Aircraft Target Detection Research Articles

Research on Airport Aircraft Target Detection Algorithm Based on YOLOv4

Aiming at the complex airport environment and the large scale transformation of aircraft, a target detection algorithm based on YOLOv4 is designed. Based on the YOLOv4 algorithm structure, a feature fusion scale is added to the original 3 detection scales, which has the ability to obtain smaller target information. Simultaneously, the residual network structure is simplified, and a certain amount of calculation is reduced. In order to optimize the loss, the regression loss function CIoU is introduced, which accelerates the convergence of the network. The test results show that the algorithm of this article can reach a prediction accuracy of 93.31% for airplane target, a recall rate of 83.92%, a mean average accuracy of 91.02%, which is 2.49% higher than YOLOv4, which improves the recognition accuracy of the model in the airport environment.

Improved High Precision Aircraft Target Detection Method of YOLT

The first remote sensing dataset that can be used for aircraft target detection is created and a 3D model simulation method for data augmentation is proposed. After statistical analysis of aircraft sizes, a high-precision improved YOLT method for target detection is proposed. YOLT is the first light algorithm focusing on target detection in remote sensing images. We improve its network structure, design a creative method based on receptive field improvement and adopt an optimized non-maximum suppression strategy. The results show that our method has better performance than other main target detection algorithms, especially for small targets and cross-scale samples.

Airborne infrared aircraft target detection algorithm based on YOLOv4-tiny

Aiming at the problem that the current aerial infrared aircraft targets are blurred, low contrast, and susceptible to noise interference, which can lead to inaccurate recognition, an improved YOLOv4-tiny infrared aircraft target detection method based on cavity convolution is proposed. First, in order to make full use of the shallow features, add a parallel branch after the feature layer whose output size of YOLOv4-tiny is; then, after the first network output layer, add three parallel holes of 1, 3 respectively. 5. The depth of 5 can separate the hollow convolution layer to expand the feature map receptive field; finally, the feature fusion network is improved, the final output feature layer of the network, the improved anti-residual block extraction feature, and the size is adjusted after convolution. The prediction result is processed and output by yolo head. Experiments on the aerial infrared aircraft data set show that compared with the original YOLOv4-tiny, the detection accuracy is increased by 4.29% and the detection effect is significantly improved under the premise of less loss of detection frame rate and small weight.

Attention and feature fusion for aircraft target detection in optical remote sensing images

Attention and feature fusion for aircraft target detection in optical remote sensing images

Aircraft Detection System Based on Regions with Convolutional Neural Networks

Object detection in remote sensing imagery is an important topic of image processing researches. Detection of objects and regions from satellite imagery takes its place in various applications such as the detection of residential areas and agricultural lands, road lines, ships, as well as airport and hangar detections. As a more specific remote sensing imagery based object-detection process, a stationary aircraft detection system could serve as a model in some military applications. Such a model could serve the detection of stationary aircraft targets in airports. In the proposed study, a deep learning-based model detects the aircraft in the airports using the satellite images from Google Earth. The deep learning model uses the state of the art Regions with Convolutional Neural Network (RCNN). Firstly a built from scratch CNN design is used for the basic learning step of the system. Then, RCNN performs region detection, which anchors the stationary aircraft object bounding boxes. A large dataset containing aircraft images is preferred for the training of CNN. To validate the system, satellite images captured from airports in Turkey are used. The results of the study show that the proposed model successfully operates aircraft detection with high-performance rates. While the classifier network structure, which constitutes the first step of the study, produces 98.4% test accuracy, the proposed aircraft detection framework has successfully performed the aircraft identification process by producing matched bounding boxes in the test images.

A dataset for detection and tracking of dim aircraft targets through radar echo sequences

A dataset for detection and tracking of dim aircraft targets through radar echo sequences

A dataset for infrared detection and tracking of dim-small aircraft targets under ground / air background

A dataset for infrared detection and tracking of dim-small aircraft targets under ground / air background

Deep learning and optimization algorithm for high efficient searching and detection of aircraft targets in remote sensing images

Deep learning and optimization algorithm for high efficient searching and detection of aircraft targets in remote sensing images

基于旋转不变特征的遥感图像飞机目标检测方法

基于旋转不变特征的遥感图像飞机目标检测方法

Aircraft target detection using multimodal satellite-based data

Abstract In recent years, remote sensing image processing on orbit has become an essential task to conduct rapid satellite response, where the target detection using multimodal remote sensing images has attracted much research attention. More specifically, the aircraft is an important type of targets and aircraft target detection on-orbit becomes much essential due to the safety reasons. In this work, we main focus on the detection of aircraft targets using multimodal satellite-based data. Our method consists of three main procedures. First, we estimate the position of the imaging target in the combination of satellite attitude and orbit information, and then we can select several candidate image patch from the original large scale image data. Then, the initial investigation of candidate target areas is detected based on the texture characteristics, where Gabor filtering, image binarization and regional Unicom are utilized and the candidate aircraft target can be roughly detected. Since the characteristics of aircrafts remain relatively stable, the candidate areas can be further refined based on circular-matched filtering. To evaluate the performance of the proposed method on aircraft target detection, we have conducted experiments on six large scale remote sensing images. Experiments show that our proposed method is able to achieve an accuracy of 90% for target detection and the detection time is less than 0.5 s, which can be used for real time applications.

2-D Coherent Integration Processing and Detecting of Aircrafts Using GNSS-Based Passive Radar

Long time coherent integration is a vital method for improving the detection ability of global navigation satellite system (GNSS)-based passive radar, because the GNSS signal is not radar-designed and its power level is very low. For aircraft detection, the large range cell migration (RCM) and Doppler frequency migration (DFM) will seriously affect the coherent processing of azimuth signals, and the traditional range match filter will also be mismatched due to the Doppler-intolerant characteristic of GNSS signals. Accordingly, the energy loss of 2-dimensional (2-D) coherent processing is inevitable in traditional methods. In this paper, a novel 2-D coherent integration processing and algorithm for aircraft target detection is proposed. For azimuth processing, a modified Radon Fourier Transform (RFT) with range-walk removal and Doppler rate estimation is performed. In respect to range compression, a modified matched filter with a shifting Doppler is applied. As a result, the signal will be accurately focused in the range-Doppler domain, and a sufficiently high SNR can be obtained for aircraft detection with a moving target detector. Numerical simulations demonstrate that the range-Doppler parameters of an aircraft target can be obtained, and the position and velocity of the aircraft can be estimated accurately by multiple observation geometries due to abundant GNSS resources. The experimental results also illustrate that the blind Doppler sidelobe is suppressed effectively and the proposed algorithm has a good performance even in the presence of Doppler ambiguity.

RESEARCH ON AIRCRAFT TARGET DETECTION ALGORITHM BASED ON IMPROVED RADIAL GRADIENT TRANSFORMATION

Abstract. Aiming at the problem that the target may have different orientation in the unmanned aerial vehicle (UAV) image, the target detection algorithm based on the rotation invariant feature is studied，and this paper proposes a method of RIFF (Rotation-Invariant Fast Features) based on look up table and polar coordinate acceleration to be used for aircraft target detection. The experiment shows that the detection performance of this method is basically equal to the RIFF, and the operation efficiency is greatly improved.

Key parameters design of an aerial target detection system on a space-based platform

To ensure flight safety of an aerial aircraft and avoid recurrence of aircraft collisions, a method of multi-information fusion is proposed to design the key parameter to realize aircraft target detection on a space-based platform. The key parameters of a detection wave band and spatial resolution using the target-background absolute contrast, target-background relative contrast, and signal-to-clutter ratio were determined. This study also presented the signal-to-interference ratio for analyzing system performance. Key parameters are obtained through the simulation of a specific aircraft. And the simulation results show that the boundary ground sampling distance is 30 and 35 m in the mid- wavelength infrared (MWIR) and long-wavelength infrared (LWIR) bands for most aircraft detection, and the most reasonable detection wavebands is 3.4 to 4.2 μm and 4.35 to 4.5 μm in the MWIR bands, and 9.2 to 9.8 μm in the LWIR bands. We also found that the direction of detection has a great impact on the detection efficiency, especially in MWIR bands.

Coarse to fine aircraft detection from front-looking infrared images

Due to the weak feature and wide angle of long-distance aircraft targeting in the parking apron from front-looking infrared images, there are always false alarms in aircraft targeting detection. This leads to relatively poor reliability for detection results. In this paper, we present a scene-driven coarse-to-fine aircraft target detection method. First, we preprocess the image by combining the sharpened and enhanced images. Second, the region of interest (ROI) is segmented by using the local mean variance of the image and a series of subsequent processing. Then, target candidate areas are located by using the feature of local marginal distributions. Lastly, aircrafts can be detected accurately by a novel aircraft shape filter. Experiments on three infrared image sequences have shown that the presented method is effective and robust in detecting long-distance aircraft from front-looking infrared images and can also improve the reliability of the detection results.

A Novel Method of Aircraft Detection Based on High-Resolution Panchromatic Optical Remote Sensing Images.

In target detection of optical remote sensing images, two main obstacles for aircraft target detection are how to extract the candidates in complex gray-scale-multi background and how to confirm the targets in case the target shapes are deformed, irregular or asymmetric, such as that caused by natural conditions (low signal-to-noise ratio, illumination condition or swaying photographing) and occlusion by surrounding objects (boarding bridge, equipment). To solve these issues, an improved active contours algorithm, namely region-scalable fitting energy based threshold (TRSF), and a corner-convex hull based segmentation algorithm (CCHS) are proposed in this paper. Firstly, the maximal variance between-cluster algorithm (Otsu’s algorithm) and region-scalable fitting energy (RSF) algorithm are combined to solve the difficulty of targets extraction in complex and gray-scale-multi backgrounds. Secondly, based on inherent shapes and prominent corners, aircrafts are divided into five fragments by utilizing convex hulls and Harris corner points. Furthermore, a series of new structure features, which describe the proportion of targets part in the fragment to the whole fragment and the proportion of fragment to the whole hull, are identified to judge whether the targets are true or not. Experimental results show that TRSF algorithm could improve extraction accuracy in complex background, and that it is faster than some traditional active contours algorithms. The CCHS is effective to suppress the detection difficulties caused by the irregular shape.

Aircraft Detection in High-Resolution SAR Images Based on a Gradient Textural Saliency Map.

This paper proposes a new automatic and adaptive aircraft target detection algorithm in high-resolution synthetic aperture radar (SAR) images of airport. The proposed method is based on gradient textural saliency map under the contextual cues of apron area. Firstly, the candidate regions with the possible existence of airport are detected from the apron area. Secondly, directional local gradient distribution detector is used to obtain a gradient textural saliency map in the favor of the candidate regions. In addition, the final targets will be detected by segmenting the saliency map using CFAR-type algorithm. The real high-resolution airborne SAR image data is used to verify the proposed algorithm. The results demonstrate that this algorithm can detect aircraft targets quickly and accurately, and decrease the false alarm rate.

Calculation of Aircraft Target’s Single-Pulse Detection Probability

The original radar cross section data or some rough models are often used to estimate a given aircraft target detection probability. The calculation results may not be very accurate as targets are different from one another and the real radar detection process is complex. A new method for radar cross section model generation is proposed and it takes the random factors like air turbulence into account; this makes it conform to the reality. In addition, this radar cross section model can be directly applied to the radar detection process to calculate the detection probability of a specific aircraft at any attitude. Four typical aerial vehicles are taken as examples to demonstrate this method and information such as detection probability, signal to noise ratio and detection distance. Target's instantaneous probability of being tracked, which corresponds to target's detection probability, can also be calculated. Using these calculation results, we can compare two different aircrafts' stealth performance in detail or optimize an aircraft's flight path.

Research on Aircraft Target Detection Probability for OTHR

In this paper, a simulation method of detection probability of aircraft target for Over-The-Horizon Radar (OTHR) by computer is proposed. The effects of different ionosphere states on detection range for OTHR is concluded, which become constraint on simulation of detection probability. Taking variety of target RCS with attitude during flight through given track into consideration, simulation model of target dynamic RCS is established. Models of instantaneous detection probability and comprehensive detection probability are also presented. Then, detection probability of aircraft can be obtained through utilizing all models above based on given calculation steps. Simulations show that ionosphere state and target RCS have a great influence on detection probability.

Utilization of a nonrecurrent waveform to mitigate range‐folded spread Doppler clutter: Application to over‐the‐horizon radar

This paper describes the application of a new nonrecurrent waveform (NRWF) to a relocatable over‐the‐horizon radar (ROTHR) located in southern Virginia. The waveform is designed to improve the detection of aircraft targets through the mitigation of long‐range spread Doppler clutter (SDC) encountered during nighttime operations. A discussion of the NRWF and its principle of operation are included, along with a brief description of ROTHR modifications. The focus of the paper is the presentation of test results from engineering, clutter mitigation, and target detection tests conducted during January through April of 1997.