Detecting small objects in remote sensing images is meaningful challenging, especially when deploying existing object detection models on edge terminal devices with limited hardware resources. In this study, we present an efficient remote sensing object detection model named SCNet, based on the ultra-lightweight YOLOv5n. To address the significant feature loss issue in small objects within the model’s neck, we introduce the Selective Feature Enhancement Block (SFEB). The SFEB selectively processes a portion of feature maps that contribute more to semantic information extraction while retaining another portion, enabling us to extract rich semantic information while preserving crucial details information necessary for small object detection. Furthermore, we incorporate the Contextual Transformer Block (CTB) at the neck and Backbone junction, which enhances the model’s ability to understand relationships and boundaries between object s and backgrounds by exploring contextual information in shallow-level feature maps. This improves the model’s capability to detect challenging small and medium objects. Experimental results on the NWPU VHR-10 and DIOR datasets demonstrate the model’s performance, achieving mean Average Precisions (mAP) of 96.6% and 72.6% at IOU=0.5. The model operates at 487 Frames Per Second with a batch size of 32 (FPS32), requiring only 4.6 Giga Floating-point Operations Per second (GFLOPs) and 1.8 million params.
The current challenges in Synthetic Aperture Radar (SAR) ship detection tasks revolve around handling significant variations in target sizes and managing high computational expenses, which hinder practical deployment on satellite or mobile airborne platforms. In response to these challenges, this research presents YOLOv7-LDS, a lightweight yet highly accurate SAR ship detection model built upon the YOLOv7 framework. In the core of YOLOv7-LDS’s architecture, we introduce a streamlined feature extraction network that strikes a delicate balance between detection precision and computational efficiency. This network is founded on Shufflenetv2 and incorporates Squeeze-and-Excitation (SE) attention mechanisms as its key elements. Additionally, in the Neck section, we introduce the Weighted Efficient Aggregation Network (DCW-ELAN), a fundamental feature extraction module that leverages Coordinate Attention (CA) and Depthwise Convolution (DWConv). This module efficiently aggregates features while preserving the ability to identify small-scale variations, ensuring top-quality feature extraction. Furthermore, we introduce a lightweight Spatial Pyramid Dilated Convolution Cross-Stage Partial Channel (LSPHDCCSPC) module. LSPHDCCSPC is a condensed version of the Spatial Pyramid Pooling Cross-Stage Partial Channel (SPPCSPC) module, incorporating Dilated Convolution (DConv) as a central component for extracting multi-scale information. The experimental results show that YOLOv7-LDS achieves a remarkable Mean Average Precision (mAP) of 99.1% and 95.8% on the SAR Ship Detection Dataset (SSDD) and the NWPU VHR-10 dataset with a parameter count (Params) of 3.4 million, a Giga Floating Point Operations Per Second (GFLOPs) of 6.1 and an Inference Time (IT) of 4.8 milliseconds. YOLOv7-LDS effectively strikes a fine balance between computational cost and detection performance, surpassing many of the current state-of-the-art object detection models. As a result, it offers a more resilient solution for maritime ship monitoring.
In this paper, two versions of capacitive accelerometers based on low-temperature co-fired ceramic (LTCC) technology are developed, different with respect to the detection technique, as well as the mechanical structure. Fabrication of the key structure, a heavy proof mass with thin beams embedded in a large cavity, which is extremely difficult for the conventional LTCC process, is successfully completed by the optimized process. The LC resonant accelerometer, using coupling resonance frequency sensing which is first applied to LTCC accelerometer and may facilitate application in harsh environments, demonstrates a sensitivity of 375 KHz/g over the full scale range 1 g, with nonlinearity less than 6%, and the telemetry distance is 5 mm. The differential capacitive accelerometer adopting differential capacitive sensing presents a larger full scale range 10 g and lower nonlinearity less than 1%, and the sensitivity is 30.27 mV/g.
The hydrodynamic and thermal characteristics of microchannel networks are investigated by finite element analysis with commercial software Fluent. The simulation model is based on fabricated thick film LTCC substrate with 3D cooling microchannels. A comparison of the cooling performance among fractal-shaped microchannel, parallel microchannel, serpentine microchannel, spiral microchannel is also conducted numerically based on the same heat flux and the same mass flow rate. It is found that fractal-shaped microchannel facilitates the lowest fluid pressure drop and the most uniform temperature distribution over the substrate, and that the spiral microchannel network enables the smallest temperature rise.
Mobile devices support more and more real-time multimedia contents such as live video, high-definition television, virtual reality and so on. Real-time multimedia services over mobile networks face several challenges, including the efficient management of radio resources, high data throughput and the latency induced by transmission delay. In order to address network errors on Long Time Evolution (LTE) multimedia broadcast services, forward error correction and unicast recovery techniques are proposed in standard at the application level. In this paper, a parallel coding scheme with Turbo Product Code (TPC) is proposed to fit the antenna array of Multiple-Input Multiple-Output Filter Bank Multi-Carrier (MIMO-FBMC) system for transmission latency reduction. In this scheme, multimedia content information data are firstly reformed into two dimensional blocks with (k 1 × k 2 ) bits in every block. And then each block is encoded into (n 1 × n 2 ) codeword block using TPC to be transmitted parallel through the massive antenna array of transmitter in MIMO-FBMC system. In the receiver, the multimedia content information is re-formed by concurrent soft decision iterative decoding algorithm of TPC. This parallel TPC coding scheme achieves high throughput, low transmission latency and high reliability, which is suitable for the multimedia communication. Simulation results confirmed the superiority of the proposed parallel TPC coding scheme.
The large-scale application of Bi2Te3-based film thermoelectric devices is facing a bottleneck, owing to the poor stability of n-type materials. Here, (015) plane-oriented Bi2Se0.5Te2.5 films were fabricated using a magnetron co-sputtering method, and enhanced thermoelectric properties with a wide temperature range stability were achieved through a facile post-annealing process.