检索结果-内蒙古大学图书馆

A study of falling behavior recognition of the elderly based on deep learning

SIGNAL IMAGE AND VIDEO PROCESSING 2024年第10期18卷 7383-7394页

作者： Xu, Pengfei Sulaiman, Nor Anis Asma Ding, Yafei Zhao, Jiangwei Li, Shengpu Pingdingshan Univ Dept Informat Engn Pingdingshan 467000 Henan Peoples R China SEGI Univ Fac Engn Ctr Sustainable Software Engn Built Environm & Informat Technol Kota Damansara Malaysia

The current computer vision-based elderly falling behavior recognition algorithm mainly uses target detection followed by behavior recognition for a single human body, but there are mostly numerous human targets and noise interference in the actual scene, which makes it difficult to accurately detect and recognize the anomalous behavior of the moving individual, for which detection and tracking of the moving human body is needed. In this paper, the fusion applications of histogram of oriented gradients human body detection algorithm, camshift human body tracking algorithm, and spatial temporal graph convolutional networks gesture recognition algorithm are investigated for the recognition of anomalous behaviors in elderly people during falls. After testing with 100 motion target groups, the time lag of this paper's fusion algorithm for motion human falling behavior recognition is < 0.5 s on average, and the average accuracy of anomalous falling behavior recognition is 97.0%, which is better than that of falling behavior recognition based on acquisition devices such as environmental sensors and deep learning models such as YOLOv5 and thus provides more powerful protection for the personal safety of elderly people.

关键词： Anomalous behavior ST-GCN algorithm camshift algorithm HOG algorithm

来源：评论

学校读者我要写书评

暂无评论

BP neural Network-Kalman filter fusion method for unmanned aerial vehicle target tracking

引用

PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART C-JOURNAL OF MECHANICAL ENGINEERING SCIENCE 2023年第18期237卷 4203-4212页

作者： Liu, Yongqi Nie, Liangcheng Dong, Rui Chen, Gang Xi An Jiao Tong Univ State Key Lab Strength & Vibrat Mech Struct Xian Peoples R China Xi An Jiao Tong Univ Shanxi Key Lab Serv Environm & Control Flight Veh Xian Peoples R China

The poor real-time performance and target occlusion occurred easily when the UAV was tracking the target. In this paper, a target tracking method based on the Back Propagation neural network fusion Kalman filter algorithm was developed to solve the position prediction problem of the UAV target tracking in real time. Firstly, the target tracking algorithm was used to acquire the center position coordinates of the target on the onboard computer, and then the coordinate difference matrix was constructed to train the BP neural network in real time. Secondly, when the target was occluded by the obstacles judged by the Bhattacharyya coefficient, the BP neural network fusion Kalman filter algorithm was used to accurately predict the center position coordinates of the occluded target. Then the flight speed of UAV was calculated by the deviation between the coordinates of the target and the image center. Finally, the velocity command was sent to the UAV by the onboard computer. The experimental results shown that the target position predicted by BP neural network fusion Kalman filter algorithm was more accurate and robust in predicting the center position coordinates of the target, and the UAV can track the moving target on the ground stably.

关键词： Target tracking back propagation neural network Kalman filter unmanned aerial vehicle camshift algorithm

来源：评论

学校读者我要写书评

暂无评论

The improved TLD algorithm that combines camshift and orientation prediction to realize face tracking in low illumination

The improved TLD algorithm that combines CAMShift and orient...

引用

Chinese Automation Congress (CAC)

作者： Zhang, Lin Hou, Jin Chen, MingJu Li, HongWen Sichuan Univ Sci & Engn Sch Automat & Informat Engn Yibin 644000 Sichuan Peoples R China

ISBN: (纸本)9781728176871

TLD(Tracking-Learning-Detection)algori thm acquires the target characteristics through continuous learning of the initial target. It can carry out long-term target Tracking. However, during the Tracking process, illumination, occlusion and target movement have a great impact on the Tracking effect. At the same time, the algorithm has a relatively large amount of calculation in the calculation process, which leads to the poor real-time performance of tracking. In order to reduce the influence of low illumination and occlusion on the algorithm, an improved algorithm integrating LBP algorithm into camshift algorithm was adopted to replace the original algorithm of tracking module in the algorithm. At the same time, in order to eliminate the defect of tracking loss caused by the target movement, Markov method is used to predict the direction and position of target movement, which can reduce the detection range of the algorithm and improve the real-time performance of the algorithm. The experiment shows that: compared with the traditional TLD algorithm, the improved algorithm has greatly improved tracking accuracy and faster tracking speed.

关键词： TLD algorithm low illumination Direction prediction LBP texture feature camshift algorithm

来源：评论

学校读者我要写书评

暂无评论

Kalman Filter-based Signal Processing for Robot Target Tracking

引用

INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS 2023年第6期14卷 589-597页

作者： Gong, Baofu Criminal Invest Police Univ China Lib Shenyang 110854 Peoples R China

In the field of computer vision, the signal tracking of moving objects is a highly representative problem. Therefore, how to accurately and quickly track the target unit has become the focus of the research. Based on this, a Cam Shift algorithm improved by Kalman filtering algorithm is introduced to realize fast tracking of moving targets. This method uses the prediction function of the Kalman filter to predict the moving target of the next frame, transforms the global search problem into a local search problem, and improves the real-time performance. The experimental results show that, in the case of complete occlusion, the trajectory of the unimproved algorithm will deviate compared with the actual trajectory of the improved trajectory tracking curve, but the improved algorithm has no trajectory deviation. The error of the improved algorithm is about 4%, while the maximum error of the unimproved algorithm is about 90%. The improved algorithm reached the expected target accuracy after 110 and 78 trainings in X and Y coordinates, respectively, while the camshift algorithm without Kalman filtering still failed to reach the expected error after 200 trainings in X and Y coordinates. This indicates that the performance of the improved camshift algorithm based on Kalman filter has been greatly improved. In conclusion, the improved algorithm proposed in this study is highly practical.

关键词： Motion target tracking Kalman filter camshift algorithm occlusion processing

来源：评论

学校读者我要写书评

暂无评论

Joint Detection and Tracking with Movable Camera and Its Application to a Drilling Robot in Underground Coal Mine 19

Joint Detection and Tracking with Movable Camera and Its App...

引用

19th IEEE International Conference on Mechatronics and Automation (IEEE ICMA)

作者： Guo, Jiongchi Zou, Xiaoyu Wang, Zhongbin Pan, Jie China Univ Min & Technol Sch Mech & Elect Engn Jiangsu Key Lab Mine Mech & Elect Equipment Xuzhou 221116 Jiangsu Peoples R China

ISBN: (数字)9781665408530

ISBN: (纸本)9781665408530;9781665408523

The movable camera usually has two states, namely static and moving, which makes it difficult to detect or track the object. The following three problems may rise. First, when the camera and the object are relatively stationary, the stationary object may possibly be misjudged as the background or even be gradually absorbed by the background, due to the complexity and limitation of the background model construction. Second, when the camera and the object are relatively moving, the object may be blurred due to camera vibration since the relative movement between them is irregular, which affects the tracking effect. Third, the background is constantly changing when the camera is moving, which may cause confusion between the object and the background. In order to solve the above problems, this paper proposes a joint detection and tracking method with moving camera. The relative status between the camera and the object is judged in real time through the Lucas-Kanade (LK) algorithm at first. For relative stationary state, object detection can be conducted with foreground segmentation method. For relative moving state, object tracking can be implemented with color based adaptive tracking method. Then, the objective can be simultaneously detected and tracked with moving camera, by distinguishing relative stationary and moving states. Finally, to verify the effectiveness of the proposed method, it is applied to borehole detection and tracking for a drilling robot in underground coal mine.

关键词： Object Detection ViBe algorithm camshift algorithm Borehole Recognition Coal Mine Drilling Robot

来源：评论

学校读者我要写书评

暂无评论

Vision based two-level hand tracking system for dynamic hand gestures in indoor environment

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2021年第13期80卷 20579-20598页

作者： Saboo, Shweta Singha, Joyeeta Dept Elect & Commun Jaipur Rajasthan India LNM Inst Informat Technol Jaipur 302031 Rajasthan India

Object detection and tracking is one of the most challenging phases in any image processing application. The challenges that arise during hand gesture recognition are: hand shape variation, presence of multiple persons, illumination variation or occlusion with background. In this paper, a robust hand detector and tracker algorithm has been proposed which overcomes the above difficulties to a great extent. The proposed system first detects hand using a combination of color and motion information. Then, the hand is tracked using combination of feature based tracker modified KLT algorithm and a color-based tracker camshift algorithm. New feature points have been added to our modified combination of feature and color based tracker. This prevents the loss of tracking as seen in traditional KLT algorithm. The experiments carried out using the proposed system shows that the system provides better results in comparison to the existing literatures on various challenging hand sequences.

关键词： Hand tracking Hand detection KLT algorithm Dynamic hand gestures camshift algorithm

来源：评论

学校读者我要写书评

暂无评论

Isolated Dynamic Persian Sign Language Recognition Based On camshift algorithm and Radon Transform

Isolated Dynamic Persian Sign Language Recognition Based On ...

引用

1st Iranian Conference on Pattern Recognition and Image Analysis (PRIA)

作者： Madani, Hadis Nahvi, Manoochehr Univ Guilan Dept Elect Engn DSP Res Lab Rasht Iran

ISBN: (纸本)9781467362061;9781467362047

Sign language is the initial tool for communication of deaf people in their everyday life. A lot of attention has recently been assigned to sign language recognition (SLR) by researchers in various domains such as computer vision, image processing and pattern recognition. Sign language gestures are divided in two groups, static and dynamic. The former includes the alphabets and the latter presents particular concepts. This paper presents a system for recognizing Persian sign language (PSL) in color video sequences. The system includes three main parts: tracking hand using continuously adaptive mean-shift (camshift) algorithm, feature extraction using radon transform and discrete cosine transform (DCT). Finally to evaluate the impact of feature extraction technique on recognition rate, four different classifiers include minimum distance (MD), K-nearest neighbor (KNN), neural network (NN), and support vector machine (SVM) are used. The experimental results show that the suggested system is successfully able to recognize Persian gestures.

关键词： camshift algorithm Hand gesture Hand tracking Sign language recognition Persian sign language PSL

来源：评论

学校读者我要写书评

暂无评论

Video-based pedestrian crossing the cordon detection system

Video-based pedestrian crossing the cordon detection system

引用

Chinese Automation Congress (CAC)

作者： Cui, Jianming Li, Xiaojian Zhang, Xiaojun Kong, Wenxiu Shandong Univ Sci & Technol Coll Comp Sci & Engn Qingdao Peoples R China Shandong Univ Sci & Technol Coll Elect Informat Engn Qingdao Peoples R China

ISBN: (纸本)9781728176871

In order to strengthen protection of personal safety and important places, this paper designs a pedestrian crossing the cordon detection system to process the image information captured by the camera intelligently in real time. Firstly, Gaussian mixture model is established to detect pedestrians. The detected target image is processed and initialized. Then target information is transferred to the camshift algorithm for tracking, which solves the problem of manually selecting tracking targets. The camshift algorithm combined with the Kalman filter which has update and prediction functions can overcome tracking failure due to interference and occlusion especially in the dark environment. On this basis, system can achieve crossing the cordon warning and information reporting to ensure the safety of people and important places. This system can be used in mines, culverts, tunnels and other dangerous and dark areas for safety protection, and has great practical application value.

关键词： pedestrian detection camshift algorithm Kalman filter dark environment interference occlusion crossing the cordon detection

来源：评论

学校读者我要写书评

暂无评论

Visual-based Tracking and Control algorithm Design for Quadcopter UAV 31

Visual-based Tracking and Control Algorithm Design for Quadc...

引用

31st Chinese Control And Decision Conference (CCDC)

作者： Qin, Xiangdong Wang, Tingting Hohai IJniv Sch Mech & Elect Engn Changzhou 213022 Jiangsu Peoples R China

ISBN: (纸本)9781728101057

The problems of tracking moving target of quad-rotor UAV involve target tracking in image sequence and flight control of UAV. Because camshift algorithm is easily disturbed by background with similar color and has poor robustness to occlusion interference when tracking objects in image sequence. A new tracking algorithm based on Kalman filter and camshift algorithm with multi-feature fusion is proposed. On this basis, the horizontal displacement between the target and the UAV is calculated as the control input, and a position-attitude outer-inner loop controller is designed to ensure the target near the center of view of the camera in order to track the target efficiently. Experimental and simulation results verify the performance of the algorithm.

关键词： quad-rotor UAV target tracking camshift algorithm outer-inner loop control

来源：评论

学校读者我要写书评

暂无评论

Dynamic Human Tracking for Mobile Robot 37

Dynamic Human Tracking for Mobile Robot

引用

37th Chinese Control Conference (CCC)

作者： Su, Li Zhu, Wei Wang, Boyu Harbin Engn Univ Coll Automat Harbin 150001 Heilongjiang Peoples R China

ISBN: (纸本)9789881563958

The movement of the robot adds great difficulty to dynamic human tracking. The traditional method of image stabilization can not remove the error caused by the movement of the human body to the stable image, resulting in low tracking accuracy and low real-time performance. This paper improves on the basis of traditional image stabilization techniques. In this paper, the least squares method is used to fit the position of the human body in the first N frames to infer the position of the human body in the (N + 1)th frame. Subsequently, this paper adopts the method of sub-regional gray projection to separate the positions of the human body in two adjacent frames of images and stabilize the images, which greatly reduces the error caused by the movement of the human body on the stable image distance. In addition, the traditional mobile body tracking method cannot solve the occlusion tracking situation of the target human body while satisfying the real-time performance. In this paper, various strategies such as camshift algorithm, particle filtering method, image stabilization, and cross-frame difference are integrated, and a dynamic evaluation strategy of tracking quality is designed. The strategy can realize the normal tracking of the moving human body in the state of dynamic robot and tracking of the target human body in the occlusion situation.

关键词： Dynamic background Target tracking Background compensation camshift algorithm Particle filter algorithm

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：