Advanced Materials Research Vols. 945-949

Abstract: In recent years, wireless communication plays an important role in many fields. This paper put forward a design of wireless transmission system based on nRF24L01 chip and STC89C52RC. It can realize a multi-point measurement, such as temperature, liquid level and displacement measurement at a high rate and low cost. It reduces current consumption and data collisions. More functions are to be added to the system in further experiments.

Abstract: In view of the safety and real-time responsiveness of auto electric window system requirements, using the embedded system design based on PIC18F2480 microcontroller and automatic code generator of intelligent control system for electric sunroof, the system adopts the hall sensor measurement skylight switch's real-time position, permanent magnet motor load torque change rate is chosen as the obstacle detection judgement index, the system is stable and reliable operation.

Abstract: Spectrum analysis is the superposition signal intodifferent frequency component and the imaginary indexcomponent, the analysis of signal from the frequency point of view. It is widely used in voice processing, image processing, digital audio, seismic exploration. The FFT algorithm, provides an effective solution forreal-time processing of frequency domain analysis. Music display system based on FFT spectrum, the main work is as follows:First, the fast Fourier transform ideas a brief description, and combined with the specific hardware and software implementations of the algorithm of the system used by the fast Fourier transform is described in detail. Then, describes the main hardware devices used in the system, including STC12C5A60S2 chips, display principle Principle 32 * 64LED dot matrix screen, use 74LS595 and 74LS164's. The system is simple, easy to use, you can use STC12C5A60S2 SCM data processing functions of the sound signal spectrum analysis.

Abstract: Currently embedded software reliability testing of intellectual ammeter is through software comparison, which has poor scalability and can’t detect software’s fault tolerance ability after failure in running scene. In this regard, this paper presents a detection platform’s construction scheme for intellectual ammeter software reliability testing and designs testing communication protocol based on Ethernet master-slave mode. Experiments prove that the testing protocol possesses high usability and flexibility, and has value for intellectual ammeter software testing.

Abstract: Chin-up physical exercises need to be judged regular or foul and counted, the work can be automated finished by computer based on image recognition accurately and objectively. There are two difficulties in this automated system: one is to judge whether chin has been above the bar, the other is to determine whether chin-up arms have moment unbent state during sagging. This paper proposed judging chin above bar by Microsoft Kinect depth image and determining arm unbending by skeletal tracking. Depth image can help image segmentation, and skeletal tracking can position key points of arms. Experimental results showed that the approach could automate judge chin-up rapidly, accurately and practically.

Abstract: Human behavior recognition is an active research field in computer vision and image processing. A novel method is proposed for human behavior recognition in video image sequences. First of all, a video sequence is represented by extracting space-time interest points. Then Human behavior is represented by activities through Motion Decomposition. The activity comprises labeled bags that are composed of unlabeled instances comprising to action. Final labeled activities are used to train a strong classifier which is used to predict the labels of unseen behavior bags. Experimental results show the effectiveness of the proposed method in comparison with other related works in the literature and can also tolerate noise and interference conditions.

Abstract: Using the method of image processing, some palm images are collected by scanner. Method of these images' key points' location and segmentation is researched. After proper preprocessing, images of palm's clear borderline can be acquired. A method of calculating distance derivative is used to mark the key points. Through experiments, it can be seen that the marking effect is good. The key points' marking method has positive significance to the development of automatic diagnostician.

Abstract: With the rapid development of China's automobile industry, intelligent transportation systems have become an important means of modern traffic management. The paper analyzes the prospects for detection of several sports: frame difference method, optical flow method and the background model, and compared the effects of several methods of detection, using a strong adaptability to disturbance Gaussian mixture background model to detect moving targets. Then the detected motion foreground image OTSU threshold, using morphological methods de-noising and holes filled, get a complete moving target. In this paper, the characteristics of the target shadow and existing methods are analyzed, using a shadow removal method based on color features.

Abstract: In order to adapt to the target appearance changes during visual tracking, feature model needs to be updated by online learning. However, online adaptive methods suffer from the drifting problem: error data are used for updating and will finally lead to tracking failure. In this paper, we propose a novel hierarchical online ensemble tracking method. Optical flow tracker is employed to predict the rough location. Online learning classifier is employed to detect the target. Template match is used to filter the data for updating. All these parts are combined together hierarchically by their confidence to ensure the stability of online learning and tracking. In contrast to the individual online learning and semi-supervised online learning, our method show more adaptability and stability. We demonstrate the performance on several public video sequences, which shows the improvement of our method over other online tracking approaches.

Abstract: In this paper, a robust face representation method based on multiple gradient orientations for face recognition is proposed. We introduce multiple gradient orientations and compute multiple orientation images which display different spatial locality and orientation properties. Each orientation image is normalized using the “z-score” method, and all normalized vectors are concatenated into an augmented feature vector. The dimensionality of the augmented feature vector is reduced by linear discriminant analysis to yield a low-dimensional feature vector. Experimental results show that our method achieves state-of-the-art performance for difficult problems such as illumination and occlusion-robust face recognition.