있다.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.6
• /
• pp.89-97
• /
• 2011

When examining current process of object tracking and search, objects were tracked by extracting them from image that was inputted through fixed single camera and objects were recognized through Zoom function to know detailed information on objects tracked. This study proposed system that expresses information on area that can seek and recognize object tracked as augmented reality by recognizing and seeking object by using multi camera. The result of experiment on proposed system showed that the number of pixels that was included in calculation was remarkably reduced and recognition rate of object was enhanced and time that took to identify information was shortened. Compared with existing methods, this system has advantage of better accuracy that can detect the motion of object and advantage of shortening time that took to detect motion.

• Journal of Internet Computing and Services
• /
• v.21 no.4
• /
• pp.117-126
• /
• 2020

A maritime object detection system is an intelligent assistance system to maritime autonomous surface ship(MASS). It detects automatically floating debris, which has a clash risk with objects in the surrounding water and used to be checked by a captain with a naked eye, at a similar level of accuracy to the human check method. It is used to detect objects around a ship. In the past, they were detected with information gathered from radars or sonar devices. With the development of artificial intelligence technology, intelligent CCTV installed in a ship are used to detect various types of floating debris on the course of sailing. If the speed of processing video data slows down due to the various requirements and complexity of MASS, however, there is no guarantee for safety as well as smooth service support. Trying to solve this issue, this study conducted research on the minimization of computation volumes for video data and the increased speed of data processing to detect maritime objects. Unlike previous studies that used the Hough transform algorithm to find the horizon and secure the areas of interest for the concerned objects, the present study proposed a new method of optimizing a binarization algorithm and finding areas whose locations were similar to actual objects in order to improve the speed. A maritime object detection system was materialized based on deep learning CNN to demonstrate the usefulness of the proposed method and assess the performance of the algorithm. The proposed algorithm performed at a speed that was 4 times faster than the old method while keeping the detection accuracy of the old method.

• Journal of Digital Convergence
• /
• v.14 no.2
• /
• pp.183-190
• /
• 2016

This paper proposes algorithm to reduce the computing time in a neural network that reduces transmission of data for tracking mobile objects in surveillance networks in terms of detection and communication load. Object Detection can be defined as follows : Given image sequence, which can forom a digitalized image, the goal of object detection is to determine whether or not there is any object in the image, and if present, returns its location, direction, size, and so on. But object in an given image is considerably difficult because location, size, light conditions, obstacle and so on change the overall appearance of objects, thereby making it difficult to detect them rapidly and exactly. Therefore, this paper proposes fast and exact object detection which overcomes some restrictions by using neural network. Proposed system can be object detection irrelevant to obstacle, background and pose rapidly. And neural network calculation time is decreased by reducing input vector size of neural network. Principle Component Analysis can reduce the dimension of data. In the video input in real time from a CCTV was experimented and in case of color segment, the result shows different success rate depending on camera settings. Experimental results show proposed method attains 30% higher recognition performance than the conventional method.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.3
• /
• pp.670-678
• /
• 2014

This paper presents a method to extract objects in radiographic images where all the allowable combinations of segmented regions are compared to a target object using Fourier descriptor. In the object extraction for usual images, a main problem is occlusion. In radiographic images, there is an advantage that the shape of an object is not occluded by other objects. It is because radiographic images represent the amount of radiation penetrated through objects. Considering the property of no occlusion in radiographic images, the shape based descriptors can be very effective to find objects. After all, the proposed object extraction method consists of three steps of segmenting regions, finding all the combinations of the segmented regions, and matching the combinations to the shape of the target object. In finding the combinations, we reduce a lot of computations to remove unnecessary combinations before matching. In matching, we employ Fourier descriptor so that the proposed method is rotation and shift invariant. Additionally, shape normalization is adopted to be scale invariant. By experiments, we verify that the proposed method works well in extracting objects.

• Tunnel and Underground Space
• /
• v.33 no.4
• /
• pp.281-298
• /
• 2023

Continuous research efforts are being devoted to unmanned mobile platforms for lunar exploration. There is an ongoing demand for real-time information processing to accurately determine the positioning and mapping of areas of interest on the lunar surface. To apply deep learning processing and analysis techniques to practical rovers, research on software integration and optimization is imperative. In this study, a foundational investigation has been conducted on real-time analysis of virtual lunar base construction site images, aimed at automatically quantifying spatial information of key objects. This study involved transitioning from an existing region-based object recognition algorithm to a boundary box-based algorithm, thus enhancing object recognition accuracy and inference speed. To facilitate extensive data-based object matching training, the Batch Hard Triplet Mining technique was introduced, and research was conducted to optimize both training and inference processes. Furthermore, an improved software system for object recognition and identical object matching was integrated, accompanied by the development of visualization software for the automatic matching of identical objects within input images. Leveraging satellite simulative captured video data for training objects and moving object-captured video data for inference, training and inference for identical object matching were successfully executed. The outcomes of this research suggest the feasibility of implementing 3D spatial information based on continuous-capture video data of mobile platforms and utilizing it for positioning objects within regions of interest. As a result, these findings are expected to contribute to the integration of an automated on-site system for video-based construction monitoring and control of significant target objects within future lunar base construction sites.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2012.01a
• /
• pp.63-64
• /
• 2012

본 논문은 보다 유연하고 추상적인 데이터를 사용자에게 전달하여 스스로가 물체를 인지하고 느낄 수 있도록 하는 공감각 현상에 대하여 연구하고 이 연구 결과를 응용하도록 한다. 오픈소스인 ReacTable을 이용하여 일종의 TAG 역할을 하는 특징적 그림을 명세코드화 한다. 그리고 이를 실제 숫자나 문자 혹은 객체 인식에 응용하도록 한다. 그리하여 시각적인 정보 없이 객체를 인식하고 사용할 수 있는 일상적인 생활이 가능하도록 하였다. 또한 가격이 이용가능성이 많으며 이동성과 휴대성을 동시에 고려한 ZigBee 무선 영상통신 기술을 통하여 영상을 서버나 휴대용단말기에 전송하는 방법을 사용하였다.

• 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.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2008.06a
• /
• pp.205-209
• /
• 2008

본 논문은 입력되는 영상에서 특정 객체를 찾기 위하여 특징 검출 및 매칭 결과를 분석하여 기술한다. 영상의 특징을 추출하는 방법 중 코너를 특징으로 하는 방법인 해리스 코너 검출(Harris corner detection)을 이용하여 코너를 추출하였으며, 추출한 특징을 이용하여 다양한 크기의 템플릿을 만들어 입력된 영상과 상관계수를 구해 최대값을 가지는 위치를 찾아 입력된 영상과 객체를 매칭 시킨 결과를 분석하였다. 본 논문의 연구 결과들은 객체의 탐지 등과 같은 영상 분석 기반 기술에 활용될 수 있으리라 기대된다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2001.04a
• /
• pp.135-138
• /
• 2001

증강현실 시스템을 구축하는데 있어 실시간 가상객체 위치 추적은 실세계와 가상객체를 정확하고 깊이감 있게 정합하고, 실세계 움직임에 따른 가상객체 위치변화 추적에 중요하다. 따라서 실시간 카메라 입력영상으로부터 가상객체의 위치를 추적하는데 있어 정확성과 함께 빠른 수행시간이 요구된다. 본 논문에서는 HMD(Head Mounted Display)장비에 장착된 두 개의 카메라로부터 관찰자의 시점 이동에 따른 가상객체 정합위치 정보를 입력받아 그 위치를 정확하게 인식하고 빠르게 추적하기 위하여 인위적인 랜드마크 형태를 정의하였으며, 실시간 입력영상으로부터 랜드마크 중심점 위치를 실시간으로 추적하기 위해 일정시간 간격마다 입력받은 첫 영상으로부터 얻은 랜드마크 영역 정보를 이용하여 중심점의 위치를 추적함으로써 수행시간을 줄이고자 하였다.