• 전기학회논문지
• /
• 제66권4호
• /
• pp.682-691
• /
• 2017

In this paper, we propose the fusion design methodology of both pedestrian detection and object tracking system realized with the aid of HOG-PCA based RBFNN pattern classifier. The proposed system includes detection and tracking parts. In the detection part, HOG features are extracted from input images for pedestrian detection. Dimension reduction is also dealt with in order to improve detection performance as well as processing speed by using PCA which is known as a typical dimension reduction method. The reduced features can be used as the input of the FCM-based RBFNNs pattern classifier to carry out the pedestrian detection. FCM-based RBFNNs pattern classifier consists of condition, conclusion, and inference parts. FCM clustering algorithm is used as the activation function of hidden layer. In the conclusion part of network, polynomial functions such as constant, linear, quadratic and modified quadratic are regarded as connection weights and their coefficients of polynomial function are estimated by LSE-based learning. In the tracking part, object tracking algorithms such as mean shift(MS) and cam shift(CS) leads to trace one of the pedestrian candidates nominated in the detection part. Finally, INRIA person database is used in order to evaluate the performance of the pedestrian detection of the proposed system while MIT pedestrian video as well as indoor and outdoor videos obtained from IC&CI laboratory in Suwon University are exploited to evaluate the performance of tracking.

• 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 Information Processing Systems
• /
• 제15권4호
• /
• pp.1017-1028
• /
• 2019

Pedestrian tracking is a particular object tracking problem and an important component in various vision-based applications, such as autonomous cars and surveillance systems. Following several years of development, pedestrian tracking in videos remains challenging, owing to the diversity of object appearances and surrounding environments. In this research, we proposed a tracking-by-detection system for pedestrian tracking, which incorporates a convolutional neural network (CNN) and color information. Pedestrians in video frames are localized using a CNN-based algorithm, and then detected pedestrians are assigned to their corresponding tracklets based on similarities between color distributions. The experimental results show that our system is able to overcome various difficulties to produce highly accurate tracking results.

• International Journal of Contents
• /
• 제9권3호
• /
• pp.1-9
• /
• 2013

In this paper, we propose a fast and accurate system for detecting pedestrians from a static image. Histogram of Oriented Gradients (HOG) is a well-known feature for pedestrian detection systems but extracting HOG is expensive due to its high dimensional vector. It will cause long processing time and large memory consumption in case of making a pedestrian detection system on high resolution image or video. In order to deal with this problem, we use Principal Components Analysis (PCA) technique to reduce the dimensionality of HOG. The output of PCA will be input for a linear SVM classifier for learning and testing. The experiment results showed that our proposed method reduces processing time but still maintains the similar detection rate. We got twenty five times faster than original HOG feature.

• 제어로봇시스템학회논문지
• /
• 제20권9호
• /
• pp.930-935
• /
• 2014

A Gabor filter is a linear filter used for edge detectionas frequency and orientation representations of Gabor filters are similar to those of the human visual system. In this thesis, we propose a pedestrian detection algorithm using a Gabor filter bank. In order to extract the features of the pedestrian, we use various image processing algorithms and data structure algorithms. First, color image segmentation is performed to consider the information of the RGB color space. Second, histogram equalization is performed to enhance the brightness of the input images. Third, convolution is performed between a Gabor filter bank and the enhanced images. Fourth, statistical values are calculated by using the integral image (summed area table) method. The calculated statistical values are used for the feature matrix of the pedestrian area. To evaluate the proposed algorithm, the INRIA pedestrian database and SVM (Support Vector Machine) are used, and we compare the proposed algorithm and the HOG (Histogram of Oriented Gradient) pedestrian detector, presentlyreferred to as the methodology of pedestrian detection algorithm. The experimental results show that the proposed algorithm is more accurate compared to the HOG pedestrian detector.

• 대한임베디드공학회논문지
• /
• 제8권2호
• /
• pp.121-128
• /
• 2013

There have been various research efforts for pedestrian recognition in embedded imaging systems. However, many suffer from their heavy computational complexities. SVM classification method has been widely used for pedestrian recognition. The reduction of candidate region is crucial for low-complexity scheme. In this paper, We propose a real time HOG based pedestrian detection system on GPU which images are captured by a pair of cameras. To speed up humans on road detection, the proposed method reduces a number of detection windows with disparity-search and near-search algorithm and uses the GPU and the NVIDIA CUDA framework. This method can be achieved speedups of 20% or more compared to the recent GPU implementations. The effectiveness of our algorithm is demonstrated in terms of the processing time and the detection performance.

• 방송공학회논문지
• /
• 제21권4호
• /
• pp.493-505
• /
• 2016

컴퓨터 비전이나 감시영상 시스템에서 유동인구 수 측정은 안전, 스케줄링, 광고효과 측면에서 중요한 과제 중 하나이다. 유동인구 수 측정은 조명변화, 부분적인 폐색, 중첩, 사람검출과 같은 다양한 어려움을 겪고 있다. 가장 큰 문제점은 혼잡한 상황에서 추적되는 객체에 대한 폐색과 중첩이다. 정확한 유동인구 수 측정을 위해 폐색과 중첩은 반드시 해결해야 할 과제이다. 본 논문에서는 기존의 보행자 추적 방법을 개선한 효율적인 유동인구 수 측정 시스템을 제안한다. 기존의 보행자 추적과 달리, 제안된 방법은 평균 필터 추적방법을 적용하여 성능을 향상시킬 수 있음을 보인다. 또한 객체 추적의 성능향상을 위한 프레임 보상, 아웃라이어 제거를 통해서 추적을 개선한다. 그와 동시에 제안된 시스템은 추적된 객체의 다양한 정보를 저장한다. 데이터 셋 S6와 데이터 셋 S7에 대하여 유동인구 수 측정 정확도를 향상시키고 에러율을 줄인다. 또한 제안된 방법은 실시간으로 평균 80fps의 검출을 제공한다.

• ETRI Journal
• /
• 제45권5호
• /
• pp.836-846
• /
• 2023

Mobile robots are used in modern life; however, object recognition is still insufficient to realize robot navigation in crowded environments. Mobile robots must rapidly and accurately recognize the movements and shapes of pedestrians to navigate safely in pedestrian-rich spaces. This study proposes real-time, accurate, three-dimensional (3D) multi-pedestrian detection and tracking using a 3D light detection and ranging (LiDAR) point cloud in crowded environments. The pedestrian detection quickly segments a sparse 3D point cloud into individual pedestrians using a lightweight convolutional autoencoder and connected-component algorithm. The multi-pedestrian tracking identifies the same pedestrians considering motion and appearance cues in continuing frames. In addition, it estimates pedestrians' dynamic movements with various patterns by adaptively mixing heterogeneous motion models. We evaluate the computational speed and accuracy of each module using the KITTI dataset. We demonstrate that our integrated system, which rapidly and accurately recognizes pedestrian movement and appearance using a sparse 3D LiDAR, is applicable for robot navigation in crowded spaces.

• 제어로봇시스템학회논문지
• /
• 제19권11호
• /
• pp.1017-1021
• /
• 2013

The traffic signal has been widely used in the transport system with a fixed time interval currently. This kind of setting time was determined based on experience for vehicles to generate a waiting time while allowing pedestrians crossing the street. However, this strict setting causes inefficient problems in terms of economic and safety crossing. In this research, we propose a monitoring algorithm to detect, track and check pedestrian crossing the crosswalk by the patterns of behavior. This monitoring system ensures the safety for pedestrian and keeps the traffic flow in efficient. In this algorithm, pedestrians are detected by using HOG feature which is robust to illumination changes in outdoor environment. According to a complex computation, the parallel process with the GPU as well as CPU is adopted for real-time processing. Therefore, pedestrians are tracked by the relationship of hue channel in image sequence according to the predefined pedestrian zone. Finally, the system checks the pedestrians' crossing on the crosswalk by its HOG based behavior patterns. In experiments, the parallel processing by both GPU and CPU was performed so that the result reaches 16 FPS (Frame Per Second). The accuracy of detection and tracking was 93.7% and 91.2%, respectively.

• 정보과학회 논문지
• /
• 제44권1호
• /
• pp.44-50
• /
• 2017

보행자 검출은 수년간 광범위하게 연구된 문제이며, 자율주행 자동차와 운전자 보조시스템에서 매우 중요한 역할을 차지하고 있다. 특히, 계층적 분류기[1]와 Histogram of Gradient[2]특징벡터 등 영상기반의 보행자 검출기법과 ConvNet같이 deep model을 이용하여 검출하는 기법들이 연구되었고 검출성능은 꾸준히 상승하였다. 하지만 보행자 검출은 작은 오차에도 생명과 연관된 문제를 야기할 수 있기 때문에, 자율주행 시스템의 보행자검출 오차율은 더욱 낮출 필요가 있다. 따라서 본 연구에서는 Faster R-CNN 응용 기법에 새로 개발한 데이터 학습 모델을 적용하여 보행자 검출 오류를 줄이는 기법을 제안한다. 그리고 기존에 제안된 모델들과 비교를 통해, 보행자 검출에 있어 제안된 방법의 우수성을 보이고자 한다.