In the intelligent traffic system, real-time and accurate detections of vehicles in images and video data are very important and challenging work. Especially in situations with complex scenes, different models, and high density, it is difficult to accurately locate and classify these vehicles during traffic flows. Therefore, we propose a single-stage deep neural network YOLOv3-DL, which is based on the Tensorflow framework to improve this problem. The network structure is optimized by introducing the idea of spatial pyramid pooling, then the loss function is redefined, and a weight regularization method is introduced, for that, the real-time detections and statistics of traffic flows can be implemented effectively. The optimization algorithm we use is the DL-CAR data set for end-to-end network training and experiments with data sets under different scenarios and weathers. The analyses of experimental data show that the optimized algorithm can improve the vehicles’ detection accuracy on the test set by 3.86%. Experiments on test sets in different environments have improved the detection accuracy rate by 4.53%, indicating that the algorithm has high robustness. At the same time, the detection accuracy and speed of the investigated algorithm are higher than other algorithms, indicating that the algorithm has higher detection performance.

Due to the abundant natural resources of the underwater world, autonomous exploration using underwater robots has become an effective technological tool in recent years. Real-time object detection is critical when employing robots for independent underwater exploration. However, when a robot detects underwater, its computing power is usually limited, which makes it challenging to detect objects effectively. To solve this problem, this study presents a novel algorithm for underwater object detection based on YOLOv4-tiny to achieve better performance with less computational cost. First, a symmetrical bottleneck-type structure is introduced into the YOLOv4-tiny’s backbone network based on dilated convolution and 1 × 1 convolution. It captures contextual information in feature maps with reasonable computational cost and improves the mAP score by 8.74% compared to YOLOv4-tiny. Second, inspired by the convolutional block attention module, a symmetric FPN-Attention module is constructed by integrating the channel-attention module and the spatial-attention module. Features extracted by the backbone network can be fused more efficiently by the symmetric FPN-Attention module, achieving a performance improvement of 8.75% as measured by mAP score compared to YOLOv4-tiny. Finally, this work proposed the YOLO-UOD for underwater object detection through the fusion of the YOLOv4-tiny structure, symmetric FPN-Attention module, symmetric bottleneck-type dilated convolutional layers, and label smoothing training strategy. It can efficiently detect underwater objects in an embedded system environment with limited computing power. Experiments show that the proposed YOLO-UOD outperforms the baseline model on the Brackish underwater dataset, with a detection mAP of 87.88%, 10.5% higher than that of YOLOv4-tiny’s 77.38%, and the detection result exceeds YOLOv5s’s 83.05% and YOLOv5m’s 84.34%. YOLO-UOD is deployed on the embedded system Jetson Nano 2 GB with a detection speed of 9.24 FPS, which shows that it can detect effectively in scenarios with limited computing power.

We theoretically proposed and numerically analyzed a polarization-independent, wide-angle, and ultra-broadband absorber based on a multi-layer metasurface. The numerical simulation results showed that the average absorption rates were more than 97.2% covering the broad wavelength of 400~6000 nm (from visible light to mid-infrared light) and an absorption peak was 99.99%, whatever the polarization angle was changed from 0° to 90°. Also, as the incidence angle was swept from 0° to 55°, the absorption performance had no apparent change over the wavelength ranges of 400 to 6000 nm. We proved that the proposed metasurface structure was obviously advantageous to achieve impedance matching between the absorber and the free space as compared with conventionally continuous planar-film structures. The broadband and high absorption resulted from the strong localized surface plasmon resonance and superposition of resonant frequencies. As expectable the proposed absorber structure will hold great potential in plasmonic light harvesting, photodetector applications, thermal emitters and infrared cloaking.

We propose a high-performance algorithm while using a promoted and modified form of the You Only Look Once (YOLO) model, which is based on the TensorFlow framework, to enhance the real-time monitoring of traffic-flow problems by an intelligent transportation system. Real-time detection and traffic-flow statistics were realized by adjusting the network structure, optimizing the loss function, and introducing weight regularization. This model, which we call YOLO-UA, was initialized based on the weight of a YOLO model pre-trained while using the VOC2007 data set. The UA-CAR data set with complex weather conditions was used for training, and better model parameters were selected through tests and subsequent adjustments. The experimental results showed that, for different weather scenarios, the accuracy of the YOLO-UA was ~22% greater than that of the YOLO model before optimization, and the recall rate increased by about 21%. On both cloudy and sunny days, the accuracy, precision, and recall rate of the YOLO-UA model were more than 94% above the floating rate, which suggested that the precision and recall rate achieved a good balance. When used for video testing, the YOLO-UA model yielded traffic statistics with an accuracy of up to 100%; the time to count the vehicles in each frame was less than 30 ms and it was highly robust in response to changes in scenario and weather.

Aiming at a series of problems such as detection accuracy, calculation blocking, display delay, and so on in the ship detection of surveillance video, an improved YOLOv5 algorithm is proposed in this paper. First, to improve the detection performance, it is proposed to optimize the anchor box algorithm in the YOLOv5 network according to the ship target characteristics. Then, the t‐SNE algorithm is used to reduce and visualize the data set label information and perform weighted analysis on the processed features for low‐dimensional data. The mapped kernel k‐means clustering algorithm adaptively selects a more appropriate anchor box and considers the detection performance of large and small ship targets. Secondly, to improve the problem of computational blocking and delay, the BN scaling factor γ is used to compress the YOLOv5 network, so that the model can be reduced without reducing the detection performance. The optimized YOLOv5 framework is trained on the self‐integrated data set. The accuracy of the algorithm is increased by 2.34%, and the ship detection speed reaches 98 fps and 20 fps in the server environment and the low computing power version (Jetson nano), respectively.

Underwater object detection with Synthetic Aperture Sonar (SAS) images faces many problems, including low contrast, blurred edges, high-frequency noise, and missed small objects. To improve these problems, this paper proposes a high-accuracy underwater object detection algorithm for SAS images, named the HAUOD algorithm. First, considering SAS image characteristics, a sonar preprocessing module is designed to enhance the signal-to-noise ratio of object features. This module incorporates three-stage processing for image quality optimization, and the three stages include collaborative adaptive Contrast Limited Adaptive Histogram Equalization (CLAHE) enhancement, non-local mean denoising, and frequency-domain band-pass filtering. Subsequently, a novel C2fD module is introduced to replace the original C2f module to strengthen perception capabilities for low-contrast objects and edge-blurred regions. The proposed C2fD module integrates spatial differential feature extraction, dynamic feature fusion, and Enhanced Efficient Channel Attention (Enhanced ECA). Furthermore, an underwater multi-scale contextual attention mechanism, named UWA, is introduced to enhance the model’s discriminative ability for multi-scale objects and complex backgrounds. The proposed UWA module combines noise suppression, hierarchical dilated convolution groups, and dual-dimensional attention collaboration. Experiments on the Sonar Common object Detection dataset (SCTD) demonstrate that the proposed HAUOD algorithm achieves superior performance in small object detection accuracy and multi-scenario robustness, attaining a detection accuracy of $95.1\%$, which is $8.3\%$ higher than the baseline model (YOLOv8n). Compared with YOLOv8s, the proposed HAUOD algorithm can achieve $6.2\%$ higher accuracy with only $50.4\%$ model size, and reduce the computational complexity by half. Moreover, the HAUOD method exhibits significant advantages in balancing computational efficiency and accuracy compared to mainstream detection models.