Autonomous driving, as a pivotal technology in modern transportation, is progressively transforming the modalities of human mobility. In this domain, vehicle detection is a significant research direction that involves the intersection of multiple disciplines, including sensor technology and computer vision. In recent years, many excellent vehicle detection methods have been reported, but few studies have focused on summarizing and analyzing these algorithms. This work provides a comprehensive review of existing vehicle detection algorithms and discusses their practical applications in the field of autonomous driving. First, we provide a brief description of the tasks, evaluation metrics, and datasets for vehicle detection. Second, more than 200 classical and latest vehicle detection algorithms are summarized in detail, including those based on machine vision, LiDAR, millimeter-wave radar, and sensor fusion. Finally, this article discusses the strengths and limitations of different algorithms and sensors, and proposes future trends.

The extraction of power line plays a key role in power line inspection by Unmanned Aerial Vehicles (UAVs). While it is challenging to extract power lines in aerial images because of the weak targets and the complex background. In this paper, a novel power line extraction method is proposed. First of all, we create a line segment candidate pool which contains power line segments and large amount of other line segments. Secondly, we construct the irregular graph model with these line segments as nodes. Then a novel object-based Markov random field with anisotropic weighted penalty (OMRF-AWP) method is proposed. It defines a new neighborhood system based on the irregular graph model and builds a new potential function by considering the region angle information. With the OMRF-AWP method, we can distinguish between the power line segments and other line segments. Finally, an envelope-based piecewise fitting (EPF) method is proposed to fit the power lines. Experimental results show that the proposed method has good performance in multiple scenes with complex background.

Electrostatic actuators are simple but important switching devices for microelectromechanical systems applications. Due to the difficulties associated with the electrostatic nonlinearity, precise mathematical description is often hard to obtain for the dynamics of these actuators. Here we present two sharp theorems concerning the dynamics of an undamped electrostatic actuator with one-degree of freedom, subject to linear and nonlinear elastic forces, respectively. We prove that both situations are characterized by the onset of one-stagnation-point periodic response below a well-defined pull-in voltage and a finite-time touch-down or collapse of the actuator above this pull-in voltage. In the linear-force situation, the stagnation level, pull-in voltage, and pull-in coordinate of the movable electrode may all be determined explicitly, following the recent work of Leus and Elata based on numerics. Furthermore, in the nonlinear-force situation, the stagnation level, pull-in voltage, and pull-in coordinate may be described completely in terms of the electrostatic and mechanical parameters of the model so that they approach those in the linear-force situation monotonically in the zero nonlinear-force limit.

Power line extraction is not only crucial for UAVs obstacle avoidance, but also a fundamental step for fault diagnosis of power lines. Therefore, achieving robust and accurate extraction of power lines in aerial images is essential to enable intelligent UAVs inspection. Unfortunately, power line extraction is an extremely challenging task, and all the current methods attempt to utilize a single model to solve the problem of power line extraction in complex and variable scenes. This results in insufficient generalization ability and suboptimal computational efficiency. In this work, we propose a power line scene classification network based on complexity assessment, named SceneNet, which can provide a solution for tackling power line extraction challenges. Firstly, we propose a human-machine hybrid reasoning model to obtain the ground truth of image complexity reasonably and build the first benchmark dataset that can be used for automatic classification research of power line scenes. Secondly, we propose an improved StyleGAN3 model and loop transfer learning strategy for data augmentation. Most importantly, the SceneNet comprises a multi-feature joint embedding module and a feature encoding-decoding module. On the one hand, it achieves the multi-level fusion of artificial features and high-dimensional semantic features. On the other hand, we use a self-attention mechanism to enable full use of the contextual association between each block of the fusion feature map. The SceneNet has successfully achieved the mapping and pattern recognition between the abstract concept and the concrete features. Experimental results demonstrate that the SceneNet is obviously superior to the existing 12 state-of-the-art models, and it provides guidance and delineation of applicable scenes for power line extraction methods.

Semantic segmentation is one of the most important tasks in remote sensing. In the semantic segmentation of remote sensing images, some regions are repeatedly transformed between multi-classes, which affects the convergence speed and segmentation accuracy. This is because the increased spatial resolution makes the spectral distribution of geographic targets differ from the overall category distribution. Markov random field (MRF) model is widely used for semantic segmentation of remote sensing images because of its outstanding spatial description ability. Some scholars have made improvements on MRF models to extract more information or enhance semantic inference. However, these improvements fail to capture the correlation between the multi-granularity layers and the historical information. In this article, we propose a new MRF-based model, which adopts multi-granularity layers to realize the multi-granularity correlation representation of targets and the spatial-temporal inference of segmentation labels. First, the algorithm constructs a multi-grained layer structure based on remote sensing images to enhance feature extraction for targets of different sizes in images; secondly, for the multi-layer feature field, a cross-layer Gauss-Markov model is constructed based on intra-inter-layer feature correlation constraints; then, for the multi-granularity layer label field, a self-renewing pairwise spatial-temporal potential function with blinking coefficients is constructed based on the newly defined cross-layer augmented neighborhood system, which can accelerate the convergence of segmentation by using the history information and spatial neighborhood information. The proposed method is tested on texture images, SPOT-5, and Gaofen-2 images. Experiments show that the proposed method has better performance compared to other state-of-the-art MRF-based methods.