• 제어로봇시스템학회논문지
• /
• 제21권4호
• /
• pp.367-371
• /
• 2015

In this paper, a novel localization method for a monocular camera is proposed by using a feature-based probabilistic map. The localization of a camera is generally estimated from 3D-to-2D correspondences between a 3D map and an image plane through the PnP algorithm. In the computer vision communities, an accurate 3D map is generated by optimization using a large number of image dataset for camera pose estimation. In robotics communities, a camera pose is estimated by probabilistic approaches with lack of feature. Thus, it needs an extra system because the camera system cannot estimate a full state of the robot pose. Therefore, we propose an accurate localization method for a monocular camera using a probabilistic approach in the case of an insufficient image dataset without any extra system. In our system, features from a probabilistic map are projected into an image plane using linear approximation. By minimizing Mahalanobis distance between the projected features from the probabilistic map and extracted features from a query image, the accurate pose of the monocular camera is estimated from an initial pose obtained by the PnP algorithm. The proposed algorithm is demonstrated through simulations in a 3D space.

• 제어로봇시스템학회논문지
• /
• 제15권2호
• /
• pp.203-210
• /
• 2009

The problem of outdoor localization can be practically solved by GPS. However, GPS is not perfect and some areas of outdoor navigation should consider other solutions. This research deals with outdoor localization using an elevation map without GPS. This paper proposes a novel feature, elevation moment of inertia (EMOI), which represents the distribution of elevation as a function of distance from a robot in the elevation map. Each cell of an elevation map has its own EMOI, and outdoor localization can be performed by matching EMOIs obtained from the robot and the pre-given elevation map. The experiments and simulations show that the proposed EMOI can be usefully exploited for outdoor localization with an elevation map and this feature can be easily applied to other probabilistic approaches such as Markov localization method.

• 전자공학회논문지CI
• /
• 제40권6호
• /
• pp.95-105
• /
• 2003

본 논문에서는 지문인증 시스템에서 인증 성능을 향상시키기 위한 기준점 검출 알고리즘과 특징 추출에 있어서 새로운 filterbank방법을 제안한다. 제안한 기준점 검출 알고리즘 GPM(Gradient Probabilistic Method)은 4개의 방향성분을 추출하여 방향성분을 가장 균일하게 가지는 지점을 검출하는 방법이며, 기존의 Poincare index방법과 달리 수학적 통계적 방법을 사용하기 때문에 지문의 융선에 대한 세부적이고 세밀한 전처리 과정이 불필요하며, arch형태 지문의 기준점 검출에 대한 단점을 해결한다. 또한, 제안한 filterbank방법은 기존filterbank방법에서 특징의 불균일한 분포로 생기는 단점을 균일한 분포로 만들어 추출함으로써 해결한다. 제안한 GPM의 실험결과 기존의 Poincare index방법에 비해서, 일반환경뿐 아니라 잡음환경에서의 특징 추출 시간과 인증률에서 우수함을 보여준다. 특히, 제안한 GPM은 Poincare index방법에 비해서, arch type의 지문에 대한 FAR은 일반 환경에서 49%, 밝기 잡음환경에서 39.2%, salt and pepper 잡음환경에서 15.7%의 향상을 보여준다. 또한, 기준점 검출시간에 있어서, 제안한 GPM방법은 기존의 Poincare index방법보다 0.07초의 감소를 보여주며, 특징추출 시간에 있어서도 제안한 filterbank 알고리즘은 기존의 filterbank 방법에 비해서 0.06sec의 감소를 보여준다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권3호
• /
• pp.755-778
• /
• 2024

In recent years, the number of devices being connected to the internet has grown enormously, as has the intrusive behavior in the network. Thus, it is important for intrusion detection systems to report all intrusive behavior. Using deep learning and machine learning algorithms, intrusion detection systems are able to perform well in identifying attacks. However, the concern with these deep learning algorithms is their inability to identify a suitable network based on traffic volume, which requires manual changing of hyperparameters, which consumes a lot of time and effort. So, to address this, this paper offers a solution using the extended compact genetic algorithm for the automatic tuning of the hyperparameters. The novelty in this work comes in the form of modeling the problem of identifying attacks as a multi-objective optimization problem and the usage of linkage learning for solving the optimization problem. The solution is obtained using the feature map-based Convolutional Neural Network that gets encoded into genes, and using the extended compact genetic algorithm the model is optimized for the detection accuracy and latency. The CIC-IDS-2017 and 2018 datasets are used to verify the hypothesis, and the most recent analysis yielded a substantial F1 score of 99.23%. Response time, CPU, and memory consumption evaluations are done to demonstrate the suitability of this model in a fog environment.

• 한국산학기술학회논문지
• /
• 제19권4호
• /
• pp.161-166
• /
• 2018

본 논문에서는 컨볼루션 신경망 구조(Convolution Neural Network)에서 정규화 및 교차검증 횟수 감소를 위한 무작위로 풀링 연산을 선택하는 방법에 대해 설명한다. 컨볼루션 신경망 구조에서 풀링 연산은 피쳐맵(Feature Map) 크기 감소 및 이동 불변(Shift Invariant)을 위해 사용된다. 기존의 풀링 방법은 각 풀링 계층에서 하나의 풀링 연산이 적용된다. 이러한 방법은 학습 간 신경망 구조의 변화가 없기 때문에, 학습 자료에 과도하게 맞추는 과 적합(Overfitting) 문제를 가지고 있다. 또한 최적의 풀링 연산 조합을 찾기 위해서는, 각 풀링 연산 조합에 대해 교차검증을 하여 최고의 성능을 내는 조합을 찾아야 한다. 이러한 문제를 해결하기 위해, 풀링 계층에 확률적인 개념을 도입한 무작위 풀링 연산 선택 방법을 제안한다. 제안한 방법은 풀링 계층에 하나의 풀링 연산을 적용하지 않는다. 학습기간 동안 각 풀링 영역에서 여러 풀링 연산 중 하나를 무작위로 선택한다. 그리고 시험 시에는 각 풀링 영역에서 사용된 풀링 연산의 평균을 적용한다. 이러한 방법은 풀링 영역에서 서로 다른 풀링 조합을 사용한 구조의 평균을 한 것으로 볼 수 있다. 따라서, 컨볼루션 신경망 구조가 학습데이터에 과도하게 맞추어지는 과적합 문제를 피할 수 있으며, 또한 각 풀링 계층에서 특정 풀링 연산을 선택할 필요가 없기 때문에 교차 검증 횟수를 감소시킬 수 있다. 실험을 통해, 제안한 방법은 정규화 성능을 향상시킬 뿐만 아니라 및 교차 검증 횟수를 줄일 수 있다는 것을 검증하였다.

• 제어로봇시스템학회논문지
• /
• 제16권4호
• /
• pp.381-390
• /
• 2010

This paper describes a procedure of the map-based localization for mobile robots by using a sensor fusion technique in structured environments. A combination of various sensors with different characteristics and limited sensibility has advantages in view of complementariness and cooperation to obtain better information on the environment. In this paper, for robust self-localization of a mobile robot with a monocular camera and a laser structured light sensor, environment information acquired from two sensors is combined and fused by a Bayesian sensor fusion technique based on the probabilistic reliability function of each sensor predefined through experiments. For the self-localization using the monocular vision, the robot utilizes image features consisting of vertical edge lines from input camera images, and they are used as natural landmark points in self-localization process. However, in case of using the laser structured light sensor, it utilizes geometrical features composed of corners and planes as natural landmark shapes during this process, which are extracted from range data at a constant height from the navigation floor. Although only each feature group of them is sometimes useful to localize mobile robots, all features from the two sensors are simultaneously used and fused in term of information for reliable localization under various environment conditions. To verify the advantage of using multi-sensor fusion, a series of experiments are performed, and experimental results are discussed in detail.