Non-contact and active vegetation or plant parameters extraction using hyperspectral information is a prospective research direction among the remote sensing community. Hyperspectral LiDAR (HSL) is an instrument capable of acquiring spectral and spatial information actively, which could mitigate the environmental illumination influence on the spectral information collection. However, HSL usually has limited spectral resolution and coverage, which is vital for vegetation parameter extraction. In this paper, to broaden the HSL spectral range and increase the spectral resolution, an Acousto-optical Tunable Filter based Hyperspectral LiDAR (AOTF-HSL) with 10 nm spectral resolution, consecutively covering from 500–1000 nm, was designed. The AOTF-HSL was employed and evaluated for vegetation parameters extraction. “Red Edge” parameters of four different plants with green and yellow leaves were extracted in the lab experiments for evaluating the HSL vegetation parameter extraction capacity. The experiments were composed of two parts. Firstly, the first-order derivative of the spectral reflectance was employed to extract the “Red Edge” position (REP), “Red Edge” slope (RES) and “Red Edge” area (REA) of these green and yellow leaves. The results were compared with the referenced value from a standard SVC^© HR-1024 spectrometer for validation. Green leaf parameter differences between HSL and SVC results were minor, which supported that notion the HSL was practical for extracting the employed parameter as an active method. Secondly, another two different REP extraction methods, Linear Four-point Interpolation technology (LFPIT) and Linear Extrapolation technology (LET), were utilized for further evaluation of using the AOTF-HSL spectral profile to determine the REP value. The differences between the plant green leaves’ REP results extracted using the three methods were all below 10%, and the some of them were below 1%, which further demonstrated that the spectral data collected from HSL with this spectral range and resolution settings was applicable for “Red Edge” parameters extraction.

This paper offers a solution to challenge navigation in the indoor environment by making use of the existing infrastructure. Estimating pedestrian trajectory using pedestrian dead reckoning (PDR) and WiFi is a very popular technique. However, cumulative errors and mismatching are major problems in PDR and WiFi fingerprint matching, respectively. PDR and pedestrian heading are used as the state transition equation, and the step length and WiFi matching results are used as observation equations. A federated particle filter (FPF) based on the principle of information sharing is proposed to fusion PDR and WiFi, which improves pedestrian navigation accuracy. The experimental results show that the average positioning accuracy is 0.94 m and 1.5 m, respectively.

LiDAR has become a vital sensor for autonomous driving scene understanding. To meet the accuracy and speed of LiDAR point clouds semantic segmentation, an efficient model ACPNet is proposed in this paper. In the feature extraction stage, the backbone is constructed with asymmetric convolutions, so the skeleton of the square convolution kernel is enhanced, which leads to greater robustness to target rotation. Moreover, a contextual feature enhancement module is designed to extract richer contextual features. During training, global scaling and global translation are performed to enrich the diversity of datasets. Compared with the baseline network PolarNet, the mIoU of ACPNet on the SemanticKITTI, SemanticPOSS and nuScenes datasets are improved by 5.1%, 1.6% and 2.9%, respectively. Meanwhile, the speed of ACPNet is 14 FPS, which basically meets the real-time requirements in autonomous driving scenarios. The experimental results show that ACPNet significantly improves the performance of LiDAR point cloud semantic segmentation.

Based on the analysis of the accurate estimation method of the state of charge (SOC) of lithium battery for electric vehicles, aiming at the shortcomings of back propagation (BP) neural network model, an algorithm based on Improved Particle Swarm Optimization (IPSO) is proposed to optimize the parameters of BP neural network. In this algorithm, the particle swarm optimization algorithm is optimized by introducing shrinkage factor to limit the particle speed, so as to determine the initial parameters of BP neural network. Finally, the battery estimation model is established by using the data set of lithium battery published by NASA PCoE, and the simulation test is carried out by using MATLAB platform. The results show that the method can effectively reduce the SOC error and control the error within 2%. It has practical significance for SOC estimation in battery management system.

WiFi fingerprint-based positioning is a method for indoor localization with the advent of widespread deployment of WiFi and the Internet of Things. However, single WiFi fingerprint positioning has the problems of mismatch, unstable signal strength and limited accuracy. Aiming to address these issues, this paper proposes the fusion algorithm combining WiFi and pedestrian dead reckoning (PDR). Firstly, the particle swarm optimization (PSO) model is utilized to optimize the weighted k-nearest neighbors (WKNN) in the WiFi part. Additionally, the artemisinin optimization (AO) algorithm is used to optimize the particle filter (PF) to improve the fusion effect of the WiFi and PDR. Finally, to thoroughly validate the localization performance of the proposed algorithm, we designed experiments involving two scenarios with four smartphone gestures: calling, dangling, handheld, and pocketed. The experimental results unequivocally indicate that the positioning error of AO-PSO-PF algorithm is lower than that of other algorithms including PDR, WiFi, PF, APF, and FPF. The average positioning errors for the two experiments are 0.95 m and 1.42 m, respectively.