Automobile surface defects like scratches or dents occur during the process of manufacturing and cross-border transportation. This will affect consumers’ first impression and the service life of the car itself. In most worldwide automobile industries, the inspection process is mainly performed by human vision, which is unstable and insufficient. The combination of artificial intelligence and the automobile industry shows promise nowadays. However, it is a challenge to inspect such defects in a computer system because of imbalanced illumination, specular highlight reflection, various reflection modes and limited defect features. This paper presents the design and implementation of a novel automatic inspection system (AIS) for automobile surface defects which are the located in or close to style lines, edges and handles. The system consists of image acquisition and image processing devices, operating in a closed environment and noncontact way with four LED light sources. Specifically, we use five plane-array Charge Coupled Device (CCD) cameras to collect images of the five sides of the automobile synchronously. Then the AIS extracts candidate defect regions from the vehicle body image by a multi-scale Hessian matrix fusion method. Finally, candidate defect regions are classified into pseudo-defects, dents and scratches by feature extraction (shape, size, statistics and divergence features) and a support vector machine algorithm. Experimental results demonstrate that automatic inspection system can effectively reduce false detection of pseudo-defects produced by image noise and achieve accuracies of 95.6% in dent defects and 97.1% in scratch defects, which is suitable for customs inspection of imported vehicles.

Remote sensing change detection (RSCD) aims to utilize paired temporal remote sensing images to detect surface changes in the same area. Traditional CNN-based methods are limited by the size of the receptive field, making it difficult to capture the global features of remote sensing images. In contrast, Transformer-based methods address this issue with their powerful modeling capabilities. However, applying the Transformer architecture to image processing introduces a quadratic complexity problem, significantly increasing computational costs. Recently, the Mamba architecture based on state-space models has gained widespread application in the field of RSCD due to its excellent global feature extraction capabilities and linear complexity characteristics. Nevertheless, existing Mamba-based methods lack optimization for complex change areas, making it easy to lose shallow features or local features, which leads to poor performance on challenging detection cases and high-difficulty datasets. In this paper, we propose a Mamba-based RSCD network for difficult cases (DC-Mamba), which effectively improves the model’s detection capability in complex change areas. Specifically, we introduce the edge-feature enhancement (EFE) block and the dual-flow state-space (DFSS) block, which enhance the details of change edges and local features while maintaining the model’s global feature extraction capability. We propose a dynamic loss function to address the issue of sample imbalance, giving more attention to difficult samples during training. Extensive experiments on three change detection datasets demonstrate that our proposed DC-Mamba outperforms existing state-of-the-art methods overall and exhibits significant performance improvements in detecting difficult cases.

The degradation of image resolution reduces the detection performance in aerial imagery because it generates a large number of small objects, and accurately detecting these small objects remains a challenge. Existing methods mostly use a Super-Resolution (SR) model to first obtain the SR image of the Low-Resolution degraded image ( $I^{LR}$ ) and then use this image as the input of the object detection (OD) network to solve this problem. However, this architecture that involves executing a complex SR network before the detector is time-consuming and makes it hard to achieve real-time model inference. To address this challenge, we propose a simple and effective rotated small object detection method, named End-to-end Super-Resolution enhanced real-Time rotated object Detector (ESRTMDet). Firstly, we design a lightweight Embedded feature map Super-Resolution Module (ESRM) embedded in the detection model to enhance and amplify the backbone output features, making the detection heads detect small objects more easily. Furthermore, we train a parallel SR network branch (PSRB) simultaneously that uses the backbone feature to restore a High-Resolution image ( $I^{HR}$ ). Through our proposed feature alignment loss ( $\mathcal {L}_{AL}$ ) and feature affinity layer (FAL), our PSRB effectively guides the feature map enhancement of ESRM. Finally, through end-to-end joint optimization of the detector and PSRB, the detection performance on $I^{LR}$ is significantly improved. Extensive experiments over DOTA and UCAS-AOD demonstrate that our method can achieve state-of-the-art (SOTA) results. Additionally, we discard our PSRB and use $I^{LR}$ as the input during inference, reducing the inference time-consuming of our model. Therefore, our ESRTMDet-X not only achieves 77.11% mean of Average Precision (mAP) on the degraded DOTA dataset, but also achieves an amazing inference speed of 337 FPS, thus obtaining the best speed-accuracy trade-off. The code and models will be released at https://github.com/liufeinuaa/aisodet.git .

In the context of area coverage tasks in three-dimensional space, unmanned aerial vehicle (UAV) clusters face challenges such as uneven task assignment, low task efficiency, and high energy consumption. This paper proposes an efficient mission planning strategy for UAV clusters in area coverage tasks. First, the area coverage search task is analyzed, and the coverage scheme of the task area is determined. Based on this, the cluster task area is divided into subareas. Then, for the UAV cluster task allocation problem, a step-by-step solution is proposed. Afterward, an improved fuzzy C-clustering algorithm is used to determine the UAV task area. Furthermore, an optimized particle swarm hybrid ant colony (PSOHAC) algorithm is proposed to plan the UAV cluster task path. Finally, the feasibility and superiority of the proposed scheme and improved algorithm are verified by simulation experiments. The simulation results show that the proposed method achieves full coverage of the task area and efficiently completes the task allocation of the UAV cluster. Compared with related comparison algorithms, the method proposed in this paper can achieve a maximum improvement of 21.9% in balanced energy consumption efficiency for UAV cluster task search planning, and the energy efficiency of the UAV cluster can be improved by up to 7.9%.

Unmanned aerial vehicle (UAV) swarm intelligence technology has shown unique advantages in agricultural and forestry disaster detection, early warning, and prevention with its efficient and precise cooperative operation capability. In this paper, a systematic application strategy of UAV swarms in forest fire detection is proposed, including fire point detection, fire assessment, and control measures, based on the fusion of particle swarm optimization (PSO) and the artificial bee colony (ABC) algorithm. The UAV swarm application strategy provides optimized paths to quickly locate multiple mountain forest fire points in 3D forest modeling environments and control measures based on the analysis of the fire situation. This work lays a research foundation for studying the precise application of UAV swarm technology in real-world forest fire detection and prevention.

This article presents an adaptive maximum power point tracking technique for broadband vibration energy harvesting. The presented technique employs a discontinuous conduction mode buck–boost converter to emulate a matched resistor for a vibration energy harvester. Instead of traversal search, the optimal duty cycle can be tuned in one step based on direct calculation of source impedance, which is realized by active pulse width modulation perturbation strategy; based on it, the circuit can work well in impedance match adaptively without any prior knowledge of a harvester. The prototype circuit is implemented by an ultra-low-power consumption MSP430 microcontroller with a stable external power supply. It produces 1.32 mW (0.4 g and 88.2 Hz acceleration) from a piezoelectric vibration energy harvester and 1.16 mW (0.12 g and 19.3 Hz acceleration) from an electromagnetic vibration energy harvester. According to the definition of power–bandwidth product, the experimental results achieve 75.2% and 39.9% of the theoretical optimal capacity of the piezoelectric vibration energy harvester and electromagnetic vibration energy harvester, respectively. The detailed experimental data indicate that the proposed approach achieves a large improvement than employing a fixed load resistance in a wide frequency band. Furthermore, the possibility of self-powered is confirmed based on a brief estimation of power losses on the proposed circuit.