http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
A Simple and Fast Action Recognition Method Based on AdaBoost Algorithm
Xiaofei Ji,Lu Zhou,Ningli Qin,Yibo Li 보안공학연구지원센터 2016 International Journal of Multimedia and Ubiquitous Vol.11 No.8
A novel feature representation method based on AdaBoost algorithm is put forward for action recognition in this paper. The method can not only adequately describe action in complex scenarios, but also select the most discriminative sample subset from a large amount of raw features of training data. So it can realize a double result, that is, reduce the recognition computational complexity and achieve a good recognition accuracy. The pyramid histogram of oriented gradient feature (PHOG) descriptor is utilized to represent raw feature data. In order to select most discriminative samples subset, AdaBoost algorithm is used to extract the raw feature data. The nearest neighbor classifier algorithm is utilized to test the proposed method on the UCF Sports database. Experiment results show that the method not only achieve the better recognition rate but also greatly improve the speed of recognition.
Xiaofei Ji,Lu Zhou,Qianqian Wu 보안공학연구지원센터 2015 International Journal of Hybrid Information Techno Vol.8 No.5
Most of existed action recognition methods based on spatio-temporal descriptors have ignored their spatial distribution information. However the spatial distribution information usually is very useful to improve the discriminative ability of the motion representation. An improved spatio-temporal is proposed in this paper by combining local spatio-temporal feature and global positional distribution information (FEA) of interest points. Furthermore, in order to improve the classifier’s performance, an Adaboost-SVM method is utilized to recognize the human actions by using the proposed motion descriptor. The proposed recognition method is tested on the public dataset of KTH. The test results verified the proposed representation and recognition method can more accurately describe and recognize the human motion.
( Rui Hao ),( Yan Qiang ),( Xiaolei Liao ),( Xiaofei Yan ),( Guohua Ji ) 한국인터넷정보학회 2019 KSII Transactions on Internet and Information Syst Vol.13 No.1
In the computer-aided detection (CAD) system of pulmonary nodules, a high false positive rate is common because the density and the computed tomography (CT) values of the vessel and the nodule in the CT images are similar, which affects the detection accuracy of pulmonary nodules. In this paper, a method of automatic detection of pulmonary nodules based on multi-scale enhancement filters and 3D shape features is proposed. The method uses an iterative threshold and a region growing algorithm to segment lung parenchyma. Two types of multi-scale enhancement filters are constructed to enhance the images of nodules and blood vessels in 3D lung images, and most of the blood vessel images in the nodular images are removed to obtain a suspected nodule image. An 18 neighborhood region growing algorithm is then used to extract the lung nodules. A new pulmonary nodules feature descriptor is proposed, and the features of the suspected nodules are extracted. A support vector machine (SVM) classifier is used to classify the pulmonary nodules. The experimental results show that our method can effectively detect pulmonary nodules and reduce false positive rates, and the feature descriptor proposed in this paper is valid which can be used to distinguish between nodules and blood vessels.
Real Time Object Tracking with Sparse Prototypes
Dongxu Gao,Jiangtao Cao,Zhaojie Ju,Xiaofei Ji 보안공학연구지원센터 2015 International Journal of Signal Processing, Image Vol.8 No.4
Sparse representation (compressive sampling) has achieved impressive results in object tracking by looking for the best candidate with minimum reconstruction error using the target template. However, it may fail in some circumstances such as illumination changes, scale changes, the object color is similar with the surrounding region, and occlusion etc., in addition, high computational cost is required due to numerous calculations for solving an l1 norm related minimization problems. In order to resolve above problems, a novel method is introduced by exploiting an accelerated proximal gradient approach which aims to make the tracker runs in real time; moreover, both classic principal component analysis algorithm and sparse representation schemes are adapted for learning effective observation model and reduces the influence of appearance change. Both qualitative and quantitative evaluation demonstrate that the proposed tracking algorithm has favorably better performance than several state-of-the-art trackers using challenging benchmark image sequences, and significantly reduces the computing cost.