This paper proposes a method for salient crowd motion detection based on direction entropy and a repulsive force network. This work focuses on how to effectively detect salient regions in crowd movement through calculating the crowd vector field and constructing the weighted network using the repulsive force. The interaction force between two particles calculated by the repulsive force formula is used to determine the relationship between these two particles. The network node strength is used as a feature parameter to construct a two-dimensional feature matrix. Furthermore, the entropy of the velocity vector direction is calculated to describe the instability of the crowd movement. Finally, the feature matrix of the repulsive force network and direction entropy are integrated together to detect the salient crowd motion. Experimental results and comparison show that the proposed method can efficiently detect the salient crowd motion.

/pdf/detection-of-salient-crowd-motion-based-on-repulsive-force-3wdohhjowm.pdf

Detection of Salient Crowd Motion Based on Repulsive Force Network and Direction Entropy

The invention discloses an intelligent community illegally-parked vehicle alarm system and method based on an image identification algorithm. By arranging a vehicle identification module at an entrance of a community and arranging monitoring cameras on a road in the community, road monitoring covers all road surfaces, and license plates are used as marks to achieve real-time monitoring and positioning of position information of vehicles entering the community. Illegally-parked vehicles entering the community are found in time and automatically alarmed, suspicious or determined illegal parkingpersons are prompted to find and handle illegal parking behaviors, and for owners not complying with prompting cautions to illegally park vehicles, the information and positions of the illegally-parked vehicles are sent to a monitoring room, and community managers perform manual handling.

Intelligent community illegally-parked vehicle alarm system and method based on image identification algorithm

The invention provides a method for video monitoring of foreign vehicles passing in and out of community. An access control system is arranged at an entrance of the community, photograph cameras are respectively arranged in two sides of the access control system, and a central monitoring chamber is arranged and comprises a microprocessor module and a display and a memory connected to the microprocessor module. Temporary parking spaces in the community are numbered, cameras are arranged at the temporary parking spaces to cover the temporary parking spaces and the access control system, the cameras and the photograph cameras are respectively communicated with the microprocessor module. A memory stores resident vehicle information in the community. The method comprises carrying out monitoringon people passing in and out of the entrance of the community in real time through the microprocessor module and controlling opening and closing of the access control system. The method for video monitoring of foreign vehicles passing in and out of community has the advantages of scientific design, simple operation, comprehensive monitoring, strong safety and good protection effect.

Method for video monitoring of foreign vehicles passing in and out of community

Learning transfer is widely present in the learning of all kinds of knowledge, skills and social norms, and is one of the important phenomena of learning, and the reasonable use of transfer is conducive to improving the learning effect of students and the quality of teaching. This study starts from the data of college students' academic performance, takes real students' academic performance as a sample, measures the relevance of courses through students' academic performance, constructs various networks of learning transfer, and studies the topology and evolution of the networks to clarify the essential laws of learning transfer and put forward suggestions for the optimization of teaching strategies. Finally, using complex network analysis to analyze and mine the data on college students' academic performance, the article quantifies the overall structure of the courses and their hidden connections in a global and dynamic manner, and discovers the inheritance relationship between the courses, the clustering characteristics and the basic pattern of learning transfer. It also provides a platform for exploring the differences in the course structure of different majors and the learning transfer of male and female students.

/pdf/an-approach-to-the-permeation-mechanism-of-learning-transfer-27bbxacxf0.pdf

An approach to the permeation mechanism of learning transfer and teaching strategy in physical education based on complex network.

The utility model discloses a residential communities ground parking stall guiding device based on video image, camera, AD converter, video image collector, wireless data transmission unit and video image treater are gathered including the vehicle profile image who connects gradually to ground parking stall monitor, and vehicle profile image gathers the camera installation and sets up in ground parking stall top, road video image gathers the camera and installs the top at the road. The utility model discloses utilize parking stall image supervision camera and mileage chart to acquire idle parking stall in real time and get into the vehicle form path information in the community like keeping watch on the camera to with these two kinds of real -time demonstrations of information on the display screen of community entry, information acquisition equipment only needs the video camera, the video camera is the partly of parking stall guiding device promptly, also is simultaneously the partly of community's security monitoring, has the video monitoring function, has reduced the management system's of community cost.

Residential communities ground parking stall guiding device based on video image

Under the perspectives of network science and modern educational science, the complex network model is a better tool for teaching evaluation then the context of traditional evaluation methods, whose potential mainly unexplored yet. In this work, we propose a new method to construct teaching evaluation network model based on complex network theory. Furthermore, the proposed method is evaluated on the “VC++ program design” course. We present an exhaustive topological analysis of the teaching evaluation network of “VC++ program design” course, focusing on the statistical characterization of degree and closeness centrality. The results demonstrate that the vast majority of students received similar learning outcomes, while there is a small received excellent learning outcomes. These results are the same as the practical situation. We believe that the newly assembled model, which is a weight complex network, can provide valuable hints of teaching evaluation.

An evaluation model of curriculum teaching base on complex network theory

Interest point detection is one of the key technologies in image processing and target recognition. This paper presents a new method for detecting interest points in digital images and computer vision problems based on complex network theory. We associate a directed and weighted complex network model to each image and then we propose three different algorithms to locate these key points based on three topological features of image complex network model, which are degree, closeness and betweenness.

Interest point detection in images based on topology structure features of directed complex network

Key point detection is still a challenging issue in pattern recognition. With the recent developments on complex network theory, pattern recognition techniques based on graphs have improved considerably. Key point detection can be approached by community identification in directed complex network because image is related with network model. This paper presents a complex network approach for key point detection in video monitoring image, which is both accurate and fast. We evaluate our method for square and subway station video monitoring images. Results show that our algorithm can outperform other traditional method both in accuracy and processing times.

Key Point Detection in Images Based on Triangle Distribution of Directed Complex Network

The invention discloses a sunlight concentrating device, which comprises a main controller, a solar cell panel, at least two sunlight sensors evenly distributed at the edge of the solar cell panel anda plurality of biaxial concentrating mirrors evenly distributed at the edge of the solar cell panel. The sunlight sensors are used for detecting the incidence angle of sunlight. The output end of each sunlight sensor is connected with the signal input end of the main controller. The control output end of the main controller is connected with the control input end of each biaxial concentrating mirror. The main controller is used for controlling the rotation angle of each biaxial concentrating mirror according to the incidence angle. The sunlight concentrating device of the invention can reducethe energy consumption in the tracking process.

Qingyu Zou

Papers

Residential communities ground parking stall guiding device based on video image

An evaluation model of curriculum teaching base on complex network theory

Interest point detection in images based on topology structure features of directed complex network

Key Point Detection in Images Based on Triangle Distribution of Directed Complex Network

Sunlight concentrating device