• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권2호
• /
• pp.855-870
• /
• 2020

Windows are key components of building facades. Detecting windows, crucial to 3D semantic reconstruction and scene parsing, is a challenging task in computer vision. Early methods try to solve window detection by using hand-crafted features and traditional classifiers. However, these methods are unable to handle the diversity of window instances in real scenes and suffer from heavy computational costs. Recently, convolutional neural networks based object detection algorithms attract much attention due to their good performances. Unfortunately, directly training them for challenging window detection cannot achieve satisfying results. In this paper, we propose an approach for window detection. It involves an improved Faster R-CNN architecture for window detection, featuring in a window region proposal network, an RoI feature fusion and a context enhancement module. Besides, a post optimization process is designed by the regular distribution of windows to refine detection results obtained by the improved deep architecture. Furthermore, we present a newly collected dataset which is the largest one for window detection in real street scenes to date. Experimental results on both existing datasets and the new dataset show that the proposed method has outstanding performance.

• Journal of Multimedia Information System
• /
• 제6권1호
• /
• pp.1-6
• /
• 2019

In the field of industrial applications, the real-time performance of the target detection problem is very important. The most serious time consumption in the pedestrian detection process is the extraction phase of the candidate window. To accelerate the speed, in this paper, a fast extraction of pedestrian candidate window based on the BING (Binarized Normed Gradients) algorithm replaces the traditional sliding window scanning. The BING features are extracted with the positive and negative samples and input into the two-stage SVM (Support Vector Machine) classifier for training. The obtained BING template may include a pedestrian candidate window. The trained template is loaded during detection, and the extracted candidate windows are input into the classifier. The experimental results show that the proposed method can extract fewer candidate window and has a higher recall rate with more rapid speed than the traditional sliding window detection method, so the method improves the detection speed while maintaining the detection accuracy. In addition, the real-time requirement is satisfied.

• Journal of Electrical Engineering and Technology
• /
• 제10권3호
• /
• pp.1227-1232
• /
• 2015

Several works help make sliding window object detection fast, nevertheless, computational demands remain prohibitive for numerous applications. This paper proposes a fast object detection method based on three strategies: cascade classifier, selective window search and fast feature extraction. Experimental results show that the proposed method outperforms the compared methods and achieves both high detection precision and low computation cost. Our approach runs at 17ms per frame on 640×480 images while attaining state-of-the-art accuracy.

• 대한전자공학회논문지SP
• /
• 제37권3호
• /
• pp.57-69
• /
• 2000

본 논문에서는 주행차량에 장착된 CCD 카메라를 통하여 획득되어진 영상으로부터 moving window를 사용하여 차선을 인식하고 장애물을 감지하는 방법을 제안한다 입력되는 동영상을 실시간에 처리하기 위해서는 하드웨어적으로 상당히 많은 제약을 초래한다. 이러한 문제점을 극복하고 영상을 사용하여 실시간에 차선 인식 및 장애물을 감지하기 위해, 도로조건과 차량상태에 바탕을 둔 최적의 window 크기를 결정하고 그 window 영상만을 처리하여 차선 인식 및 장애물 감지를 실시간에 가능하게 하는 기법을 제안한다 영상의 각 프레임에 대하여 moving window는 칼만필터에 의해 정확성이 향상된 예측방향으로 옮겨진다. 제안된 알고리즘의 효용성을 고속도로 주행영상을 사용한 실험을 통해 보여준다

• 전자공학회논문지
• /
• 제51권7호
• /
• pp.201-208
• /
• 2014

지뢰 탐지 시스템의 성능은 지뢰의 특징을 일관성 있게 추출하는 것에 달려 있다. 그러나 지뢰는 다양한 크기를 가지므로, 지뢰영역을 일관성 있게 표현하기 위한 적절한 윈도우의 크기를 선택하는 것이 중요하다. 기존의 시스템들은 고정된 크기의 윈도우로 특징을 추출하기 때문에, 일관성 있는 지뢰의 특징을 획득할 수 없다. 본 논문에서는 지뢰의 크기에 따라 윈도우를 선택하는 기법을 제안한다. 제안 기법은 시스템에서 획득된 응답신호를 통해 지뢰의 종류를 추정한 후, 이에 따른 윈도우 크기를 선택한다. 제안 기법의 성능을 검증하기 위하여 시뮬레이션 프로그램으로 다양한 토양과 지뢰에 대한 데이터를 생성하였다. 실험 결과 고정 크기의 윈도우를 이용한 시스템의 성능에 비해 제안한 기법을 이용한 시스템의 성능이 2%높은 탐지율을 가지는 것을 확인하였다.

• 정보과학회 컴퓨팅의 실제 논문지
• /
• 제23권7호
• /
• pp.408-416
• /
• 2017

본 논문에서는 주행 중 사각지역내의 차량을 빠르고 정확하게 실시간으로 검출하는 측후방 차량 검출 알고리즘을 제안한다. 제안 알고리즘은 실시간 처리를 위해 MCT(Modified Census Transformation) 특징벡터를 기반으로 에이다부스트 학습을 통해 생성되는 캐스케이드 분류기를 사용한다. MCT 분류기는 검출윈도우가 작을수록 처리속도가 빠르고, 검출윈도우가 클수록 정확도가 증가한다. 제안 알고리즘은 이러한 특징을 이용하여 검출윈도우가 작은 분류기로 차량후보를 빠르게 생성한 후 보다 큰 사이즈의 검출윈도우를 가지는 분류기로 생성된 차량후보에 대해 정확하게 차량인지 검증한다. 또한, 차량분류기와 바퀴분류기를 동시에 사용하여 사각지역내로 진입하는 차량과 사각지역내의 인접차량을 효과적으로 검출한다.

• Current Optics and Photonics
• /
• 제7권1호
• /
• pp.73-82
• /
• 2023

In this study, we demonstrate ultrahigh-resolution spectral-domain optical coherence tomography with a 200-kHz line rate using a superluminescent diode with a -3-dB bandwidth of 100 nm at 849 nm. To increase the line rate, a subset of the total number of camera pixels is used. In addition, a partial-spectrum detection method is used to obtain OCT images within an imaging depth of 2.1 mm while maintaining ultrahigh axial resolution. The partially detected spectrum has a flat-topped intensity profile, and side lobes occur after fast Fourier transformation. Consequently, we propose and apply the super-Gaussian window function as a new window function, to reduce the side lobes and obtain a result that is close to that of the axial-resolution condition with no window function applied. Upon application of the super-Gaussian window function, the result is close to the ultrahigh axial resolution of 4.2 ㎛ in air, corresponding to 3.1 ㎛ in tissue (n = 1.35).

• ETRI Journal
• /
• 제35권1호
• /
• pp.80-88
• /
• 2013

A passive infrared or pyroelectric infrared (PIR) sensor is mainly used to sense the existence of moving objects in an indoor environment. However, in an outdoor environment, there are often outbreaks of false alarms from environmental changes and other sources. Therefore, it is difficult to provide reliable detection outdoors. In this paper, two algorithms are proposed to reduce false alarms and provide trustworthy quality to surveillance systems. We gather PIR signals outdoors, analyze the collected data, and extract the target features defined as window energy and alarm duration. Using these features, we model target and false alarms, from which we propose two target decision algorithms: window energy detection and alarm duration detection. Simulation results using real PIR signals show the performance of the proposed algorithms.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2008년도 추계학술대회B
• /
• pp.2070-2075
• /
• 2008

Identification of steady-state is the first step in developing a fault detection and diagnosis (FDD) system. In a complete FDD system, the steady-state detector will be included as a module in a self-learning algorithm which enables the working system's reference model to "tune" itself to its particular installation. In this study, a steady-state detector of a residential air conditioner based on moving windows was designed. Seven representing measurements were selected as key features for steady-state detection. The optimized moving window size and the feature thresholds was suggested through startup transient test and no-fault steady-state test. Performance of the steady-state detector was verified during indoor load change test. From the research, the general methodology to design a moving window steady-state detector was provided for vapor compression applications.

• 전자공학회논문지B
• /
• 제32B권11호
• /
• pp.1424-1433
• /
• 1995

The edge detection process serves to simplify the analysis of images by drastically reducing the amount of data to be processed, while preserving useful structural informations about object boundaries. At first, this paper proposes an edge detection algorithm to reduce the amount of computation. The gradients of pixels are calculated by using first order differential equations on the pixels with even rows and even columns or odd rows and odd columns, and they are compared with a threshold to decide edges. As a result, the computational complexity is reduced to one third or one forth compared with the provious ones. To enhance the accuracy of edge detection, a method with the adaptive threshold for each pixel window which is calculated by using characteristic values is proposed. In this case, the performance can be improved since the threshold is calculated properly for each window according to the local characteristics of corresponding window.