Unmanned rollers are typically equipped with satellite-based positioning systems for positional monitoring. However, satellite-based positioning systems may result in unmanned rollers driving out of the specified compaction areas during asphalt road construction, which affects the compaction quality and has potential safety hazards. Additionally, satellite-based positioning systems may encounter signal interference and cannot locate unmanned rollers. To solve this problem, a lateral positioning method for unmanned rollers is proposed to realize the positioning of unmanned rollers relative to asphalt road. First, we captured images from different perspectives and developed a dataset for asphalt road construction. Second, a method for boundary extraction of asphalt road is proposed to accurately locate pixels of asphalt road boundary. Subsequently, the lateral distances are measured by the designed lateral positioning methods. Finally, field validation experiments are conducted to evaluate the effectiveness of the proposed lateral positioning method. The results indicate that the method excels in extracting the asphalt road boundary. Furthermore, the proposed lateral positioning method shows excellent performance, with a mean relative error of 3.40% and a frequency of 6.25 Hz. The proposed lateral positioning method meets the performance requirements for lateral positioning in both accuracy and real-time in asphalt road construction for unmanned rollers.

Research on systems that imitate the gaze function of human eyes is valuable for the development of humanoid eye intelligent perception. However, the existing systems have some limitations, including the redundancy of servo motors, a lack of camera position adjustment components, and the absence of interest-point-driven binocular cooperative motion-control strategies. In response to these challenges, a novel biomimetic binocular cooperative perception system (BBCPS) was designed and its control was realized. Inspired by the gaze mechanism of human eyes, we designed a simple and flexible biomimetic binocular cooperative perception device (BBCPD). Based on a dynamic analysis, the BBCPD was assembled according to the principle of symmetrical distribution around the center. This enhances braking performance and reduces operating energy consumption, as evidenced by the simulation results. Moreover, we crafted an initial position calibration technique that allows for the calibration and adjustment of the camera pose and servo motor zero-position, to ensure that the state of the BBCPD matches the subsequent control method. Following this, a control method for the BBCPS was developed, combining interest point detection with a motion-control strategy. Specifically, we propose a binocular interest-point extraction method based on frequency-tuned and template-matching algorithms for perceiving interest points. To move an interest point to a principal point, we present a binocular cooperative motion-control strategy. The rotation angles of servo motors were calculated based on the pixel difference between the principal point and the interest point, and PID-controlled servo motors were driven in parallel. Finally, real experiments validated the control performance of the BBCPS, demonstrating that the gaze error was less than three pixels.

It is a challenging problem to extract aero-engine fault signals which contaminated by non-Gaussian noises under complex operation conditions. A Learnable Wavelet Packet De-noising Network (LWPD-Net) is proposed in this paper to address it. The highlights of LWPD-Net are to performs multi-scale decomposition of the original signal to extract features across various frequency bands, and more importantly the Double-Sharp threshold function with learnable parameter is employed to suppresses the non-Gaussian noise. Moreover, supervised learning strategy is adopted to learn LWPD-Net parameters for adaptively enhancing the fault features through conducting training samples from fault signals corrupted by non-Gaussian noises. Simulation experiments show that LWPD-Net can recover fault feature frequencies in the envelope spectrum for varying noise levels, and achieves satisfying fault feature extraction performances. Additionally, experiments conducted on aero-engine gear hubs confirm that the proposed method can recover the spectral features of vibration signals interfered with non-Gaussian noise under different operation conditions.

A detail-enhanced multi-exposure image fusion method was proposed to address the problem of low weights obtained in the light and dark regions in the sequence image,resulting in the loss of details in the bright and dark regions of the fused image.Wavelet decomposition was conducted on the sequence image and the fused image based on the weight map.This process involved extracting the low-frequency components from the fused image and the high-frequency components from the edge regions,and they were fused with the high-frequency components from the non-edge regions of the sequence image.Finally,the detail-enhanced fused image was obtained through wavelet inverse transform.Experimentally,nine sets of classical multi-exposure image sequences were selected for comparison with nine multi-exposure image fusion algorithms in terms of subjective comparison and objective evaluation,respectively.The results demonstrated that the proposed method,which combined the spatial and frequency domain image fusion methods,could effectively solve the problem of detail loss in the bright and dark areas of fused images,while avoiding the problem of ringing phenomenon often encountered in frequency domain image fusion methods.The fused images were realistic,natural,and exhibited vibrant colors.The mean image information entropy value and the mean image gradient value of the fused images obtained through the proposed method were 7.6555 and 7.0273,respectively,ranking first and second among the ten multi-exposure image fusion algorithms.Considering both subjective and objective evaluation results,the proposed method outperformed the nine comparative methods.

Aiming at realizing monocular 3D perception based on the motion parallax for the robot before its body starts to move, a visual 3D perception method based on the monocular single-degree-of-freedom rotation (V3PM-MSR) is proposed. The camera is fixed on the single-degree-of-freedom rotary platform, and the motion parallax is generated by the camera motion. The 3D coordinates of the object points are calculated by the derived principle of V3PM-MSR and the acquired input parameters of V3PM-MSR. In addition, the device is designed to achieve the transformation of V3PM-MSR from theory to practice. Finally, the experiment validates the effectiveness of V3PM-MSR and shows that the minimum relative error is 0.46%. It indicates that the monocular 3D perception based on the motion parallax for the robot can be effectively realized by V3PM-MSR before its body starts to move. Furthermore, the paper also has the application potential in the visual omnidirectional perception of the robot.

Conventional SIFT image feature extraction methods have difficulty in extracting features from the defocused blurred area of multi-focus images.As a result,common features between images are local and few,leading to poor accuracy in multi-focus image registration,which seriously affects the quality of subsequent image fusion and 3D reconstruction.Based on analyzing the uncertainty of feature extraction from the defocused blurred areas of images,a feature extraction method is proposed for the defocused blurred area of multi-focus images.First,features are extracted from the focused clear area of multi-focus images.Subsequently,the features in the corresponding defocused blurred area are extracted using optical flow tracking,thereby avoiding the uncertainty of directly extracting features from the defocused blurred ar-ea.Experimental results show that the proposed method displays good feature extraction ability and accura-cy in the defocused blurred area,significantly increasing the number of features matches.Feature extrac-tion error ranges between 0.03-0.39 pixels,which is better than the 0.21-1.71 pixels of existing meth-ods.This indicates a reduction in the uncertainty of feature extraction from the defocused blurred area,making it suitable for multi-focus image registration.

Accurate Remaining Useful Life (RUL) prediction of turbofan engines not only reduces labor and maintenance costs but also mitigates the risk of aircraft accidents. To solve the noise interference problem, we present a Legendre memory model enabled Attention Network (LAN). The LAN utilizes Legendre memory model and dual multi-head self-attention. Legendre memory model contains two sub-layers: Legendre Projection Unit (LPU) and Frequency Selection Layer (FSL). The sensor data is projected into the state space using the LPU to retain the historical data information. Next, frequency components are selected using the FSL to reduce the impact of noise. Meanwhile, the dual multi-head self-attention is applied to capture useful feature information from both the time step and sensor dimensions for RUL prediction. Lastly, the extracted features are inputted into the residual convolutional network for RUL prediction. Experiments are performed on the widely adopted C-MAPSS dataset, and the results substantiate the efficacy of the proposed approach.

针对传统Canny算子对道路标线检测不全、阈值选取困难及检测结果中噪声和伪边缘较多的问题,提出了一种新的道路标线检测算法.根据提出的程序框图对图像进行形态学预处理,结合提出的两个标准,自动寻找到Canny算子提取道路标线的最佳阈值,并利用该阈值对图像进行边缘检测,使用提出的两种后续处理方式剔除伪边缘和路面干扰.实验结果表明,该算法能够克服传统Canny算子在道路标线检测中存在的上述问题,实现道路标线准确检测.