Abstract:It is well known that the accuracy of camera calibration is constrained by the size of the reference plate, it is difficult to fabricate large reference plates with high precision. Therefore, it is non-trivial to calibrate a camera with large field of view (FOV). In this paper, a method is proposed to construct a virtual large reference plate with high precision. Firstly, a high precision datum plane is constructed with a laser interferometer and one-dimensional air guideway, and then the reference plate is positioned at different locations and orientations in the FOV of the camera. The feature points of reference plate are projected to the datum plane to obtain a virtual large reference plate with high-precision. The camera is moved to several positions to get different virtual reference plates, and the camera is calibrated with the virtual reference plates. The experimental results show that the mean re-projection error of the camera calibrated with the proposed method is 0.062 pixels. The length of a scale bar with standard length of 959.778mm was measured with a vision system composed of two cali-brated cameras, and the length measurement error is 0.389mm.

Abstract:The process of wafer polishing is known to be highly demanding, and even small deviations in the processing parameters can have a significant impact on the quality of the wafers obtained. During the process of wafer polishing, maintaining a constant pressure value applied by the polishing head is essential to achieve the desired flatness of the wafer. The accuracy of the downward pressure output by the polishing head is a crucial factor in producing flat wafers. In this paper, the uncertainty component of downward pressure is calculated and its measurement uncertainty is evaluated, and a method for calculating downward pressure uncertainty traceable to international basic unit is established. Therefore, the reliability of double side polishing machine has been sig-nificantly improved.

Abstract:Aiming at the scattering and absorption of light in the water body, which causes the problems of color shift, uneven brightness, poor sharpness and missing details in the acquired underwater images, an underwater image enhancement algorithm based on IMSRCR and CLAHE-WGIF is proposed. Firstly, the IMSRCR algorithm proposed in this paper is used to process the original underwater image with adaptive color shift correction; secondly, the image is converted to HSV color space, and the segmentation exponential algorithm is used to process the S component to enhance the image saturation; finally, multi-scale Retinex is used to decompose the V component image into detail layer and base layer, and adaptive two-dimensional gamma correction is made to the base layer to adjust the brightness unevenness, while the detail layer is processed by CLAHE-WGIF algo-rithm to enhance the image contrast and detail information. The experimental results show that our algorithm has some advantages over existing algorithms in both subjective and objective evaluations, and the information entropy of the image is improved by 6.3% on average, and the UIQM and UCIQE indexes are improved by 12.9% and 20.3% on average.

Abstract:Aiming at the problem that indoor positioning technology based on wireless ultra-wideband pulse technology is susceptible to non-line-of-sight effects and multipath effects in confined spaces and weak signal environments, a high-precision positioning system based on UWB and IMU in a confined environment is designed. The STM32 chip is used as the main control, and the data information of IMU and UWB is fused by the fusion filtering algorithm. Finally, the real-time information of the positioning is transmitted to the host computer and the cloud. The experimental results show that the positioning accuracy and positioning stability of the system have been improved in the non-line-of-sight case of closed environment. The system has high positioning accuracy in a closed environment, and the components used are consumer-grade, which has strong practicability.

Abstract:Aiming at the problem of greenhouse environmental information collection in agricultural production, this paper designs a greenhouse monitoring system based on STM32 microcontroller. The system uses STM32F103 series MCU as the main control unit, which is used to receive the detection results of the sensor. The host computer software displays and processes the monitoring data. The temperature and humidity sensors monitor air temperature and humidity. The capacitive soil moisture detection sensor monitors soil moisture. The carbon dioxide sensor monitors the concentration of carbon dioxide. The photosensitive sensor monitors light intensity. This design has low hardware cost and high data acquisition accuracy, which can be applied to the actual greenhouse agricultural production and has wide practicability.

Abstract:Violence detection is very important for public safety. However, violence detection is not an easy task. Because recognizing violence in surveillance video requires not only spatial information but also sufficient temporal information. In order to highlight the time information, we propose an efficient deep learning architecture for violence detection based on temporal attention mechanism, which utilizes pre-trained MobileNetV3, convolu-tional LSTM and temporal attention block Temporal Adaptive (TA). TA block can focus on further refining temporal information from spatial information extracted from backbone. Experimental results show the pro-posed model is validated on three publicly datasets: Hockey Fight, Movies, and RWF-2000 datasets.

Abstract:This paper presents a low sampling rate digital pre-distortion technique based on an improved Chebyshev polynomial for the non-linear distortion problem of amplifiers in 5G broadband communication systems. An improved Chebyshev polynomial is used to construct the behavioural model of the broadband amplifier, and an undersampling technique is used to sample the output signal of the amplifier, reduce the sampling rate, and extract the pre-distortion parameters from the sampled signal through an indirect learning structure to finally correct the non-linearity of the amplifier system. This technique is able to improve the linearity and efficiency of the power amplifier and provides better flexibility. Experimental results show that by constructing the behav-ioural model of the amplifier using memory polynomials (MP), generalised polynomials (GMP) and modified Chebyshev polynomials respectively, the adjacent channel power ratio of the obtained system can be improved by more than 13.87dB, 17.6dB and 19.98dB respectively compared to the output signal of the amplifier without digital pre-distortion. The Chebyshev polynomial improves the neighbourhood channel power ratio by 6.11dB and 2.38dB compared to the memory polynomial and generalised polynomial respectively, while the normalised mean square error is effectively improved and enhanced. This shows that the improved Chebyshev pre-distortion can guarantee the performance of the system and improve the non-linearity better.