Video-based noncontact detection of heart rate has a wide range of applications in the field of medicine and health. However, this method is susceptible to noise interference, making it difficult to effectively extract blood volume pulse (BVP) signals. To overcome this problem, a new method of noncontact heart rate estimation that can suppress noise interference is proposed in this paper. First, the established data acquisition system conducts video collection, and the captured videos are divided into multiple small regions. Subsequently, the initial signals of BVP are extracted in accordance with the chrominance features extracted through multi-channel data fusion. The BVP signals are separated using the FastICA algorithm. The kurtosis value and signal-to-noise ratios of the power spectrum of the separated signals are analyzed to determine the effective separation component. Results show that this method can extract and process pulse signals, effectively suppressing non-periodic interference. The experiment also proves that the method has good consistency with the measurement of pulse oximeter and has good stability and accuracy in the detection of heart rate of the human body.
Defects in labeling represent a prevalent issue that significantly impacts product quality during the manufacturing process. In response to the challenges associated with the detection of label stain defects, this research introduces an enhanced version of the CenterNet algorithm, termed Improved CenterNet. This novel approach predicts the centroid of the object, the diagonal length, and the sine value, which collectively contribute to the optimization of the loss function. This innovation effectively mitigates the problem of disproportionately large loss values, facilitating the accurate estimation of the object's dimensions. When compared to the conventional CenterNet, the Improved CenterNet algorithm not only preserves real-time performance but also markedly enhances the precision and robustness of the detection process. By integrating a sine value prediction mechanism, the algorithm demonstrates a heightened capacity to discern stains against intricate background contexts. Empirical findings indicate that the Improved CenterNet algorithm yields superior performance on a dataset of label stain defects, fulfilling the industrial demand for high-efficiency and high-accuracy defect detection in the manufacturing sector.
This paper describes a single-loop 3rd-order continuous time Sigma Delta modulator for audio applications in 180nm CMOS technology. It uses a feedforward topology structure that employs summation ahead technology to reduce circuit power consumption. Meanwhile, it adopts the Negative-R compensation technology to compensate the non-ideal factors of the active RC integrator, and the quantizer consists of a 3-bit flash ADC with low kickback noise dynamic comparator so that improve modulator resolution. The simulation results show that at 1. 8V supply voltage, the SNDR is 109.3 dB, the power consumption is 461.8$\mu$W, and the FOMSNDR is 185.7 dB.
In the label manufacturing industry, accurately identifying label positioning defects is of great significance for ensuring product quality. However, traditional defect detection techniques have faced significant challenges due to the diversity of label materials and the complexity of imaging conditions. In recent years, semantic segmentation technology has made breakthrough progress in the field of image processing, providing innovative solutions to the aforementioned issues. This study proposes a semantic segmentation framework that integrates ResNet50 and Global Context (GCNet) modules, aiming to accurately identify label positioning defects. Through the training of a deep learning model, this framework achieves precise delineation of the label area and effectively determines positioning defects. The experiment was conducted using a dataset composed of 1653 manually annotated images, and the results revealed that the proposed algorithm has significant advantages in terms of segmentation accuracy and algorithm robustness. The algorithm developed in this study demonstrates high efficiency in detecting label positioning defects, providing an innovative technical approach for automated quality control systems.
Defects on the feather leaf are mainly scar, wormhole and stain. Accurate segmentation of these defects on feather leaf will improve largely the quality of the feather. In this study, this paper analyses brightness distribution characteristic of feather image, proposes a denoising method based on the improved mean shift . The outstanding of differences between feather leaf and feather defect can be gotten by this proposed method. Experimental results with both better value of evaluation index and improved visual quality indicated the successful implementation of the proposed method in the denoising of feather images. Moreover, the algorithm can accurately segment feather image and effectively suppress the undesired background texture information to segment feather image with unclear color information.