Tracking and Analysis of Pedestrian’s Behavior in Public Places

Crowd management becomes a global concern due to increased population in urban areas. Better management of pedestrians leads to improved use of public places. Behavior of pedestrian’s is a major factor of crowd management in public places. There are multiple applications available in this area but the challenge is open due to complexity of crowd and depends on the environment. In this paper, we have proposed a new method for pedestrian’s behavior detection. Kalman filter has been used to detect pedestrian’s using movement based approach. Next, we have performed occlusion detection and removal using region shrinking method to isolate occluded humans. Human verification is performed on each human silhouette and wavelet analysis and particle gradient motion are extracted for each silhouettes. Gray Wolf Optimizer (GWO) has been utilized to optimize feature set and then behavior classification has been performed using the Extreme Gradient (XG) Boost classifier. Performance has been evaluated using pedestrian’s data from avenue and UBI-Fight datasets, where both have different environment. The mean achieved accuracies are 91.3% and 85.14% over the Avenue and UBI-Fight datasets, respectively. These results are more accurate as compared to other existing methods.     

An effective deep learning model for grading abnormalities in retinal fundus images using variational auto-encoders

Diabetic retinopathy (DR) and Diabetic Macular Edema (DME) are severe diseases that affect the eyes due to damage in blood vessels. Computer-aided automated grading will help clinicians conduct disease diagnoses at ease. Experiments of automated image processing with deep learning techniques using CNN produce promising results, especially in the medical imaging domain. However, the disease grading tasks in retinal images using CNN struggle to retain high-quality information at the output. A novel deep learning model based on variational auto-encoder to grade DR and DME abnormalities in retinal images is proposed. The objective of the proposed model is to extract the most relevant retinal image features efficiently. It focuses on addressing less relevant candidate region generation and translational invariance present in images. The experiments are conducted in IDRID dataset and evaluated using accuracy, U-kappa, sensitivity, specificity and precision metrics. The results outperform compared with other state-of-art techniques.     

Vortex analysis and flow field optimization for the particle classifier with three rotary cages

The particle classifiers with three rotary cages have significant advantage in powder handling capacity. The flow field inside the classifiers were investigated from the perspective of vortex using Q criterion. Formation process and distribution of the vortices were intuitively exhibited. Structure of the guide cone was further optimized, and the classifying performance of the classifiers was evaluated. The results show that complex vortex structures were formed inside the classifier. The large-scale columnar vortex under the guide cone oscillates irregularly. This unwanted vortex is eliminated by extending the guide cone. The structure of the guide cone has little effect on the cut size, but the optimized guide cone with the long cylinder and cone significantly enhances the separation degree of the fine and coarse particles. The classifier obtains finer silica powder with a median size of 2.5 μm and higher Newton efficiency about 71.5%.     

Skin detection for single images using dynamic skin color modeling

Up-to-date skin detection techniques use adaptive skin color modeling to overcome the varying skin color problem. Most methods for tracking skin regions in videos utilize the correlation between contiguous frames. This paper proposes a new approach for detecting skin in a single image. This approach uses a local skin model to shift a globally trained skin model to adapt the final skin model to the current image. Experimental results show that the proposed method can achieve better accuracy. Two improvements for speeding up the processing are also discussed.     

汉字识别方法综述

分析汉字结构特征及其演变,在汉字字库及汉字识别目标变化的基础上,结合汉字识别过程,研究与比较贝叶斯决策、二次判别函数法、隐马尔科夫模型、神经网络分类器以及支持向量机这5种汉字识别方法的优缺点及适用范围。结果表明,汉字识别方法仍需要在识别目标及特征提取、训练字符集准备方面进行改进。     

基于网格的混合神经网络计算平台研究与实现

为了模仿人脑的复杂功能,把各种相关类型的神经网络组织起来,形成一个大规模混合神经网络.根据此需求,使用自主研发的LabGrid技术开发了一个基于网格的混合神经网络计算平台,利用该平台设计了一种新的混合神经网络分类系统来对该平台进行测试.测试结果表明,该平台具有较高的效率和良好的容错性.与其它分类系统比较可知,该分类系统有较高的准确率,从而证明了模仿人脑建立大规模混合神经网络分类系统的可行性和有效性.     

基于模糊控制的驾驶疲劳检测

提出了一种判断疲劳程度的新方法,通过检测眼睛、嘴巴状态和头部位置等能够反应疲劳的生理特征,利用模糊控制器推理,得到人的疲劳状态的数值表示,改善了疲劳或者非疲劳的二值表示形式.通过肤色识别和阚值选取等方法得到人眼检测,进行边界提取的结果优于边缘检测.利用fisher线性分类器进行嘴唇和肤色的分类,提高了检测速度.模糊推理更精确的反应了人的疲劳程度,实验结果表明了检测方法的有效性和可信性.     

一种改进的AdaBoost算法在人脸检测系统中的应用

针对复杂背景条件下人脸检测的检测率低、速度慢的问题,提出了一种改进的AdaBoost算法,与遗传算法相结合,产生了一种识别率高、泛化能力好的强分类器,文中称之为GA-AdaBoost算法。该算法首先训练多个支持向量机作为弱分类器,然后用AdaBoost算法将多个弱分类器组合成一个强分类器,在组合的同时采用遗传算法对各弱分类器的权值进行全局寻优。最后,通过试验与传统AdaBoost进行对比,表明了该算法具有识别率高和速度快的优越性。     

Method of classifier selection using the genetic approach

Abstract: The paper presents a novel machine learning algorithm used for training a compound classifier system that consists of a set of area classifiers. Area classifiers recognize objects derived from the respective competence area. Splitting feature space into areas and selecting area classifiers are two key processes of the algorithm; both take place simultaneously in the course of an optimization process aimed at maximizing the system performance. An evolutionary algorithm is used to find the optimal solution. A number of experiments have been carried out to evaluate system performance. The results prove that the proposed method outperforms each elementary classifier as well as simple voting.     

基于改进联合模型的人脸表情识别

在联合主动表观模型和主动形状模型的基础上,充分挖掘标定点之间的联系,提出一种局部纹理模型构建方法。通过改进匹配算法提高特征点的定位精度和匹配速度。将该算法提取到的人脸表情特征输入最近邻分类器,分类结果表明其识别率较高。