• Asia pacific journal of information systems
• /
• 제5권2호
• /
• pp.143-176
• /
• 1995

We present an overview of the Extensional Object Model (ExOM) and describe in detail the learning and classification components which integrate concepts from machine learning and object-oriented databases. The ExOM emphasizes flexibility in information acquisition, learning, and classification which are useful to support tasks such as diagnosis, planning, design, and database mining. As a vehicle to integrate machine learning and databases, the ExOM supports a broad range of learning and classification methods and integrates the learning and classification components with traditional database functions. To ensure the integrity of ExOM databases, a subsumption testing rule is developed that encompasses categories defined by type expressions as well as concept definitions generated by machine learning algorithms. A prototype of the learning and classification components of the ExOM is implemented in Smalltalk/V Windows.

• 한국멀티미디어학회논문지
• /
• 제25권4호
• /
• pp.600-609
• /
• 2022

In supervised learning, labeling of all data is essential, and in particular, in the case of object detection, all objects belonging to the image and to be learned have to be labeled. Due to this problem, continual learning has recently attracted attention, which is a way to accumulate previous learned knowledge and minimize catastrophic forgetting. In this study, a continaul learning model is proposed that accumulates previously learned knowledge and enables learning about new objects. The proposed method is applied to CenterNet, which is a object detection model of anchor-free manner. In our study, the model is applied the knowledge distillation algorithm to be enabled continual learning. In particular, it is assumed that all output layers of the model have to be distilled in order to be most effective. Compared to LWF, the proposed method is increased by 23.3%p mAP in 19+1 scenarios, and also rised by 28.8%p in 15+5 scenarios.

• 로봇학회논문지
• /
• 제8권1호
• /
• pp.20-28
• /
• 2013

Large workspace and strong grasping force are required when a robot manipulates big and/or heavy objects. In that situation, bimanual manipulation is more useful than unimanual manipulation. However, the control of both hands to manipulate an object requires a more complex model compared to unimanual manipulation. Learning by human demonstration is a useful technique for a robot to learn a model. In this paper, we propose an imitation learning method of bimanual object manipulation by human demonstrations. For robust imitation of bimanual object manipulation, movement trajectories of two hands are encoded as a movement trajectory of the object and a force trajectory to grasp the object. The movement trajectory of the object is modeled by using the framework of dynamic movement primitives, which represent demonstrated movements with a set of goal-directed dynamic equations. The force trajectory to grasp an object is also modeled as a dynamic equation with an adjustable force term. These equations have an adjustable force term, where locally weighted regression and multiple linear regression methods are employed, to imitate complex non-linear movements of human demonstrations. In order to show the effectiveness our proposed method, a movement skill of pick-and-place in simulation environment is shown.

• 인터넷정보학회논문지
• /
• 제21권1호
• /
• pp.33-43
• /
• 2020

Retrieving a 3D model from a 3D database and augmenting the retrieved model in the Augmented Reality system simultaneously became an issue in developing the plausible AR environments in a convenient fashion. It is considered that the sketch-based 3D object retrieval is an intuitive way for searching 3D objects based on human-drawn sketches as query. In this paper, we propose a novel deep learning based approach of retrieving a sketch-based 3D object as for an Augmented Reality Model. For this work, we introduce a new method which uses Sketch CNN, Wasserstein CNN and Wasserstein center loss for retrieving a sketch-based 3D object. Especially, Wasserstein center loss is used for learning the center of each object category and reducing the Wasserstein distance between center and features of the same category. The proposed 3D object retrieval and augmentation consist of three major steps as follows. Firstly, Wasserstein CNN extracts 2D images taken from various directions of 3D object using CNN, and extracts features of 3D data by computing the Wasserstein barycenters of features of each image. Secondly, the features of the sketch are extracted using a separate Sketch CNN. Finally, we adopt sketch-based object matching method to localize the natural marker of the images to register a 3D virtual object in AR system. Using the detected marker, the retrieved 3D virtual object is augmented in AR system automatically. By the experiments, we prove that the proposed method is efficiency for retrieving and augmenting objects.

• 대한임베디드공학회논문지
• /
• 제19권2호
• /
• pp.91-99
• /
• 2024

Collision avoidance system is important to improve the robustness and functional safety of autonomous vehicles. This paper proposes an object-level distance estimation method to develop a collision avoidance system, and it is applied to golfcarts utilized in country club environments. To improve the detection accuracy, we continually trained an object detection model based on pseudo labels generated by a pre-trained detector. Moreover, we propose object-aware depth estimation (OADE) method which trains a depth model focusing on object regions. In the OADE algorithm, we generated dense depth information for object regions by utilizing detection results and sparse LiDAR points, and it is referred to as object-aware LiDAR projection (OALP). By using the OALP maps, a depth estimation model was trained by backpropagating more gradients of the loss on object regions. Experiments were conducted on our custom dataset, which was collected for the travel distance of 22 km on 54 holes in three country clubs under various weather conditions. The precision and recall rate were respectively improved from 70.5% and 49.1% to 95.3% and 92.1% after the continual learning with pseudo labels. Moreover, the OADE algorithm reduces the absolute relative error from 4.76% to 4.27% for estimating distances to obstacles.

• 한국멀티미디어학회논문지
• /
• 제18권2호
• /
• pp.138-148
• /
• 2015

Object detection methods based on background learning are widely used in video surveillance. However, when a car runs with headlights on, these methods are likely to detect the car region and the area illuminated by the headlights as one connected change region. This paper describes a method of separating the car region from the area illuminated by the headlights. First, we detect change regions with a background learning method, and extract blobs, connected components in the detected change region. If a blob is larger than the maximum object size, we extract candidate object regions from the blob by clustering the intensity histogram of the frame difference between the mean of background images and an input image. Finally, we compute the similarity between the mean of background images and the input image within each candidate region and select a candidate region with weak similarity as an object region.

• 대한임베디드공학회논문지
• /
• 제17권5호
• /
• 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.

• 한국지능시스템학회논문지
• /
• 제18권3호
• /
• pp.291-296
• /
• 2008

본 논문에서는 군집로봇시스템에서 목표물 추적을 위하여 SVM을 이용한 12각형 기반의 Q-learning 알고리즘을 제안한다. 제안한 알고리즘의 유효성을 보이기 위해 본 논문에서는 여러 대의 로봇과 장애물 그리고 하나의 목표물로 정하고, 각각의 로봇이 숨겨진 목표물을 찾아내는 실험을 가정하여 무작위, DBAM과 AMAB의 융합 모델, 마지막으로는 본 논문에서 제안한 SVM과 12각형 기반의 Q-learning 알고리즘을 이용하여 실험을 수행하고, 이 3가지 방법을 비교하여 본 논문의 유효성을 검증하였다.

• 정보교육학회논문지
• /
• 제9권3호
• /
• pp.483-500
• /
• 2005

학습 객체는 생산 및 효율성과 구성주의적 학습 효과성을 겸비하면서, 컴퓨터 기반 학습 환경에 잘 적용될 수도 있는 차세대 학습 개념으로 각광 받고 있다. 그 탄생의 연원을 소프트웨어 공학에서의 객체지향 설계 이론에 기초한 이 학습 객체 설계 이론은, 그러나 학습자라는 학습의 주체에 대한 고려의 부족, 맥락성과 연계성, 그리고 의미론적 응집성이라는 "학습"의 논리를 담아내기에 충분한 수준의 이론적 기반을 갖추고 있지 못한 것이 현실이다. 본 연구에서는 학습 객체 설계 이론이라는 독특한 설계 모델을 지향하면서, 그 기초 작업으로서 관련 이론들을 정리해 내고, 메타포 수준의 개념틀 속에 자리 잡아 두며, 나아가 그 설계를 위한 원리들에 대한 분석을 시도하였다. 본 연구는 향후 구체적인 개발 사례를 통한 실증 연구와, 아울러 LCMS, 하이퍼텍스트의 노드와 링크 개념 등과 연결되면서, 본격적인 디지털 학습 콘텐츠 개발을 위한 이론을 지향하는 이론 연구로서의 의미를 갖는다.

• 한국정보통신학회논문지
• /
• 제24권2호
• /
• pp.204-211
• /
• 2020

본 논문에서는 약한 지도학습을 통한 주 객체 위치 검출을 위한 최적의 딥러닝 네트워크 구조를 제안한다. 제안된 네트워크는 약한 지도학습을 통한 주 객체의 위치 검출 정확도를 향상시키기 위해 컨벌루션 블록을 추가하였다. 추가적인 딥러닝 네트워크는 VGG-16을 기반으로 합성곱 층을 더해주는 5가지 추가적인 블록으로 구성되며 객체의 실제 위치 정보가 필요하지 않는 약한 지도 학습의 방법으로 학습하였다. 또한 객체의 위치 검출에는 약한 지도학습의 방법 중, CAM에서 GAP이 필요하다는 단점을 보완한 Grad-CAM을 사용하였다. 제안한 네트워크는 CUB-200-2011 데이터 셋을 이용하여 성능을 테스트하였으며 Top-1 Localization Error를 산출하였을 때 50.13%의 결과를 얻을 수 있었다. 또한 제안한 네트워크는 기존의 방법보다 주 객체를 검출하는데 더 높은 정확도를 보인다.