Search

Satellite remote sensing technology significantly contributes to intelligent transportation by optimizing traffic planning via global perspectives and rich data, enhancing traffic efficiency and reducing environmental impact. However, current target detection models frequently exhibit low accuracy in vehicle detection tasks due to complex background interference in satellite imageries and a need for critical semantic information. To improve vehicle target detection accuracy, this study introduces SatDetX-YOLO, a vehicle detection model for satellite remote sensing images based on YOLOv8. The model involves reconstructing the backbone network with FasterNet for enhanced feature extraction, a redesigned decoupled head for improved computational efficiency and complex data processing, and incorporating the Deformable Attention Module (DAM) to increase sensitivity to small targets and feature correlation capture. Employing the Maximum Probabilistic Distance IoU (MPDIoU) loss function enhances adaptability and generalization to diverse vehicle targets. Experimental results demonstrate that under comparable FPS, SatDetX-YOLO’s Precision (P), Recall (R), and Mean Average Precision (mAP) improved by 3.5%, 3.3%, and 3.2%, respectively. Despite a minor reduction in FPS, the model significantly enhances detection accuracy, striking a balance between accuracy and speed.

To improve the accuracy of short term traffic flow prediction and to solve the problems of nonlinearity of short term traffic flow, more noise in the data, and more difficult to determine the parametes of long short term memory networks, a combined traffic flow prediction model based on variational modal decomposition (VMD) and improved dung beetle optimization-long short term memory network (IDBO-LSTM) is proposed. First, to extract various modal components, the historical traffic flow data are smoothed using variational modal decomposition (VMD). Second, the LSTM prediction model is built for each individual subsequence, and the parameters of the LSTM are optimized using the IDBO algorithm which combines Singer chaos mapping, variable spiral search strategy, and Levy flight strategy. Finally, to acquire the final prediction results, the predicted values of various subsequences are added up and reassembled. Experiments were conducted using data collected from eight sensors along an interstate highway in California, and taking the straight road morning peak (S-M) data as an example, compared with LSTM and VMD-LSTM, the MAE of VMD-IDBO-LSTM is reduced by 26.69 and 7.5108, MAPE is reduced by 8.08059% and 2.27569%, and RMSE is reduced by 33.6912 and 8.7657. According to the findings, the VMD-IDBO-LSTM model that was proposed is capable of significantly improving the accuracy of short-term traffic flow prediction while also effectively addressing nonlinearity, data noise, and the difficulty of identifying the LSTM parameters.

In this paper, based on the gray value change of reflected light image of porous silicon (PSi) Bragg mirror, a fast and simple biological detection method is proposed. In this method, CdSe/ZnS quantum dots (QDs) are used as markers for refractive index amplification, and digital image method is used for detection. The detection light has the same wavelength as the lowest reflectivity of the edge of the Bragg mirror, and the reflected light radiated on the surface of the Bragg mirror is received by the detector. The theoretical simulation results show that the intensity of the reflected light increases with the increase of the refractive index caused by the biological reaction. According to the experimental results, the average gray value variation increases with the increase of the target DNA concentration and becomes a linear relationship in a certain range. Based on this method, the DNA detection limit is 20.74 pM. The method is low-cost, has a short detection time and can be used in the detection of biosensor microarray.

To further improve the sensitivity of porous silicon-assembled microcavity biosensors, the detection of porous silicon assembled microcavity by angle spectrum method is also researched. This contribution uses CdSe/ZnS quantum dot-labelled probe DNA to amplify the refractive index and detect it by the angle spectrum method. The first layer is a microcavity layer, and the next is porous silicon with a Bragg structure. After functionalization, different concentrations of target DNA were coupled to construct quantum dot-labelled probe DNA to bind specifically to the target DNA. With the Bragg device based on quartz glass forming an assembled microcavity structure, using a He-Ne laser as the detection light and collimation beam, the angle spectrum method is used to detect different concentrations of target DNA before and after biological reaction with quantum dot-labelled probe DNA and reflect the angle of minimum light intensity. The experimental results show that with increasing target DNA concentration, probe DNA concentration and angle, the detection limit is 13.25 pM. The angle-spectrum method has been successfully used to detect the assembled porous silicon microcavity. The angle-spectrum method has the advantages of spectrometer free and low cost.

Plasmonic filters are excellent candidates for spectral filters in the near infrared spectrum. Such filters require only a single nanoscale thickness perforated metal film that can be tailored to tune the location of the transmission maximum. Here, we demonstrate using computational methods a double coaxial aperture array (DAA) in a hexagonal geometry that can be tuned to produce plasmon resonances accompanied by strong transmission in the near-infrared spectrum and at telecommunication wavelengths with a peak wavelength insensitive to angle of incidence. The DAA consists of two concentric annular apertures and radial distance between the two apertures is varied to tune the resonant wavelength. The presented geometry finds potential applications in modulators for telecommunication, spectroscopy, solar cells, high-resolution CMOS image sensors, chemical sensors, and biosensors.

We present design of plasmonic modulators using vanadium dioxide (VO2) as modulating material realized on silicon-on-insulator (SOI) wafer with only 200 nm × 140 nm modulating section within 1 μ m × 3 μm device footprint. By utilising the large refractive index contrast between the metallic and semiconductor phases of VO2, the modulator can achieve a broad working wavelength range from 1100 to 1800 nm around C-band, with a high modulation depth of 21.5 dB/μm. We also analyse effects of using seed layer of different dielectric materials for growing VO2 on modulation index by exploring the mixed combination of VO2 and different dielectric materials. Our device geometries can have potential applications in the development of next-generation miniaturised high-frequency optical modulators in silicon photonics for optical communications.

Automatically predicting age group and gender from face images acquired in unconstrained conditions is an important and challenging task in many real-world applications. Nevertheless, the conventional methods with manually-designed features on in-the-wild benchmarks are unsatisfactory because of incompetency to tackle large variations in unconstrained images. This difficulty is alleviated to some degree through convolutional neural networks (CNN) for its powerful feature representation. In this paper, we propose a new CNN-based method for age group and gender estimation leveraging residual networks of residual networks (RoR), which exhibits better optimization ability for age group and gender classification than other CNN architectures. Moreover, two modest mechanisms based on observation of the characteristics of age group are presented to further improve the performance of age estimation. In order to further improve the performance and alleviate over-fitting problem, RoR model is pre-trained on ImageNet first, and then it is fune-tuned on the IMDB-WIKI-101 data set for further learning the features of face images, finally, it is used to fine-tune on Adience data set. Our experiments illustrate the effectiveness of RoR method for age and gender estimation in the wild, where it achieves better performance than other CNN methods. Finally, the RoR-152+IMDB-WIKI-101 with two mechanisms achieves new state-of-the-art results on Adience benchmark.