• ETRI Journal
• /
• v.39 no.4
• /
• pp.502-513
• /
• 2017

For video understanding, namely analyzing who did what in a video, actions along with objects are primary elements. Most studies on actions have handled recognition problems for a well-trimmed video and focused on enhancing their classification performance. However, action detection, including localization as well as recognition, is required because, in general, actions intersect in time and space. In addition, most studies have not considered extensibility for a newly added action that has been previously trained. Therefore, proposed in this paper is an extensible hierarchical method for detecting generic actions, which combine object movements and spatial relations between two objects, and inherited actions, which are determined by the related objects through an ontology and rule based methodology. The hierarchical design of the method enables it to detect any interactive actions based on the spatial relations between two objects. The method using object information achieves an F-measure of 90.27%. Moreover, this paper describes the extensibility of the method for a new action contained in a video from a video domain that is different from the dataset used.

• Journal of Korea Multimedia Society
• /
• v.19 no.12
• /
• pp.1943-1950
• /
• 2016

Recently, gender classification has attracted a great deal of attention in the field of video surveillance system. It can be useful in many applications such as detecting crimes for women and business intelligence. In this paper, we proposed a method which can detect pedestrians from CCTV video and classify the gender of the detected objects. So far, many algorithms have been proposed to classify people according the their gender. This paper presents a gender classification using convolutional neural network. The detection phase is performed by AdaBoost algorithm based on Haar-like features and LBP features. Classifier and detector is trained with data-sets generated form CCTV images. The experimental results of the proposed method is male matching rate of 89.9% and the results shows 90.7% of female videos. As results of simulations, it is shown that the proposed gender classification is better than conventional classification algorithm.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.18 no.6
• /
• pp.711-720
• /
• 2015

Recently many studies of Radar systems mounted on ground vehicles for autonomous driving, SLAM (Simultaneous localization and mapping) and collision avoidance have been reported. Since several pixels per an object may be generated in a close-range radar application, a width of an object can be estimated automatically by various signal processing techniques. In this paper, we tried to attempt to develop an algorithm to estimate obstacle width using Radar images. The proposed method consists of 5 steps - 1) background clutter reduction, 2) local peak pixel detection, 3) region growing, 4) contour extraction and 5)width calculation. For the performance validation of our method, we performed the test width estimation using a real data of two cars acquired by commercial radar system - I200 manufactured by Navtech. As a result, we verified that the proposed method can estimate the widths of targets.

• Annual Conference of KIPS
• /
• 2021.05a
• /
• pp.401-403
• /
• 2021

본 시스템은 같은 환자로부터 촬영한 기존 안저영상과 초광각 안저영상을 Paired Dataset으로 지니고 있으며, 영상의 크기 및 해상도를 똑같이 맞추고, 황반부와 신경유두 및 혈관의 위치를 미세조정하는 과정을 자동화하는 것을 목표로 하고 있다. 이 과정은 황반부를 중심으로 하여 영상을 잘라내어 이미지의 크기를 맞추는 과정(Scaling)과, 황반부를 중심으로 잘라낸 한 쌍의 영상을 포개었을 때 황반부, 신경 유두, 혈관 등의 위치가 동일하도록 미세조정하는 과정(Warping)이 있다. Scaling Stage에선 기존 안저영상과 초광각 안저영상의 촬영범위가 현저하게 차이나기 때문에, 황반변성 부위를 잘 나타내도록 사전에 잘라낼 필요가 있으며, 이를 신경유두의 Object Detection을 활용할 예정이다. Warping Stage에선 동일한 위치에 같은 황반변성 정보가 내포되어야 하므로 규격조정 및 위치조정 과정이 필수적이며, 이후 안저영상 내의 특징들을 매칭하는 작업을 하기 위해 회전, 회절, 변환 작업 등이 이루어지며, 이는 Homography Estimation을 통하여 이미지 변환 matrix를 구하는 방법으로 진행된다. 자동조정된 안저영상 데이터는 추후에 GAN을 이용한 안저영상 생성모델을 위한 학습데이터로 이용할 예정이며, 현재로선 2500쌍의 데이터를 대상으로 실험을 진행중이지만, 최종적으로 3만 쌍의 안저영상 데이터를 목표로 하고 있다.

• Annual Conference of KIPS
• /
• 2020.11a
• /
• pp.224-227
• /
• 2020

엣지컴퓨팅 기반 유해조수 퇴치 Drone의 유해조수 추적 기술은 Doppler Sensor를 이용해 사유지에 침입한 유해조수를 인식 후 사용자에게 위험 요소에 대한 알림 서비스를 제공한다. 이후 사용자는 Drone의 Camera와 전용 애플리케이션을 이용해 경작지를 실시간으로 보며 Drone을 조종한다. Camera는 Tensor Flow Object Detection Deep Learning을 적용하여 유해조수를 학습 및 파악, 추적한다. 이후 Drone은 Speaker와 Neo Pixel LED Ring을 이용해 유해조수의 시각과 청각을 자극해 도망을 유도하며 퇴치한다. Tensor Flow object detection을 핵심으로 Drone에 접목했고 이를 위해 전용 애플리케이션을 개발했다.

• The Journal of Korea Robotics Society
• /
• v.19 no.1
• /
• pp.79-91
• /
• 2024

Large warehouses are building automation systems to increase efficiency. However, small warehouses, military bases, and local stores are unable to introduce automated logistics systems due to lack of space and budget, and are handling tasks manually, failing to improve efficiency. To solve this problem, this study designed small loading and unloading equipment that can be mounted on transportation vehicles. The equipment can be controlled remotely and is automatically controlled from the point where pallets loaded with cargo are visible using real-time video from an attached camera. Cargo recognition and control command generation for automatic control are achieved through a newly designed deep learning model. This model is designed to be optimized for loading and unloading equipment and mission environments based on the YOLOv3 structure. The trained model recognized 10 types of palettes with different shapes and colors with an average accuracy of 100% and estimated the state with an accuracy of 99.47%. In addition, control commands were created to insert forks into pallets without failure in 14 scenarios assuming actual loading and unloading situations.

• Journal of KIISE:Software and Applications
• /
• v.29 no.1_2
• /
• pp.114-125
• /
• 2002

In this paper, we are proposing a hierarchical segmentation method that first segments the video data into units of shots by detecting cut and dissolve, and then decides types of camera operations or object movements in each shot. In our previous work[1], each picture group is divided into one of the three detailed categories, Shot(in case of scene change), Move(in case of camera operation or object movement) and Static(in case of almost no change between images), by analysing DC(Direct Current) component of I(Intra) frame. In this process, we have designed two-stage hierarchical neural network with inputs of various multiple features combined. Then, the system detects the accurate shot position, types of camera operations or object movements by searching P(Predicted), B(Bi-directional) frames of the current picture group selectively and hierarchically. Also, the statistical distributions of macro block types in P or B frames are used for the accurate detection of cut position, and another neural network with inputs of macro block types and motion vectors method can reduce the processing time by using only DC coefficients of I frames without decoding and by searching P, B frames selectively and hierarchically. The proposed method classified the picture groups in the accuracy of 93.9-100.0% and the cuts in the accuracy of 96.1-100.0% with three different together is used to detect dissolve, types of camera operations and object movements. The proposed types of video data. Also, it classified the types of camera movements or object movements in the accuracy of 90.13% and 89.28% with two different types of video data.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.1
• /
• pp.22-27
• /
• 2020

Recently, as the number of households raising pets increases due to the increase of single households, there is a need for a system for monitoring the status or behavior of pets. There are regional limitations in the monitoring of pets using domestic CCTVs, which requires a large number of CCTVs or restricts the behavior of pets. In this paper, we propose a mobile system for detecting and tracking cats using deep learning to solve the regional limitations of pet monitoring. We use YOLO (You Look Only Once), an object detection neural network model, to learn the characteristics of pets and apply them to Raspberry Pi to track objects detected in an image. We have designed a mobile monitoring system that connects Raspberry Pi and a laptop via wireless LAN and can check the movement and condition of cats in real time.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.469-472
• /
• 2022

With the recent development of intelligent transportation systems, various technologies applying deep learning technology are being used. To crackdown on illegal vehicles and criminal vehicles driving on the road, a vehicle type classification system capable of accurately determining the type of vehicle is required. This study proposes a vehicle type classification system optimized for mobile traffic control systems using YOLO(You Only Look Once). The system uses a one-stage object detection algorithm YOLOv5 to detect vehicles into six classes: passenger cars, subcompact, compact, and midsize vans, full-size vans, trucks, motorcycles, special vehicles, and construction machinery. About 5,000 pieces of domestic vehicle image data built by the Korea Institute of Science and Technology for the development of artificial intelligence technology were used as learning data. It proposes a lane designation control system that applies a vehicle type classification algorithm capable of recognizing both front and side angles with one camera.

• Journal of Intelligence and Information Systems
• /
• v.8 no.2
• /
• pp.1-13
• /
• 2002

In this paper, we propose an object tracking system which can be convinced of moving area shaped on objects through color sequential images, decided moving directions of foot messengers or vehicles of image sequences. In static camera, we suggests a new evaluating method extracting co-occurrence matrix with feature vectors of RGB after analyzing and blocking difference images, which is accessed to field of camera view for motion. They are energy, entropy, contrast, maximum probability, inverse difference moment, and correlation of RGB color vectors. we describe how to analyze and compute corresponding relations of objects between adjacent frames. In the clustering, we apply an algorithm of FCM(fuzzy c means) to analyze matching and clustering problems of adjacent frames of the featured vectors, energy and entropy, gotten from previous phase. In the matching phase, we also propose a method to know correspondence relation that can track motion each objects by clustering with similar area, compute object centers and cluster around them in case of same objects based on membership function of motion area of adjacent frames.