Unauthorized unmanned aerial vehicles (UAVs) pose threats to public safety and individual privacy. Traditional object-detection approaches often fall short during their application in anti-UAV technologies. To address this issue, we propose the YOLOv7-GS model, which is designed specifically for the identification of small UAVs in complex and low-altitude environments. This research primarily aims to improve the model’s detection capabilities for small UAVs in complex backgrounds. Enhancements were applied to the YOLOv7-tiny model, including adjustments to the sizes of prior boxes, incorporation of the InceptionNeXt module at the end of the neck section, and introduction of the SPPFCSPC-SR and Get-and-Send modules. These modifications aid in the preservation of details about small UAVs and heighten the model’s focus on them. The YOLOv7-GS model achieves commendable results on the DUT Anti-UAV and the Amateur Unmanned Air Vehicle Detection datasets and performs to be competitive against other mainstream algorithms.
1 March 2021 in Computers and Electrical Engineering
Vehicle logo detection (VLD) is a special and significant topic in object detection for vehicle identification system applications. Nevertheless, the range of the research and analysis for VLD are seriously narrow in the real complex scenes, although it's a critical role in the object detection of small sizes. In this paper, we make further analysis work toward vehicle logo recognition and detection in real-world situations. To begin with, we propose a new multi-class VLD dataset, called VLD-45 (Vehicle Logo Dataset), which contains 45000 images and 50359 objects from 45 categories respectively. Our new dataset provides several research challenges involve in small sizes object, shape deformation, low contrast and so on. Meanwhile, we use 6 existing classifiers and 6 detectors to evaluate our dataset and show the baseline performance. According to the result, our dataset has very significant research value for the task of small-scale object detection. The dataset source: https://github.com/YangShuoys/VLD-45-B-DATASET-Detection
A low-noise Low Dropout Regulator (LDO) is designed in a Semiconductor Manufacturing International Corporation (SMIC) 0.18 μm process, aiming at supply of a clean and constant clamping voltage in the operation of Correlated Double Sampling (CDS) for elimination of switching and reset noise in CMOS Pixel Sensors (CPS) applied to high energy physics experiments. In order to decrease noise of the LDO, a noise model of the LDO consisting of blocks, such as a pass transistor, a resistor network, and an error amplifier, is constructed and noise contributions made by these blocks are analyzed in detail. According to results of the noise analysis, the error amplifier is identified as the major noise source. For the purpose of reduction in noise, especially 1/f noise, an error amplifier exploiting a chopper stabilization technique is proposed. Simulation results demonstrate the effectiveness of the proposed method. The Power Spectral Density (PSD) of the LDO’s output noise is only 60 nV/√Hz at 10 Hz and total integrated noise within the bandwidth is 40 μV.