• 한국멀티미디어학회논문지
• /
• 제18권4호
• /
• pp.443-451
• /
• 2015

In this paper we suggest a new two-wheelers detection algorithm using uniform local binary pattern weighting value for projection vectors. The first, we calculate feature vectors using projection method which has robustness for rotation invariant and reducing dimensionality for each cell from origin image. The second, we applied new weighting values which are calculated by the modified local binary pattern showing the fast compute and simple to implement. This paper applied the Adaboost algorithm to make a strong classification from weak classification. In this experiment, we can get the result that the detection rate of the proposed method is higher than that of the traditional method.

• Journal of Multimedia Information System
• /
• 제1권2호
• /
• pp.119-126
• /
• 2014

We propose a bicycle detection system riding on people based on modified projected local binary pattern(PLBP) for vision based intelligent vehicles. Projection method has robustness for rotation invariant and reducing dimensionality for original image. The features of Local binary pattern(LBP) are fast to compute and simple to implement for object recognition and texture classification area. Moreover, We use uniform pattern to remove the noise. This paper suggests that modified LBP method and projection vector having different weighting values according to the local shape and area in the image. Also our system maintains the simplicity of evaluation of traditional formulation while being more discriminative. Our experimental results show that a bicycle and motorcycle riding on people detection system based on proposed PLBP features achieve higher detection accuracy rate than traditional features.

• 한국멀티미디어학회논문지
• /
• 제18권11호
• /
• pp.1302-1312
• /
• 2015

Recent research has been devoted and focused on detecting pedestrian and vehicle in intelligent vehicles except for the vulnerable road user(VRUS). In this paper suggest a new projection method which has robustness for rotation invariant and reducing dimensionality for each cell from original image to detect two-wheeler. We applied new weighting values which are calculated by maximum curvature containing very important object shape features and uniform local binary pattern to remove the noise. This paper considered the Adaboost algorithm to make a strong classification from weak classification. Experiment results show that the new approach gives higher detection accuracy than of the conventional method.

• Journal of Multimedia Information System
• /
• 제4권2호
• /
• pp.79-82
• /
• 2017

Smoke and fire have different shapes and colours. This article suggests a fully connected system which is used two features using Adaboost algorithm for constructing a strong classifier as linear combination. We calculate the local histogram feature by gradient and bin, local binary pattern value, and projection vectors for each cell. According to the histogram magnitude, this paper applied adapted weighting value to improve the recognition rate. To preserve the local region and shape feature which has edge intensity, this paper processed the normalization sequence. For the extracted features, this paper Adaboost algorithm which makes strong classification to classify the objects. Our smoke detection system based on the proposed approach leads to higher detection accuracy than other system.

• 한국정보통신학회논문지
• /
• 제15권11호
• /
• pp.2365-2373
• /
• 2011

본 논문은 고속화, 소형화 및 저전력을 요구하는 모바일 기기 및 디지털 카메라에 알맞은 실시간 얼굴 검출 하드웨어 IP(Intellectual Property)를 제안한다. 제안한 얼굴 검출 시스템은 검출 성능의 주요 원인인 조명 변화나 얼굴 크기, 다양한 얼굴 각도에 강인한 얼굴 검출을 수행한다. 입력 영상에 대해 조명 변화에 강인한 특성을 가지는 LBP(Local Binary Pattern) 변환을 거치고 Adaboost 알고리즘을 이용하여 다양한 얼굴 각도에 대해 미리 학습시킨 얼굴 특징 정보를 바탕으로 얼굴을 검출한다. 입력 영상 QVGA($320{\times}240$) 크기에서 최대 36개의 얼굴 검출 가능하며 Verilog-HDL을 사용하여 하드웨어로 설계하였다. 또한 FPGA 검증을 위해 Xilinx사의 Virtex5 XC5VLX330 FPGA 보드와 HD급 CMOS 이미지 센서(CIS)를 사용하여 하드웨어 구현을 검증하였다.

• 한국멀티미디어학회논문지
• /
• 제19권6호
• /
• pp.1014-1023
• /
• 2016

In this study, we presented a method for non-square Differential LBP operation that can well describe the micro pattern in the horizontal and vertical component. We proposed a way to represent a LBP operation with various direction components as well as the diagonal component. In order to verify the validity of the proposed operation, Differential LBP was investigated with respect to accuracy, sensitivity, and specificity for the classification of facial expression. In accuracy comparison proposed LBP operation obtains better results than Square LBP and LBP-CS operations. Also, Proposed Differential LBP gets better results than previous two methods in the sensitivity and specificity indicators 'Neutral', 'Happiness', 'Surprise', and 'Anger' and excellence Differential LBP was confirmed.

• 대한전자공학회논문지SD
• /
• 제48권10호
• /
• pp.67-71
• /
• 2011

디지털 도어락, 디지털 카메라, 비디오 감시 시스템 등에서 사용되는 기존의 얼굴 검출 시스템은 비교적 낮은 해상도의 영상 처리를 사용하고 있으며 이를 위해서 소프트웨어 기반의 구현을 하고 있다. 하지만 이 경우에는 높은 해상도를 위한 얼굴 검출이 어려울 뿐만 아니라 수행해야할 영산 처리 양이 많기 때문에 실시간으로 얼굴을 검출하는데 어려움이 있다. 실시간 임베디드 시스템에서 HD(High Definition) 영상을 위한 효과적인 얼굴 검출을 위해서는 하드웨어적인 접근이 필요하다. 이에 본 논문에서는 얼굴 검출을 위해 사용되는 전처리 과정 중에 하나이며 처리시간이 많이 소요되는 국부 이진 패턴(LBP, Local Binary Pattern) 연산을 하드웨어 구조를 제시하고 설계했다. 그리고 제시한 하드웨어 구조를 FPGA(Field Programmable Gate Array) 칩을 통해서 구현 및 검증을 통해 고해상도 HD급 영상에서 효율적인 얼굴 검출이 가능 한 것을 확인했다.