Tracking by Detection of Multiple Faces using SSD and CNN Features

Do Nhu Tai,Soo-Hyung Kim,Guee-Sang Lee,Hyung-Jeong Yang,In-Seop Na,A-Ran Oh 한국스마트미디어학회 2018 스마트미디어저널 Vol.7 No.4

Multi-tracking of general objects and specific faces is an important topic in the field of computer vision applicable to many branches of industry such as biometrics, security, etc. The rapid development of deep neural networks has resulted in a dramatic improvement in face recognition and object detection problems, which helps improve the multiple-face tracking techniques exploiting the tracking-by-detection method. Our proposed method uses face detection trained with a head dataset to resolve the face deformation problem in the tracking process. Further, we use robust face features extracted from the deep face recognition network to match the tracklets with tracking faces using Hungarian matching method. We achieved promising results regarding the usage of deep face features and head detection in a face tracking benchmark.

Human Face Tracking and Modeling using Active Appearance Model with Motion Estimation

Tran, Hong Tai,Na, In Seop,Kim, Young Chul,Kim, Soo Hyung THE KOREAN INSTITUTE OF SMART MEDIA 2017 스마트미디어저널 Vol.6 No.3

Images and Videos that include the human face contain a lot of information. Therefore, accurately extracting human face is a very important issue in the field of computer vision. However, in real life, human faces have various shapes and textures. To adapt to these variations, A model-based approach is one of the best ways in which unknown data can be represented by the model in which it is built. However, the model-based approach has its weaknesses when the motion between two frames is big, it can be either a sudden change of pose or moving with fast speed. In this paper, we propose an enhanced human face-tracking model. This approach included human face detection and motion estimation using Cascaded Convolutional Neural Networks, and continuous human face tracking and modeling correction steps using the Active Appearance Model. A proposed system detects human face in the first input frame and initializes the models. On later frames, Cascaded CNN face detection is used to estimate the target motion such as location or pose before applying the old model and fit new target.

Tracking by Detection of Multiple Faces using SSD and CNN Features

Tai, Do Nhu,Kim, Soo-Hyung,Lee, Guee-Sang,Yang, Hyung-Jeong,Na, In-Seop,Oh, A-Ran THE KOREAN INSTITUTE OF SMART MEDIA 2018 스마트미디어저널 Vol.7 No.4

Multi-tracking of general objects and specific faces is an important topic in the field of computer vision applicable to many branches of industry such as biometrics, security, etc. The rapid development of deep neural networks has resulted in a dramatic improvement in face recognition and object detection problems, which helps improve the multiple-face tracking techniques exploiting the tracking-by-detection method. Our proposed method uses face detection trained with a head dataset to resolve the face deformation problem in the tracking process. Further, we use robust face features extracted from the deep face recognition network to match the tracklets with tracking faces using Hungarian matching method. We achieved promising results regarding the usage of deep face features and head detection in a face tracking benchmark.

Human Face Tracking and Modeling using Active Appearance Model with Motion Estimation

Hong Tai Tran,In Seop Na,Young Chul Kim,Soo Hyung Kim 한국스마트미디어학회 2017 스마트미디어저널 Vol.6 No.3

Images and Videos that include the human face contain a lot of information. Therefore, accurately extracting human face is a very important issue in the field of computer vision. However, in real life, human faces have various shapes and textures. To adapt to these variations, A model-based approach is one of the best ways in which unknown data can be represented by the model in which it is built. However, the model-based approach has its weaknesses when the motion between two frames is big, it can be either a sudden change of pose or moving with fast speed. In this paper, we propose an enhanced human face-tracking model. This approach included human face detection and motion estimation using Cascaded Convolutional Neural Networks, and continuous human face tracking and modeling correction steps using the Active Appearance Model. A proposed system detects human face in the first input frame and initializes the models. On later frames, Cascaded CNN face detection is used to estimate the target motion such as location or pose before applying the old model and fit new target.

인터랙티브 게임을 위한 색상정보 파티클필터 기반 얼굴추적 알고리즘

Mai Thanh Nhat Truong,김상훈(Sang Hoon Kim) 한국컴퓨터게임학회 2017 한국컴퓨터게임학회논문지 Vol.30 No.1

For several years, keyboard and mouse have been used as the main interacting devices between users and computer games, but they are becoming outdated. Gesture-based human-computer interaction systems are becoming more popular owing to the emergence of virtual reality and augmented reality technologies. Therefore research on these systems has attracted a significant attention. The researches focus on designing the interactive interfaces between users and computers. Human-computer interaction is an important factor in computer games because it affects not only the experience of the users, but also the design of the entire game. In this research, we develop an particle filter-based face tracking method using color distributions as features, for the purpose of applying to gesture-based human-computer interaction systems for computer games. The experimental results proved the efficiency of particle filter and color features in face tracking, showing its potential in designing human-computer interactive games.

Comparison of Face Tracking and Eye Tracking for Scrolling a Web Browser on Mobile Devices

Temiran Dzhoroev,Byounghern Kim,Hui Sung Lee 한국HCI학회 2022 한국HCI학회 학술대회 Vol.2022 No.2

Even though the technology for hands-free interaction is getting close to our lives, a practical way like scrolling and clicking has not been discovered. Instead, many researches focus on how the implementation was done rather than how much a hands-free system is helpful for the target context. This paper investigates the advanced method and the novel method for smartphone hands-free pointing and scrolling in usability. A camera-based head-tracking system is chosen for the advanced technique, and the eye-tracking system using a depth camera is selected for the novel method. A usability test is conducted with both techniques in terms of Fitts’ law test. The results show that the eye-tracking technique takes more time to scroll when the target distance increases, whereas consistent time is consumed with the face-tracking technique. We conclude that increasing the usability of hands-free interaction can be achieved by increasing the area of the scrolling zone and decreasing the area of the faster scrolling zone. Novel scrolling design and generalized techniques for hands-free scroll tasks can be studied in the future.

Human-Robot Interaction in Real Environments by Audio-Visual Integration

Hyun-Don Kim,Jong-Suk Choi,Munsang Kim 대한전기학회 2007 International Journal of Control, Automation, and Vol.5 No.1

In this paper, we developed not only a reliable sound localization system including a VAD (Voice Activity Detection) component using three microphones but also a face tracking system using a vision camera. Moreover, we proposed a way to integrate three systems in the human-robot interaction to compensate errors in the localization of a speaker and to reject unnecessary speech or noise signals entering from undesired directions effectively. For the purpose of verifying our system's performances, we installed the proposed audio-visual system in a prototype robot, called IROBAA (Intelligent ROBot for Active Audition), and demonstrated how to integrate the audio-visual system.

CCD 카메라와 적외선 카메라의 융합을 통한 효과적인 객체 추적 시스템

김승훈(Seung-Hun Kim),정일균(Il-Kyun Jung),박창우(Changwoo Park),황정훈(Jung-Hoon Hwang) 제어로봇시스템학회 2011 제어·로봇·시스템학회 논문지 Vol.17 No.3

To make a robust object tracking and identifying system for an intelligent robot and/or home system, heterogeneous sensor fusion between visible ray system and infrared ray system is proposed. The proposed system separates the object by combining the ROI(Region of interrest) estimated from two different images based on a heterogeneous sensor that consolidates the ordinary CCD camera and the IR (Infrared) camera. Human"s body and face are detected in both images by using different algorithms, such as histogram, optical-flow, skin-color model and Haar model. Also the pose of human body is estimated from the result of body detection in IR image by using PCA algorithm along with AdaBoost algorithm. Then, the results from each detection algorithm are fused to extract the best detection result. To verify the heterogeneous sensor fusion system, few experiments were done in various environments. From the experimental results, the system seems to have good tracking and identification performance regardless of the environmental changes. The application area of the proposed system is not limited to robot or home system but the surveillance system and military system.

Coordinated Task Execution by Humanoid Robot

Kang Geon Kim,Ji-Yong Lee,Seungsu Kim,Joongjae Lee,Mun-HoJeong,Chang Hwan Kim,Bum-Jae You 제어로봇시스템학회 2009 제어로봇시스템학회 국제학술대회 논문집 Vol.2009 No.8

This paper presents a framework for the coordinated task execution by a humanoid robot. To execute given tasks, various sub-systems of the robot need to be coordinated effectively. The goal of our paper is to develop the framework which makes it possible to inter act with humans while executing various tasks in daily life environmens. As cript is used as a tool for describing tasks to easily regulate actions of the sub-systems while the robot is performing the task. The performance of the presented framework is experimentally demonstrated as follows: A mobile robot, as the platform of the task execution, recognizes the designated object. The object pose is calculated by performing model-based object tracking using aparticle filter with back projection-based sampling. An approach proposed by Kimetal.[1] is used to solve a human-like arm inverse kinematics and then the control system generates smooth trajectories for each joint of the humanoid robot. The mean-shift algorithm using bilateral filtering is also used for real-time and robust object tracking. The results of our implementations how the robot can execute the task efficiently in human workspaces, such as an office or home.

안정적 사람 검출 및 추적을 위한 검증 프로세스

안정호(Ahn, Jung-Ho),최종호(Choi, Jong-Ho) 한국정보전자통신기술학회 2011 한국정보전자통신기술학회논문지 Vol.4 No.3

최근 들어 인간과 컴퓨터의 상호작용을 통해 컴퓨터 시스템을 제어하는 기술에 관한 연구가 진행되고 있다. 이러한 응용분야의 대부분은 얼굴검출을 통해 사용자의 위치를 파악하고 사용자의 제스처를 인식하는 방법을 포함하고 있으나, 얼굴검출 성능은 아직 미흡한 실정이다. 사용자의 위치가 안정적으로 검출되지 못 하는 경우에는 제스처 인식 등의 인터페이스 성능은 현격하게 저하된다. 따라서 본 논문에서는 피부색과 얼굴검출의 누적 분포를 이용하여 동영상에서 안정적으로 얼굴을 검출할 수 있는 알고리즘을 제안하고, 실험을 통해 알고리즘의 유용성을 증명하였다. 제안한 알고리즘은 대응행렬 분석을 적용하여 사람을 추적하는 분야에 응용이 가능하다. Recently the technologies that control the computer system through human computer interaction(HCI) have been widely studied. Their applications usually involve the methods that locate user's positions via face detection and recognize user's gestures, but face detection performance is not good enough. In case that the applications do not locate user's position stably, user interface performance, such as gesture recognition, is significantly decreased. In this paper we propose a new stable face detection algorithm using skin color detection and cumulative distribution of face detection results, whose effectiveness was verified by experiments. The propsed algorithm can be applicable in the area of human tracking that uses correspondence matrix analysis.