A New Method of Recognizing Polygons under Perspective Transformation

Existing methods for recognizing polygons can be improved. A new concept ＂homograph＂ and then a new method for recognizing polygons based on the principle of homograph are proposed. First, five topological characteristics and geometrical characteristics are introduced that are invariant to describe polygon under perspective transformation. Then, the new concept of homograph is defined in terms of five topological characteristics and geometrical characteristics. Based on this definition, a new algorithm is proposed for recognizing that two polygons are homograph. The topological structure is introduced to analyze homograph qualitatively and the algorithm is insensitive to noises; and the geometrical structure is introduced to analyze homograph quantitatively, thus the algorithms can show tiny differences between polygons. It can not only recognize the objects with different shapes but also distinguish between objects with same shape but with different sizes and scales. Comparing with other recognition algorithms, the algorithm presented showed apparent improvement. The effectiveness of the algorithm is demonstrated by experiments.

Perspective in Development of Shape Memory Materials Associated with Martensitic Transformation

By consideration of the characteristics of martensitic transformation and the derivation from the application of the group theory to martensitic transformation, it may be concluded that the shape memory effect (SME) can be attained in materials through a martensitic transformation and its reverse transformation. only when there forms single or nearly single variant of martensite, with an absence of the factors causing the generation of the resistance against SME. on this principle, various shape memory materials including nonferrous alloys. iron-based alloys and ceramics containjng zirconia are expected to be further developed. A criterion for thermoelastic martensitic transformation is presented, Factors which may act as the resistance against SME in various materials are briefly described

People Flow Monitoring Based on Deep Learning

According to the application scenarios of the size of the humanflow in different consumption places,to solve the problem of crowd detection,distance estimation between crowds and the inability to monitor and calculate the humanflow in real time,this paper designs a real-time crowd detection scheme for appli-cation scenarios where consumers pay attention to the size of the humanflow in consumption places.The main use of the YOLO algorithm with the Darknet53 net-work as the main network is to separate pedestrians from the background.Pedes-trians’central two-dimensional coordinates are converted into three-dimensional coordinates,realizing crowd detection and apart from the distance estimation of crowds,real-time monitoring of current regional traffic andflow density,and solv-ing the problem of being unable to monitor and calculate people in real time.It can be applied to many aspects,such as shop rating,traffic control andflow control of scenic spots.Existing monitors are affected by different lights and cannot provide accurate data.In addition,the processing algorithm of this scheme is stable and accurate,and preprocessing is performed before judging the humanflow and the position of the human body to reduce the interference of light.This scheme has the performance of real-time monitoring and calculation through experimental verification.

Segment Based Camera Calibration

The basic idea of calibrating a camera system in previous approaches is to determine camera parameters by using a set of known 3D points as calibration reference.In this paper,we present a method of camera calibration in which camera parameters are determined by a set of 3D lines.A set of constraints is derived on camera parameters in terms of perspective line mapping.From these con- straints,the same perspective transformation matrix as that for point mapping can be computed linearly.The minimum number of calibration lines is 6.This result generalizes that of Lin,Huang and Faugeras for camera location determination in which at least 8 line correspondences are re- quired for linear computation of camera location.Since line segments in an image can be located easi- ly and more accurately than points,the use of lines as calibration reference tends to ease the compu- tation in image preprocessing and to improve calibration accuracy.Experimental results on the calibration along with stereo reconstruction are reported.

Critical Technical Awakenings

Starting with Philip E.Agre’s 1997 essay on“critical technical practice”,we consider examples of writings from computer science where authors describe“waking up”from a previously narrow technical approach to the world,enabling them to recognize how their previous efforts towards social change had been ineffective.We use these examples first to talk about the underlying assumptions of a technology-centric approach to social problems,and second to theorize these awakenings in terms of Paulo Freire’s idea of critical consciousness.Specifically,understanding these awakenings among technical practitioners as examples of this more general phenomenon gives guidance for how we might encourage and guide critical awakenings in order to get more technologists working effectively towards positive social change.