In order to improve the effects of denoising, this paper introduces the basic principles of wavelet threshold denoising and traditional structures threshold functions. Meanwhile, it proposes wavelet threshold function and fixed threshold formula which are both improved here. First, this paper studies the problems existing in the traditional wavelet threshold functions and introduces the adjustment factors to construct the new threshold function basis on soft threshold function. Then, it studies the fixed threshold and introduces the logarithmic function of layer number of wavelet decomposition to design the new fixed threshold formula. Finally, this paper uses hard threshold, soft threshold, Garrote threshold, and improved threshold function to denoise different signals. And the paper also calculates signal-to-noise (SNR) and mean square errors (MSE) of the hard threshold functions, soft thresholding functions, Garrote threshold functions, and the improved threshold function after denoising. Theoretical analysis and experimental results showed that the proposed approach could improve soft threshold functions with constant deviation and hard threshold with discontinuous function problems. The proposed approach could improve the different decomposition scales that adopt the same threshold value to deal with the noise problems, also effectively filter the noise in the signals, and improve the SNR and reduce the MSE of output signals.

As an essential procedure of data fusion, LiDAR-camera calibration is critical for autonomous vehicles and robot navigation. Most calibration methods require laborious manual work, complicated environmental settings, and specific calibration targets. The targetless methods are based on some complex optimization workflow, which is time-consuming and requires prior information. Convolutional neural networks (CNNs) can regress the six degrees of freedom (6-DOF) extrinsic parameters from raw LiDAR and image data. However, these CNN-based methods just learn the representations of the projected LiDAR and image and ignore the correspondences at different locations. The performances of these CNN-based methods are unsatisfactory and worse than those of non-CNN methods. In this paper, we propose a novel CNN-based LiDAR-camera extrinsic calibration algorithm named CFNet. We first decided that a correlation layer should be used to provide matching capabilities explicitly. Then, we innovatively defined calibration flow to illustrate the deviation of the initial projection from the ground truth. Instead of directly predicting the extrinsic parameters, we utilize CFNet to predict the calibration flow. The efficient Perspective-n-Point (EPnP) algorithm within the RANdom SAmple Consensus (RANSAC) scheme is applied to estimate the extrinsic parameters with 2D–3D correspondences constructed by the calibration flow. Due to its consideration of the geometric information, our proposed method performed better than the state-of-the-art CNN-based methods on the KITTI datasets. Furthermore, we also tested the flexibility of our approach on the KITTI360 datasets.

Ultrafast ultrasound imaging remains an active area of interest in the ultrasound community due to its ultrahigh frame rates. Recently, a wide variety of studies based on deep learning have sought to improve ultrafast ultrasound imaging. Most of these approaches have been performed on radio frequency (RF) signals. However, in- phase/quadrature (I/Q) digital beamformers are now widely used as low-cost strategies. In this work, we used complex convolutional neural networks for reconstruction of ultrasound images from I/Q signals. We recently described a convolutional neural network architecture called ID-Net, which exploited an inception layer designed for reconstruction of RF diverging-wave ultrasound images. In the present study, we derive the complex equivalent of this network, i.e., complex-valued inception for diverging-wave network (CID-Net) that operates on I/Q data. We provide experimental evidence that CID-Net provides the same image quality as that obtained from RF-trained convolutional neural networks, i.e., using only three I/Q images, CID-Net produces high-quality images that can compete with those obtained by coherently compounding 31 RF images. Moreover, we show that CID-Net outperforms the straightforward architecture that consists of processing real and imaginary parts of the I/Q signal separately, which thereby indicates the importance of consistently processing the I/Q signals using a network that exploits the complex nature of such signals.

For camera calibration based on direct linear transformation (DLT), the camera’s intrinsic and extrinsic parameters are simultaneously calibrated, which may cause coupling errors in the parameters and affect the calibration parameter accuracy. In this paper, we propose an improved direct linear transformation (IDLT) algorithm for calibration parameter decoupling. This algorithm uses a linear relationship of calibration parameter errors and obtains calibration parameters by moving a three-dimensional template. Simulation experiments were conducted to compare the calibration accuracy of DLT and IDLT algorithms with image noise and distortion. The results show that the IDLT algorithm calibration parameters achieve higher accuracy because the algorithm removes the coupling errors.

Detecting loop closures in dynamic environments is a severe challenge for the simultaneous localization and mapping (SLAM) system. Convolutional neural networks (ConvNet) could provide highlevel and abstract representations extracted directly from images as image descriptors. Some novel ConvNet-based methods have been presented. In dynamic environments, they perform better than the stateof-the-art methods which use hand-crafted features. In this paper, (1) We proposed a flexible loop closure detection workflow based on the holistic representations; (2) In this workflow, a post-processing method is applied to the raw holistic ConvNet representations for redundant information compression; (3) In addition, a compression ratio is introduced in (2) to determine how much information will be retained depending on background change and moving objects. We evaluated our workflow in four open datasets. The experimental results demonstrate that the proposed workflow performs better than many state-of-the-art methods and ConvNet-based approaches.