In terms of highway crack detection, the combination of UAV and deep learning network has become a powerful detection means. However, in the actual detection, in order to take into account the detection efficiency, it is necessary to ensure that the detection area is large enough, which makes the crack occupy few pixels in the image, and the image background is complex. Therefore, in this paper, DJI Mavic3 is used to establish the image data set of highway pavement cracks under complex background. And, the YOLOV5 deep learning model is improved by adding swin transformer structure and BIFPN feature pyramid. The improved YOLOV5 model achieved real-time pixel-level detection with detection accuracy of 90% and detection speed of 43.5 FPS. In terms of crack detection ability, the accuracy of the improved YOLOV5 reaches 4 pixels, and cracks of 1.2 mm can be detected in the experiment. Compared with the YOLOV7 model, the detection accuracy of the improved YOLOV5 model is increased by 15.4%. Compared with the YOLOV6 model, the calculated parameters of the improved YOLOV5 model are reduced by 59.25%. The proposed model is superior to other advanced models in crack detection.

Cracks provide the earliest and most immediate visual response to structural deterioration of asphalt pavements. Most of the current methods for crack detection are based on visible light sensors and convolutional neural networks. However, such an approach obviously limits the detection to daytime and good lighting conditions. Therefore, this paper proposes a crack detection technique cross-modal feature alignment of YOLOV5 based on visible and infrared images. The infrared spectrum characteristics of silicate concrete can be an important supplement. The adaptive illumination-aware weight generation module is introduced to compute illumination probability to guide the training of the fusion network. In order to alleviate the problem of weak alignment of the multi-scale feature map, the FA-BIFPN feature pyramid module is proposed. The parallel structure of a dual backbone network takes 40% less time to train than a single backbone network. As determined through validation on FLIR, LLVIP, and VEDAI bimodal datasets, the fused images have more stable performance compared to the visible images. In addition, the detector proposed in this paper surpasses the current advanced YOLOV5 unimodal detector and CFT cross-modal fusion module. In the publicly available bimodal road crack dataset, our method is able to detect cracks of 5 pixels with 98.3% accuracy under weak illumination.

Rapid and accurate identification of the initial stage of surface oil spills is crucial for reducing economic losses and environmental pollution. However, because the initial stage of a surface oil spill covers a small area and often integrates with soil and lakes, achieving rapid and accurate identification using common methods, such as satellite remote sensing, is challenging. To address this issue, UAV-based surface oil spill rapid identification technology is used. This paper proposes a Res-SUnet network model based on small samples from UAV multispectral images, utilizing the reflectance spectral feature information of oil under sunlight for fast and accurate identification and segmentation of small surface oil spill targets. By preprocessing 54 sets of multispectral images (54 × 6 spectral channel images) collected from the surface oil spill area of the Daqing oilfield and dividing them into training, test, and validation sets in a ratio of 3:2:2, the results show an improvement of 1.17% and 1.39% over traditional U-net and improved S-unet models, respectively. This method is characterized by its lightweight, rapid, and accurate identification, making it especially suitable for the rapid and precise identification of UAV surface oil spills at the initial stage, providing a valuable tool for enterprises to reduce economic losses and environmental pollution.

In this paper, a Light Detection and Ranging (LiDAR) system based on a hybrid modulation technique is proposed, which integrates ranging, velocimetry, and communication functions. First, the system performs pulse width modulation (PWM) on the baseband signal. This PWM-modulated signal controls the on-off keying (OOK) modulation of the high-frequency sinusoidal signal. Then, the OOK-modulated signal is used to perform pulse-based intensity modulation on a continuous-wave laser, which is then transmitted toward the target. Thus, the system incorporates a hybrid modulation scheme combining PWM, OOK, and intensity modulation. Experimental results demonstrate that the time interval of the pulsed signal enables coarse positioning of distant targets, while phase difference measurements of the high-frequency sinusoid within each pulse ensure ranging precision better than 9 mm. The Doppler frequency shift induced by target motion is utilized to measure dynamic target velocity, achieving a precision better than 7.98 mm/s. Accurate demodulation of the baseband signal is achieved through pulse-width extraction from the echo signal. Furthermore, multi-dimensional point cloud images of various targets are successfully realized. This work provides a viable technical approach for developing multi-functional-integrated LiDAR systems.

Three-dimensional sensing technologies can rapidly acquire 3D point cloud data for object perception and scene understanding. However, point cloud-based object classification is still constrained by limited labeled data and high computational complexity. At present, feature extractors pretrained on large-scale 2D datasets have achieved strong performance in zero-shot 2D classification. Therefore, projecting 3D point clouds into 2D images and leveraging well-established 2D pretrained models for zero-shot point cloud classification has become an effective strategy. In this strategy, generating high-fidelity 2D projections is a critical challenge. To address this challenge, this paper proposes a zero-shot 3D object classification framework based on a multi-scale local geometric feature extraction module and depth-aware multi-view projection. Specifically, point clouds are first modeled as graph structures. Multi-scale radii are used to adjust the receptive field during feature extraction, thereby capturing both fine-grained and large-scale local geometric features. Multi-view 2D images are then generated through depth-wise feature accumulation. These images are fed into a frozen CLIP model for zero-shot classification. The proposed method preserves the structural characteristics of point clouds and reduces the domain gap between point clouds and 2D images. Experiments are conducted on the ModelNet10, ModelNet40, and ScanObjectNN datasets. The results show that the proposed method outperforms current mainstream zero-shot 3D point cloud classification methods. These results suggest that the proposed framework offers an effective solution for point cloud object classification in complex scenarios.