• Journal of Digital Contents Society
• /
• v.18 no.8
• /
• pp.1509-1516
• /
• 2017

In first-person perspective training system, the users needs realistic experience. For providing this experience, the system should offer the users virtual and real images at the same time. We propose an automatic a persons's arm segmentation and image composition method. It consists of arm segmentation part and image composition part. Arm segmentation uses an arbitrary image as input and outputs arm segment or alpha matte. It enables end-to-end learning because we make use of FCN in this part. Image composition part conducts image combination between the result of arm segmentation and other image like road, building, etc. To train the network in arm segmentation, we used arm images through dividing the videos that we took ourselves for the training data.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.12 no.1
• /
• pp.22-28
• /
• 2019

This paper presents a method for detection of an emergency signal expressed by arm gestures based on motion segmentation and face area detection in the surveillance system. The important indicators of emergency can be arm gestures and voice. We define an emergency signal as the 'Help Me' arm gestures in a rectangle around the face. The 'Help Me' arm gestures are detected by tracking changes in the direction of the horizontal motion vectors of left and right arms. The experimental results show that the proposed method successfully detects 'Help Me' emergency signal for a single person and distinguishes it from other similar arm gestures such as hand waving for 'Bye' and stretching. The proposed method can be used effectively in situations where people can't speak, and there is a language or voice disability.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2007.04a
• /
• pp.125-128
• /
• 2007

최근에 지능형 로봇분야에서 주위 카메라를 기반으로 실시간으로 환경인식 및 물체 추적 등 다양한 분야에서 연구가 활발히 진행되고 있다. 환경인식 및 물체 추적은 결국 배경과 관심물체를 분리하는 것이라고 볼 수 있는 데, 차 연산을 이용하여 물체의 움직임만을 배경으로 분리하는 방법과 물체인식을 통해 배경으로부터 분리하여 추적하는 방법에 대한 연구가 지속적으로 이루어지고 있다. 본 논문에서는 배경과 물체 사이에서 변화하는 색상의 변화를 퍼지기법을 이용하여 물체를 배경과 분리하여 실시간으로 물체를 추적하고자 한다. 실시간 물체 추적을 위해 전체영상에 대한 전역적 탐색을 통해 여러 후보 물체 중 관심물체를 배경에서 추출 후, 추출된 물체의 크기에 따른 지역탐색을 통하여 물체를 추적하는 방법이다. 그리고 본 논문에서는 ARM프로세서를 이용한 카메라시스템을 제작하여 실시간 추적을 실험하였다.

• The Journal of Korea Robotics Society
• /
• v.14 no.1
• /
• pp.31-39
• /
• 2019

A robot usually adopts ANN (artificial neural network)-based object detection and instance segmentation algorithms to recognize objects but creating datasets for these algorithms requires high labeling costs because the dataset should be manually labeled. In order to lower the labeling cost, a new scheme is proposed that can automatically generate a training images and label them for specific objects. This scheme uses an instance segmentation algorithm trained to give the masks of unknown objects, so that they can be obtained in a simple environment. The RGB images of objects can be obtained by using these masks, and it is necessary to label the classes of objects through a human supervision. After obtaining object images, they are synthesized with various background images to create new images. Labeling the synthesized images is performed automatically using the masks and previously input object classes. In addition, human intervention is further reduced by using the robot arm to collect object images. The experiments show that the performance of instance segmentation trained through the proposed method is equivalent to that of the real dataset and that the time required to generate the dataset can be significantly reduced.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.3
• /
• pp.368-373
• /
• 2007

In recent year s there have been increasing interests in real-time object tracking with image information. This dissertation presents a real-time object tracking method through the object recognition based on neural networks that have robust characteristics under various illuminations. This dissertation proposes a global search and a local search method to track the object in real-time. The global search recognizes a target object among the candidate objects through the entire image search, and the local search recognizes and track only the target object through the block search. This dissertation uses the object color and feature information to achieve fast object recognition. The experiment result shows the usefulness of the proposed method is verified.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.10 no.4
• /
• pp.674-679
• /
• 2006

In this paper a gesture recognition system using 3D feature data is described. The system relies on a novel 3D sensor that generates a dense range mage of the scene. The main novelty of the proposed system, with respect to other 3D gesture recognition techniques, is the capability for robust recognition of complex hand postures such as those encountered in sign language alphabets. This is achieved by explicitly employing 3D hand features. Moreover, the proposed approach does not rely on colour information, and guarantees robust segmentation of the hand under various illumination conditions, and content of the scene. Several novel 3D image analysis algorithms are presented covering the complete processing chain: 3D image acquisition, arm segmentation, hand -forearm segmentation, hand pose estimation, 3D feature extraction, and gesture classification. The proposed system is tested in an application scenario involving the recognition of sign-language postures.

• The Journal of Korea Robotics Society
• /
• v.4 no.2
• /
• pp.139-146
• /
• 2009

This paper describes how a person extracts a unknown object with pointing gesture while interacting with a robot. Using a stereo vision sensor, our proposed method consists of two stages: the detection of the operators' face, the estimation of the pointing direction, and the extraction of the pointed object. The operator's face is recognized by using the Haar-like features. And then we estimate the 3D pointing direction from the shoulder-to-hand line. Finally, we segment an unknown object from 3D point clouds in estimated region of interest. On the basis of this proposed method, we implemented an object registration system with our mobile robot and obtained reliable experimental results.

• Proceedings of the IEEK Conference
• /
• 2001.06d
• /
• pp.211-214
• /
• 2001

This paper presents an efficient fast motion estimation algorithm and image segmentation method for low bit-rate coding. First, with region split information, the algorithm splits the image having homogeneous and semantic regions like face and semantic regions in image. Then, in these regions, We find the motion vector using adaptive search window adjustment. Additionally, with this new segment based fast motion estimation, we reduce blocking artifacts by intensively coding our interesting region(face or arm) in input image. The simulation results show the improvement in coding performance and image quality.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2007.10a
• /
• pp.239-241
• /
• 2007

최근에 지능형 로봇분야에서 주위 카메라를 기반으로 실시간으로 환경인식 및 물체 추적 등 다양한 분야에서 연구가 활발히 진행되고 있다. 환경인식 및 물체 추적은 결국 배경과 관심물체를 분리하는 것이라고 볼 수 있는 데, 차 연산을 이용하여 물체의 움직임만을 배경으로 분리하는 방법과 물체인식을 통해 배경으로부터 분리하여 추적하는 방법에 대한 연구가 지속적으로 이루어지고 있다. 본 논문에서는 배경과 물체 사이에서 변화하는 색상의 변화를 퍼지기법을 이용하여 물체를 배경과 분리하여 실시간으로 물체를 추적하고자 한다. 실시간 물체 추적을 위해 전체영상에 대한 전역적 탐색을 통해 여러 후보 물체 중 관심물체를 배경에서 추출 후, 추출된 물체의 크기에 따른 지역탐색을 통하여 물체를 추적하는 방법이다. 그리고 본 논문에서는 ARM프로세서를 이용한 카메라시스템을 제작하여 실시간으로 영상분활을 실험하였다.

• Journal of Korea Multimedia Society
• /
• v.24 no.7
• /
• pp.860-867
• /
• 2021

Lane detection is important technology for implementing ADAS or autonomous driving. Although edge detection has been typically used for the lane detection however, false detections occur frequently. To improve this problem, a deep learning based lane detection algorithm is proposed in this paper. This algorithm is mounted on an ARM-based embedded system to implement a LDW(lane departure warning). Since the embedded environment lacks computing power, the VGG-11, a lightweight model based on VGG-13, has been proposed. In order to evaluate the performance of the LDW, the test was conducted according to the test scenario of NHTSA.