Excellent Real-time Performance Research Articles

Designing signal processing for robotic olfaction based on electroantennogram

ABSTRACT In this study, we experimentally evaluated a signal-processing method for the stable use of an insect antenna as an odor sensor for a robot because of its excellent sensitivity and selectivity to odors. Changes in potential in response to an odor stimulus can be measured when the electrodes are connected to both ends of an insect antenna. This is called an electroantennogram (EAG), and is a type of physiological response. Hence, we must extract only the EAG waveform using appropriate signal processing because it has a low signal-to-noise ratio. Accordingly, we applied signal processing based on an exponentially weighted moving average (EWMA), which demonstrates excellent real-time performance, to an EAG to eliminate high-frequency noise. Moreover, we experimentally investigated the sampling rate to properly measure the EAG. From the results, the EAG-driven robot with the designed signal processing demonstrated a search performance of more than 70 % , even in odor-source localization experiments with different types of moths and environments.

Fine-Grained Feature Perception for Unmanned Aerial Vehicle Target Detection Algorithm

Unmanned aerial vehicle (UAV) aerial images often present challenges such as small target sizes, high target density, varied shooting angles, and dynamic poses. Existing target detection algorithms exhibit a noticeable performance decline when confronted with UAV aerial images compared to general scenes. This paper proposes an outstanding small target detection algorithm for UAVs, named Fine-Grained Feature Perception YOLOv8s-P2 (FGFP-YOLOv8s-P2), based on YOLOv8s-P2 architecture. We specialize in improving inspection accuracy while meeting real-time inspection requirements. First, we enhance the targets’ pixel information by utilizing slice-assisted training and inference techniques, thereby reducing missed detections. Then, we propose a feature extraction module with deformable convolutions. Decoupling the learning process of offset and modulation scalar enables better adaptation to variations in the size and shape of diverse targets. In addition, we introduce a large kernel spatial pyramid pooling module. By cascading convolutions, we leverage the advantages of large kernels to flexibly adjust the model’s attention to various regions of high-level feature maps, better adapting to complex visual scenes and circumventing the cost drawbacks associated with large kernels. To match the excellent real-time detection performance of the baseline model, we propose an improved Random FasterNet Block. This block introduces randomness during convolution and captures spatial features of non-linear transformation channels, enriching feature representations and enhancing model efficiency. Extensive experiments and comprehensive evaluations on the VisDrone2019 and DOTA-v1.0 datasets demonstrate the effectiveness of FGFP-YOLOv8s-P2. This achievement provides robust technical support for efficient small target detection by UAVs in complex scenarios.

Automated Upper Tract Urothelial Carcinoma Tumor Segmentation During Ureteroscopy Using Computer Vision Techniques.

Introduction: Endoscopic tumor ablation of upper tract urothelial carcinoma (UTUC) allows for tumor control with the benefit of renal preservation but is impacted by intraoperative visibility. We sought to develop a computer vision model for real-time, automated segmentation of UTUC tumors to augment visualization during treatment. Materials and Methods: We collected 20 videos of endoscopic treatment of UTUC from two institutions. Frames from each video (N = 3387) were extracted and manually annotated to identify tumors and areas of ablated tumor. Three established computer vision models (U-Net, U-Net++, and UNext) were trained using these annotated frames and compared. Eighty percent of the data was used to train the models while 10% was used for both validation and testing. We evaluated the highest performing model for tumor and ablated tissue segmentation using a pixel-based analysis. The model and a video overlay depicting tumor segmentation were further evaluated intraoperatively. Results: All 20 videos (mean 36 ± 58 seconds) demonstrated tumor identification and 12 depicted areas of ablated tumor. The U-Net model demonstrated the best performance for segmentation of both tumors (area under the receiver operating curve [AUC-ROC] of 0.96) and areas of ablated tumor (AUC-ROC of 0.90). In addition, we implemented a working system to process real-time video feeds and overlay model predictions intraoperatively. The model was able to annotate new videos at 15 frames per second. Conclusions: Computer vision models demonstrate excellent real-time performance for automated upper tract urothelial tumor segmentation during ureteroscopy.

Simple DFS and AOA simultaneous measurement scheme without directional ambiguity with co-frequency self-interference signal cancellation

A photonic method based on a dual-polarization dual-parallel Mach–Zehnder modulator (DPol-DPMZM) for the simultaneous measurement of the Doppler frequency shift (DFS) and angle of arrival (AOA) of microwave signals is proposed and demonstrated by simulation. The upper arm of each sub-DPMZM is driven by the echo and self-interference signals from the antenna, while the lower arm is driven by the reference signal 1 and reference signal 2. The phase and amplitude of the reference signal 1 are adjusted to match the interference signals for achieving the self-interference cancellation (SIC). At the central office (CO), the DFS and AOA can be acquired in real time without directional ambiguity by processing the two downconverted low-frequency tones in the photocurrent. The simulation results show that the presence of the SI signal will seriously interfere with the observation of the SOI frequency and waveform, and the self-interference cancellation depth of about 42 dB can be obtained after the SIC. The measurement errors of the DFS without direction ambiguity are within 0.2 Hz. After the Hilbert transformation of the intermediate frequency (IF) signal, the AOA can be measured from −87.31∘ to +87.31∘ with errors less than 3.9°. The system has a large bandwidth, excellent real-time performance, and better invisibility, and is expected to be used in modern electronic warfare systems.

An actively stabilized, miniaturized epi-fluorescence widefield microscope for real-time observation in vivo.

Recent developments in real-time, in vivo micro-imaging have allowed for the visualization of tissue pathological changes, facilitating rapid diagnosis. However, miniaturization, magnification, the field of view, and in vivo image stabilization remain challenging factors to reconcile. A key issue for this technology is ensuring it is user friendly for surgeons, enabling them to use the device manually and obtain instantaneous information necessary for surgical decision-making. This descriptive study introduces a handheld, actively stabilized, miniaturized epi-fluorescence widefield microscope (MEW-M) for real-time observation in vivo with high resolution. The methodology of MEW-M system includes high resolution microscopy miniaturization technology, thousandfold shaking suppression (actively stabilized), ultra-photosensitivity, and tailored image signal processing cell image capture and processing technology, which support for the excellent real-time imaging performance of MEW-M system in brain, mammary, liver, lung, and kidney tissue imaging of rats in vivo. With a single-objective and high-frame-rate imaging, the MEW-M system facilitates roving image acquisition, enabling contiguous analysis of large tissue areas. RESEARCH HIGHLIGHTS: A handheld, actively stabilized MEW-M system was introduced. Excellent real-time, in vivo imaging with high resolution and active stabilization in brain, mammary, liver, lung, and kidney tissue of rats.

Fine-grained grid computing model for Wi-Fi indoor localization in complex environments

The fingerprinting-based approach using the wireless local area network (WLAN) is widely used for indoor localization. However, the construction of the fingerprint database is quite time-consuming. Especially when the position of the access point (AP) or wall changes, updating the fingerprint database in real-time is difficult. An appropriate indoor localization approach, which has a low implementation cost, excellent real-time performance, and high localization accuracy and fully considers complex indoor environment factors, is preferred in location-based services (LBSs) applications. In this paper, we proposed a fine-grained grid computing (FGGC) model to achieve decimeter-level localization accuracy. Reference points (RPs) are generated in the grid by the FGGC model. Then, the received signal strength (RSS) values at each RP are calculated with the attenuation factors, such as the frequency band, three-dimensional propagation distance, and walls in complex environments. As a result, the fingerprint database can be established automatically without manual measurement, and the efficiency and cost that the FGGC model takes for the fingerprint database are superior to previous methods. The proposed indoor localization approach, which estimates the position step by step from the approximate grid location to the fine-grained location, can achieve higher real-time performance and localization accuracy simultaneously. The mean error of the proposed model is 0.36 ​m, far lower than that of previous approaches. Thus, the proposed model is feasible to improve the efficiency and accuracy of Wi-Fi indoor localization. It also shows high-accuracy performance with a fast running speed even under a large-size grid. The results indicate that the proposed method can also be suitable for precise marketing, indoor navigation, and emergency rescue.

Multimodal Medical Image Fusion Utilizing Two-scale Image Decomposition via Saliency Detection.

Modern medical imaging modalities used by clinicians have many applications in the diagnosis of complicated diseases. These imaging technologies reveal the internal anatomy and physiology of the body. The fundamental idea behind medical image fusion is to increase the image's global and local contrast, enhance the visual impact, and change its format so that it is better suited for computer processing or human viewing while preventing noise magnification and accomplishing excellent real-time performance. The top goal is to combine data from various modal images (CT/MRI and MR-T1/MR-T2) into a solitary image that, to the greatest degree possible, retains the key characteristics (prominent features) of the source images. The clinical accuracy of medical issues is compromised because innumerable classical fusion methods struggle to conserve all the prominent features of the original images. Furthermore, complex implementation, high computation time, and more memory requirements are key problems of transform domain methods. With the purpose of solving these problems, this research suggests a fusion framework for multimodal medical images that makes use of a multi-scale edge-preserving filter and visual saliency detection. The source images are decomposed using a two-scale edge-preserving filter into base and detail layers. Base layers are combined using the addition fusion rule, while detail layers are fused using weight maps constructed using the maximum symmetric surround saliency detection algorithm. The resultant image constructed by the presumed method has improved objective evaluation metrics than other classical methods, as well as unhindered edge contour, more global contrast, and no ringing effect or artifacts. The methodology offers a dominant and symbiotic arsenal of clinical symptomatic, therapeutic, and biomedical research competencies that have the prospective to considerably strengthen medical practice and biological understanding.

A coordinated optimization method of energy management and trajectory optimization for hybrid electric UAVs with PV/Fuel Cell/Battery

There are complex coupling relationships between flight motion and energy management for hybrid electric fixed wing UAVs with photovoltaic/fuel cell/battery. Aiming at realizing high-energy-efficiency long endurance autonomous flight, this paper proposes a coordinated optimization method of trajectory optimization and energy management for hybrid electric UAVs. Numerical simulation and experiment are carried out. Separated by surplus demand energy except that produced by PV, this method includes an optimal energy flight trajectory optimization layer and an energy management layer. For the former, fuzzy neural network sequential convex optimization (FNNSCP) is proposed to handle the flight trajectory optimization problem for maximizing utilization solar energy. For the latter, an online energy management strategy based on convex quadratic programming MPC (CQPMPC) is proposed to realize the power allocation. Numerical simulation results show that FNNSCP reduced 2% energy requirement compared with Radau pseudo-spectral method (RPM) from flight trajectory optimization level. From energy management level, CQPMPC saves hydrogen consumption by 3.1% and 16.3% compared with nonlinear model predictive control (NMPC) and fuzzy logic state machine (FLSM), respectively. In the experiment, less hydrogen fuel is consumed by proposed method by 5.2% and 15.6% compared with NMPC and FLSM, respectively. Experimental results show that the proposed method has better energy-saving performance and excellent real time performance. It indicates that optimizing flight trajectory and improving energy management efficiency can realize the high-energy-efficiency flight of hybrid electric UAVs. This method is conducive to promoting the application of hydrogen energy in the field of UAVs.

Single-atom Cu-attached MOFs as peroxide-like enzymes to construct dual-mode immunosensors for detection of breast cancer typing in serum

Molecular subtype of breast cancer has defined the treatment direction of breast cancer and guided the selection of drugs. Invasive tests such as tissue biopsy have the potential to promote the metastasis of cancer cells. Therefore, the continuous development of high-performance and low-cost in vitro diagnostic tools is crucial for the diagnosis and treatment of cancer prognosis. Liquid biopsy techniques provide noninvasive, real-time, dynamic, multicomponent, quantitative, and long-term observations at the cellular, genetic, and molecular levels in vivo. A Cu-Zr metal-organic framework(MOF) nanomases with monatomic Cu attachment has been synthesized by covalently attaching single atom Cu to the defect site of zirconia clusters in the UiO-66. The catalytic performance of Cu/UiO-66 as a peroxide-like enzyme was verified by enzyme kinetics calculation. Using o-phenylenediamine as substrate, a colorimetric fluorescence dual-mode immunosensor was constructed by introducing blue fluorescent carbon quantum dots (CDs) based on ultraviolet chromogenic reaction and fluorescence internal filtration effect. By magnetic adsorption separation, the background signal of the sensor is reduced and the sensitivity of the sensor is further improved. In 0.001–1 ng/mL detection range, detection of HER2/ER/PR/Ki-67, the result has obvious linear relationship. Among them, the colorimetric detection limit were 0.367/0.379/0.392/0.388 pg/mL; the ratio fluorescence detection limit can reach 0.3, 0.289, 0.257, 0.33 pg/mL, with high sensitivity. The proteins HER2, ER, PR and Ki-67 in serum related to human breast cancer typing were detected with high sensitivity. Finally, the actual serum samples were tested using sensors. According to the confirmed detection criteria, the classification of serum breast cancer was preliminarily explored with an accuracy of 87.5 %. The sensor has high catalytic performance and excellent real-time detection performance of biomarkers, and have practical application potential in human serum level detection. It provides a new method for the classification of breast cancer in serum.

An electrochemical sensor based on FeCo bimetallic single-atom nanozyme for sensitive detection of H2O2

Efficient catalytic decomposition of H2O2 is accompanied by electron transfer through Fe-Nx active sites of hemin in the human body. Inspired by this reaction process, the Fe SAs/Co CNs were successfully synthesized by combined Co atomic sites with nitrogen-carbon doped Fe single-atom active sites (SAs). The synergy between transition metals not only reduces agglomeration during synthesis but also improves its own electrical conductivity due to the interaction between Fe and Co that promotes the formation of graphite surface. Crucially, the synergistic effect of the Co site significantly enhanced the peroxidase activity of the Fe SAs and the reaction rate of the Fenton-like reaction, resulting in an efficient detection of H2O2. Catalytic kinetic calculations and enzymatic kinetic calculations were used to verify the electron transfer rate and catalytic performance of their constructed electrochemical sensing interfaces. The results showed that Fe SAs/Co CNs@GCE showed better detection performance than Fe SAs CNs@GCE. It was applied successfully to detect H2O2 released from cells in real-time as well. The linear detection range of Fe SAs/Co CNs@GCE for H2O2 was 1–16664 μM, and the detection limit was as low as 0.25 μM. Furthermore, an electrochemical sensing chip was constructed using Fe SAs/Co CNs@SPE and the prepared microfluidic channel. The constructed portable FeSAs/Co CNs@SPE had a linear range of 1–400 μM and a detection limit of 0.36 μM and achieved the recovery detection of H2O2 in serum. The electrochemical sensing interfaces constructed based on Fe SAs/Co CNs all have efficient catalytic performance and excellent real-time hydrogen peroxide detection performance, which have practical application potential for human oxidative stress level detection. And it provides a novel approach to the trace detection of bioactive small molecules.

Preparation of quaternized N-halamine modified graphene oxide based antibacterial hydrogel and wound healing of bacterial infection

In clinical practice, the wound on the surface of the skin is prone to bacterial infection, for which healing of infected wounds has always been a tremendous challenge for clinics and research institutions. We developed a multifunctional bactericidal, recyclable, and slow-release graphene oxide-based hydrogel for bacterial wound healing and real-time monitoring of bacterial infection in this study. At the same time, the material has a sensing function, which can be used in the connection between the injured skin and the continuous detection equipment. QNGH (quaternarized N-halamine-grafted GO hydrogel) is manufactured by hydrogen bonding between quaternized N-halamine-modified graphene oxide and polyvinyl alcohol (PVA). The results show that in the mouse model of full-thickness skin repair, the hydrogel can continuously release germicidal ions and recyclability, promoting wound healing and contraction. Further, the graphene oxide-based hydrogel has excellent strain sensing performance. It detects the bending and stretching movements of different parts of the human body quickly, stably, and sensitively to show an excellent real-time monitoring performance of human motion. The sensing function of the hydrogel further broadens its application field. Therefore, this hydrogel material is expected to be a candidate material for sensing devices at the wound.

Network Security Situation Prediction Based on Optimized Clock-Cycle Recurrent Neural Network for Sensor-Enabled Networks.

We propose an optimized Clockwork Recurrent Neural Network (CW-RNN) based approach to address temporal dynamics and nonlinearity in network security situations, improving prediction accuracy and real-time performance. By leveraging the clock-cycle RNN, we enable the model to capture both short-term and long-term temporal features of network security situations. Additionally, we utilize the Grey Wolf Optimization (GWO) algorithm to optimize the hyperparameters of the network, thus constructing an enhanced network security situation prediction model. The introduction of a clock-cycle for hidden units allows the model to learn short-term information from high-frequency update modules while retaining long-term memory from low-frequency update modules, thereby enhancing the model's ability to capture data patterns. Experimental results demonstrate that the optimized clock-cycle RNN outperforms other network models in extracting the temporal and nonlinear features of network security situations, leading to improved prediction accuracy. Furthermore, our approach has low time complexity and excellent real-time performance, ideal for monitoring large-scale network traffic in sensor networks.

Plane-based global registration for pavement 3D reconstruction using hybrid solid-state LiDAR point cloud

This study aims to utilize the hybrid solid-state LiDAR (SSL) point cloud to achieve pavement 3D reconstruction and overcome the stratification problem of the pavement point cloud. A low-cost Mobile Laser Scanning (MLS) system based on the hybrid SSL is constructed beforehand. Then, a region of interest (ROI) extraction algorithm is designed to filter the useless point cloud. Finally, a plane-based global registration (PGR) approach is proposed to address the stratification problem of vertical direction. PGR includes two parts: coarse registration and refined registration. The coarse registration extracts the pavement plane to reduce the vertical error. The refined registration utilizes the Iterative Closest Point (ICP) algorithm to reduce the registration error further. Compared with the mainstream registration algorithms, PGR shows the highest registration accuracy in different road scenarios and maintains excellent real-time performance. Furthermore, the reconstruction accuracy is kept within 1 cm, sufficient to extract pavement information.

Fusing Spatio-Temporal Contexts into DeepFM for Taxi Pick-Up Area Recommendation

Short-term GPS data based taxi pick-up area recommendation can improve the efficiency and reduce the overheads. But how to alleviate sparsity and further enhance accuracy is still challenging. Addressing at these issues, we propose to fuse spatio-temporal contexts into deep factorization machine (STC_DeepFM) offline for pick-up area recommendation, and within the area to recommend pick-up points online using factorization machine (FM). Firstly, we divide the urban area into several grids with equal size. Spatio-temporal contexts are destilled from pick-up points or points-of-interest (POIs) belonged to the preceding grids. Secondly, the contexts are integrated into deep factorization machine (DeepFM) to mine high-order interaction relationships from grids. And a novel algorithm named STC_DeepFM is presented for offline pick-up area recommendation. Thirdly, we devise the architecture of offline-to-online (O2O) recommendation respectively based on DeepFM and FM model in order to tradeoff the accuracy and efficiency. Some experiments are designed on the DiDi dataset to evaluate step by step the performance of spatio-temporal contexts, different recommendation models, and the O2O architecture. The results show that the proposed STC_DeepFM algorithm exceeds several state-of-the-art methods, and the O2O architecture achieves excellent real-time performance.

A Fast Detection Method Using Anisotropic Guidance for Infrared Small Target Under Complex Scenes

The development of intelligent control and visual navigation, along with the ongoing increase in imaging distance, has led to realistic demands for weak and small target detection. However, figuring out how to reduce the interference of various complex factors while achieving a high detection rate and low false alarm rate for real-time infrared small target detection is still a significant challenge. We propose a computationally simple single-frame infrared small target fast detection method applicable to complex scenes. First, a novel anisotropy filter bank suitable for small target feature extraction is constructed and modified with a point spread function. This makes it possible to map the salient features and spatial features of the target in the spatial domain using the imaging mechanism. We then combined two sets of feature parameters using the filtered features, including isotropy measure and directional energy factors, to enable the detection of small targets. Experimental findings showed that the algorithm performs well in scenarios involving complicated clouds, urban ground, and vegetation. The software also achieved excellent real-time performance because of its straightforward computational design.

Real-time and high-transmission middle-infrared optical imaging system based on a pixel-wise metasurface micro-polarization array

Real-time polarization medium-wave infrared (MIR) optical imaging systems enable the acquisition of infrared and polarization information for a target. At present, real-time polarization MIR devices face the following problems: poor real-time performance, low transmission and high requirements for fabrication and integration. Herein, we aim to improve the performance of real-time polarization imaging systems in the MIR waveband and solve the above-mentioned defects. Therefore, we propose a MIR polarization imaging system to achieve real-time polarization-modulated imaging with high transmission as well as improved performance based on a pixel-wise metasurface micro-polarization array (PMMPA). The PMMPA element comprises several linear polarization (LP) filters with different polarization angles. The optimization results demonstrate that the transmittance of the center field of view for the LP filters is up to 77% at a wavelength of 4.0 μm and an extinction ratio of 88 dB. In addition, a near-diffraction-limited real-time MIR imaging optical system is designed with a field of view of 5° and an F-number of 2. The simulation results show that an MIR polarization imaging system with excellent real-time performance and high transmission is achieved by using the optimized PMMPA element. Therefore, the method is compatible with the available optical system design technologies and provides a way to realize real-time polarization imaging in MIR wavebands.

Hybrid Compression Optimization Based Rapid Detection Method for Non-Coal Conveying Foreign Objects.

The existence of conveyor foreign objects poses a serious threat to the service life of conveyor belts, which will cause abnormal damage or even tearing, so fast and effective detection of conveyor foreign objects is of great significance to ensure the safe and efficient operation of belt conveyors. Considering the need for the foreign object detection algorithm to operate in edge computing devices, this paper proposes a hybrid compression method that integrates network sparse, structured pruning, and knowledge distillation to compress the network parameters and calculations. Combined with a Yolov5 network for practice, three structured pruning strategies are specifically proposed, all of which are proven to have achieved a good compression effect. The experiment results show that under the pruning rate of 0.9, the proposed three pruning strategies can achieve more than 95% compression for network parameters, more than 90% compression for the computation, and more than 90% compression for the size of the network model, and the optimized network is able to accelerate inference on both Central Processing Unit (CPU) and Graphic Processing Unit (GPU) hardware platforms, with a maximum speedup of 70.3% on the GPU platform and 157.5% on the CPU platform, providing an excellent real-time performance but also causing a large accuracy loss. In contrast, the proposed method balances better real-time performance and detection accuracy (>88.2%) when the pruning rate is at 0.6~0.9. Further, to avoid the influence of motion blur, a method of introducing prior knowledge is proposed to improve the resistance of the network, thus strongly ensuring the detection effect. All the technical solutions proposed are of great significance in promoting the intelligent development of coal mine equipment, ensuring the safe and efficient operation of belt conveyors, and promoting sustainable development.

LiSee

Reaching surrounding target objects is difficult for blind and low-vision (BLV) users, affecting their daily life. Based on interviews and exchanges, we propose an unobtrusive wearable system called LiSee to provide BLV users with all-day assistance. Following a user-centered design method, we carefully designed the LiSee prototype, which integrates various electronic components and is disguised as a neckband headphone such that it is an extension of the existing headphone. The top-level software includes a series of seamless image processing algorithms to solve the challenges brought by the unconstrained wearable form so as to ensure excellent real-time performance. Moreover, users are provided with a personalized guidance scheme so that they can use LiSee quickly based on their personal expertise. Finally, a system evaluation and a user study were completed in the laboratory and participants' homes. The results show that LiSee works robustly, indicating that it can meet the daily needs of most participants to reach surrounding objects.

HD-RMPC: A Hierarchical Distributed and Robust Model Predictive Control Framework for Urban Traffic Signal Timing

Due to the nonlinearity and dynamics of transportation systems, traffic signal control (TSC) in urban traffic networks has always been an important challenge. In recent years, model predictive control (MPC) has shown extraordinary potential in TSC due to its outstanding ability to model dynamic systems. However, the relatively complex online computing, lack of reasonable setpoints for target solving, and uncertainty of traffic network hinder MPC from being further applied. To address these problems, we propose a hierarchical, distributed, and robust model predictive control (HD-RMPC) framework for urban TSC. At the slow-update layer, the road network is dynamically divided into several subareas according to regional attributes and real-time traffic demand. Meanwhile, the volume is coordinated in a robust way for the purpose of traffic equilibrium and overflow prevention. Then, the set-point matrix of each subarea is calculated to equalize the flow in the subarea. This distributed framework guarantees the real-time performance of MPC in urban traffic networks. At the fast-update layer, we adopt an improved prediction model by explicit modeling of the disturbance and reduce the prediction error. Finally, the objective function is reconstructed and solved at the control layer to obtain the optimal control law. Through continuous and asynchronous optimization of the set point and prediction model, the framework significantly improves the control effect. Simulation evaluation based on a real-world road network demonstrates that the proposed HD-RMPC method outperforms all baselines and maintains excellent real-time performance.

LAG: Layered Objects to Generate Better Anchors for Object Detection in Aerial Images

You Only Look Once (YOLO) series detectors are suitable for aerial image object detection because of their excellent real-time ability and performance. Their high performance depends heavily on the anchor generated by clustering the training set. However, the effectiveness of the general Anchor Generation algorithm is limited by the unique data distribution of the aerial image dataset. The divergence in the distribution of the number of objects with different sizes can cause the anchors to overfit some objects or be assigned to suboptimal layers because anchors of each layer are generated uniformly and affected by the overall data distribution. In this paper, we are inspired by experiments under different anchors settings and proposed the Layered Anchor Generation (LAG) algorithm. In the LAG, objects are layered by their diagonals, and then anchors of each layer are generated by analyzing the diagonals and aspect ratio of objects of the corresponding layer. In this way, anchors of each layer can better match the detection range of each layer. Experiment results showed that our algorithm is of good generality that significantly uprises the performance of You Only Look Once version 3 (YOLOv3), You Only Look Once version 5 (YOLOv5), You Only Learn One Representation (YOLOR), and Cascade Regions with CNN features (Cascade R-CNN) on the Vision Meets Drone (VisDrone) dataset and the object DetectIon in Optical Remote sensing images (DIOR) dataset, and these improvements are cost-free.