Infrared Small Target Detection Algorithm Based on ISTD-CenterNet

This paper proposes a real-time detection method to improve the Infrared small target detection CenterNet(ISTD-CenterNet)network for detecting small infrared targets in complex environments.The method eliminates the need for an anchor frame,addressing the issues of low accuracy and slow speed.HRNet is used as the framework for feature extraction,and an ECBAM attention module is added to each stage branch for intelligent identification of the positions of small targets and significant objects.A scale enhancement module is also added to obtain a high-level semantic representation and fine-resolution prediction map for the entire infrared image.Besides,an improved sensory field enhancement module is designed to leverage semantic information in low-resolution feature maps,and a convolutional attention mechanism module is used to increase network stability and convergence speed.Comparison experiments conducted on the infrared small target data set ESIRST.The experiments show that compared to the benchmark network CenterNet-HRNet,the proposed ISTD-CenterNet improves the recall by 22.85%and the detection accuracy by 13.36%.Compared to the state-of-the-art YOLOv5small,the ISTD-CenterNet recall is improved by 5.88%,the detection precision is improved by 2.33%,and the detection frame rate is 48.94 frames/sec,which realizes the accurate real-time detection of small infrared targets.

Dim Moving Small Target Detection by Local and Global Variance Filtering on Temporal Profiles in Infrared Sequences

In this paper, the temporal different characteristics between the target and background pixels are used to detect dim moving targets in the slow-evolving complex background. A local and global variance filter on temporal profiles is presented that addresses the temporal characteristics of the target and background pixels to eliminate the large variation of background temporal profiles. Firstly, the temporal behaviors of different types of image pixels of practical infrared scenes are analyzed.Then, the new local and global variance filter is proposed. The baseline of the fluctuation level of background temporal profiles is obtained by using the local and global variance filter. The height of the target pulse signal is extracted by subtracting the baseline from the original temporal profiles. Finally, a new target detection criterion is designed. The proposed method is applied to detect dim and small targets in practical infrared sequence images. The experimental results show that the proposed algorithm has good detection performance for dim moving small targets in the complex background.

Multi-Channel Based on Attention Network for Infrared Small Target Detection

Infrared detection technology has the advantages of all-weather detection and good concealment,which is widely used in long-distance target detection and tracking systems.However,the complex background,the strong noise,and the characteristics of small scale and weak intensity of targets bring great difficulties to the detection of infrared small targets.A multi-channel based on attention network is proposed in this paper,aimed at the problem of high missed detection rate and false alarm rate of traditional algorithms and the problem of large model,high complexity and poor detection performance of deep learning algorithms.First,given the difficulty in extracting the features of infrared multiscale and small dim targets,the multiple channels are designed based on dilated convolution to capture multiscale target features.Second,the coordinate attention block is incorporated in each channel to suppress background clutters adaptively and enhance target features.In addition,the fusion of shallow detail features and deep abstract semantic features is realized by synthesizing the contextual attention fusion block.Finally,it is verified that,compared with other state-of-the-art methods based on the datasets SIRST and MDFA,the proposed algorithm further improves the detection effect,and the model size and computational complexity are smaller.

Fusion network for small target detection based on YOLO and attention mechanism

Target detection is an important task in computer vision research, and such an anomaly detection and the topic of small target detection task is more concerned. However, there are still some problems in this kind of researches, such as small target detection in complex environments is susceptible to background interference and poor detection results. To solve these issues, this study proposes a method which introduces the attention mechanism into the you only look once(YOLO) network. In addition, the amateur-produced mask dataset was created and experiments were conducted. The results showed that the detection effect of the proposed mothed is much better.

CAFUNeT:A small infrared target detection method in complex backgrounds

Small infrared target detection has widespread applications in various fields including military,aviation,and medicine.However,detecting small infrared targets in complex backgrounds remains challenging.To detect small infrared targets,we propose a variable-structure U-shaped network referred as CAFUNet.A central differential convolution-based encoder,ASPP,an Attention Fusion module,and a decoder module are the critical components of the CAFUNet.The encoder module based on central difference convolution effectively extracts shallow detail information from infrared images,complemented by rich contextual information obtained from the deep features in the decoder module.However,the direct fusion of the shallow detail features with semantic features may lead to feature mismatch.To address this,we incorporate an Attention Fusion(AF)module to enhance the network performance further.We performed ablation studies on each module to evaluate its effectiveness.The results show that our proposed algorithm outperforms the state-of-the-art methods on publicly available datasets.

Novel detection method for infrared small targets using weighted information entropy

This paper presents a method for detecting the small infrared target under complex background. An algorithm, named local mutation weighted information entropy （LMWIE）, is proposed to suppress background. Then, the grey value of targets is enhanced by calculating the local energy. Image segmentation based on the adaptive threshold is used to solve the problems that the grey value of noise is enhanced with the grey value improvement of targets. Experimental results show that compared with the adaptive Butterworth high-pass filter method, the proposed algorithm is more effective and faster for the infrared small target detection.

RT-YOLO:A Residual Feature Fusion Triple Attention Network for Aerial Image Target Detection

In recent years,target detection of aerial images of unmannedaerial vehicle(UAV)has become one of the hottest topics.However,targetdetection of UAV aerial images often presents false detection and misseddetection.We proposed a modified you only look once(YOLO)model toimprove the problems arising in object detection in UAV aerial images:(1)A new residual structure is designed to improve the ability to extract featuresby enhancing the fusion of the inner features of the single layer.At the sametime,triplet attention module is added to strengthen the connection betweenspace and channel and better retain important feature information.(2)Thefeature information is enriched by improving the multi-scale feature pyramidstructure and strengthening the feature fusion at different scales.(3)A newloss function is created and the diagonal penalty term of the anchor frame isintroduced to improve the speed of training and the accuracy of reasoning.The proposed model is called residual feature fusion triple attention YOLO(RT-YOLO).Experiments showed that the mean average precision(mAP)ofRT-YOLO is increased from 57.2%to 60.8%on the vehicle detection in aerialimage(VEDAI)dataset,and the mAP is also increased by 1.7%on the remotesensing object detection(RSOD)dataset.The results show that theRT-YOLOoutperforms other mainstream models in UAV aerial image object detection.

A New Method of Small Moving Target Detection and Its Performance Analysis

This paper describes a new method of small moving target detection and analyzes the performance of this algorithm. The method is based on multi-level threshold decision-making and sliding trajectory confidence testing technology. The parameters of the algorithm are also given. Experiments have been conducted, the results show that the algorithm has advantages of high detection probability, simple structure, and excellent real-time performance.

Using deep learning to detect small targets in infrared oversampling images

According to the oversampling imaging characteristics, an infrared small target detection method based on deep learning is proposed. A 7-layer deep convolutional neural network(CNN) is designed to automatically extract small target features and suppress clutters in an end-to-end manner. The input of CNN is an original oversampling image while the output is a cluttersuppressed feature map. The CNN contains only convolution and non-linear operations, and the resolution of the output feature map is the same as that of the input image. The L1-norm loss function is used, and a mass of training data is generated to train the network effectively. Results show that compared with several baseline methods, the proposed method improves the signal clutter ratio gain and background suppression factor by 3–4 orders of magnitude, and has more powerful target detection performance.

An Effective Method of Threshold Selection for Small Object Image

The image segmentation difficulties of small objects which are much smaller than their background often occur in target detection and recognition. The existing threshold segmentation methods almost fail under the circumstances. Thus, a threshold selection method is proposed on the basis of area difference between background and object and intra-class variance. The threshold selection formulae based on one-dimensional (1-D) histogram, two-dimensional (2-D) histogram vertical segmentation and 2-D histogram oblique segmentation are given. A fast recursive algorithm of threshold selection in 2-D histogram oblique segmentation is derived. The segmented images and processing time of the proposed method are given in experiments. It is compared with some fast algorithms, such as Otsu, maximum entropy and Fisher threshold selection methods. The experimental results show that the proposed method can effectively segment the small object images and has better anti-noise property.

A spatiotemporal intelligent framework and experimental platform for urban digital twins

Backgrounds This work emphasizes the current research status of the urban Digital Twins to establish an intelligent spatiotemporal framework.A Geospatial Artificial Intelligent(GeoAI)system is developed based on the Geographic Information System and Artificial Intelligence.It integrates multi-video technology and Virtual City in urban Digital Twins.Methods Besides,an improved small object detection model is proposed:YOLOv5-Pyramid,and Siamese network video tracking models,namely MPSiam and FSSiamese,are established.Finally,an experimental platform is built to verify the georeferencing correction scheme of video images.Result The MultiplyAccumulate value of MPSiam is 0.5B,and that of ResNet50-Siam is 4.5B.Besides,the model is compressed by 4.8times.The inference speed has increased by 3.3 times,reaching 83 Frames Per Second.3%of the Average Expectation Overlap is lost.Therefore,the urban Digital Twins-oriented GeoAI framework established here has excellent performance for video georeferencing and target detection problems.

A real-time detection and positioning method for small and weak targets using a 1D morphology-based approach in 2D images

A small and weak target detection method is proposed in this work that outperforms all other methods in terms of real-time capability.It is the first time that two-dimensional(2D)images are processed using only one-dimensional1D structuring elements in a morphology-based approach,enabling the real-time hardware implementation of the whole image processing method.A parallel image readout and processing structure is introduced to achieve an ultra-low latency time on the order of nanoseconds,and a hyper-frame resolution in the time domain can be achieved by combining the row-by-row structure and the electrical rolling shutter technique.Experimental results suggest that the expected target can be successfully detected under various interferences with an accuracy of 0.1 pixels(1σ)under the worst sky night test condition and that a centroiding precision of better than 0.03 pixels(1σ)can be reached for static tests.The real-time detection method with high robustness and accuracy is attractive for application to all types of real-time small target detection systems,such as medical imaging,infrared surveillance,and target measurement and tracking,where an ultra-high processing speed is required.

A Hybrid Feature Fusion Traffic Sign Detection Algorithm Based on YOLOv7

Autonomous driving technology has entered a period of rapid development,and traffic sign detection is one of the important tasks.Existing target detection networks are difficult to adapt to scenarios where target sizes are seriously imbalanced,and traffic sign targets are small and have unclear features,which makes detection more difficult.Therefore,we propose aHybrid Feature Fusion Traffic Sign detection algorithmbased onYOLOv7(HFFTYOLO).First,a self-attention mechanism is incorporated at the end of the backbone network to calculate feature interactions within scales;Secondly,the cross-scale fusion part of the neck introduces a bottom-up multi-path fusion method.Design reuse paths at the end of the neck,paying particular attention to cross-scale fusion of highlevel features.In addition,we found the appropriate channel width through a lot of experiments and reduced the superfluous parameters.In terms of training,a newregression lossCMPDIoUis proposed,which not only considers the problem of loss degradation when the aspect ratio is the same but the width and height are different,but also enables the penalty term to dynamically change at different scales.Finally,our proposed improved method shows excellent results on the TT100K dataset.Compared with the baseline model,without increasing the number of parameters and computational complexity,AP0.5 and AP increased by 2.2%and 2.7%,respectively,reaching 92.9%and 58.1%.

A convolutional neural network based approach to sea clutter suppression for small boat detection

Current methods for radar target detection usually work on the basis of high signal-to-clutter ratios.In this paper we propose a novel convolutional neural network based dual-activated clutter suppression algorithm,to solve the problem caused by low signal-to-clutter ratios in actual situations on the sea surface.Dual activation has two steps.First,we multiply the activated weights of the last dense layer with the activated feature maps from the upsample layer.Through this,we can obtain the class activation maps(CAMs),which correspond to the positive region of the sea clutter.Second,we obtain the suppression coefficients by mapping the CAM inversely to the sea clutter spectrum.Then,we obtain the activated range-Doppler maps by multiplying the coefficients with the raw range-Doppler maps.In addition,we propose a sampling-based data augmentation method and an effective multiclass coding method to improve the prediction accuracy.Measurement on real datasets verified the effectiveness of the proposed method.

FPC-BTB detection and positioning system based on optimized YOLOv5

With the aim of addressing the visual positioning problem of board-to-board(BTB)jacks during the automatic assembly of flexible printed circuit(FPC)in mobile phones,an FPC-BTB jack detection method based on the optimized You Only Look Once,version 5(YOLOv5)deep learning algorithm was proposed in this study.An FPC-BTB jack real-time detection and positioning system was developed for the real-time target detection and pose output synchronization of the BTB jack.On that basis,a visual positioning experimental platform that integrated a UR5e manipulator arm and Hikvision industrial camera was built for BTB jack detection and positioning experiments.As indicated by the experimental results,the developed FPC-BTB jack detection and positioning system for BTB target recognition and positioning achieved a success rate of 99.677%.Its average detection accuracy reached 99.341%,the average confidence of the detected target was 91%,the detection and positioning speed reached 31.25 frames per second,and the positioning deviation was less than 0.93 mm,which conforms to the practical application requirements of the FPC assembly process.

Signal waveform design to detect an underwater high-speed small target

The problem of sonar signal waveform design to detect a high-speed small target in an underwater environment is discussed. From theoretical analysis, time-frequency hop signal is regarded as the most suitable signal waveform in this application. To get precise target parameter estimation ability, the signal should have high range-Doppler resolution performance. The results of signal analysis show that hop signal with frequency serial coding as Costas array has sharp ambiguity characteristic, so it can be used in an active sonar system to detect a high speed small target. A scheme of frequency coding is also presented.

An improved defect recognition framework for casting based on DETR algorithm

The current casting surface defect detection algorithms suffer from poor small target defect recognition and imbalance between detection performance and detection time.An improved algorithmic framework for casting defect detection was proposed based on the DEtection TRansformer(DETR)algorithm.The algorithm takes ResNet with an efficient channel attention(ECA)-Net module as the backbone network.In addition,based on the original algorithm architecture,dynamic anchor boxes,improved multi-scale deformable attention module,and SIoU loss function are introduced to improve the sensitivity of transformer structure to input location information and scale size,and the small target defect detection performance is effectively improved.The recognition performance of the algorithm in a self-built casting defect dataset was studied.The improved DETR algorithm has 97.561% accuracy in recognizing two defects,namely sandinclusion and notch,with the detection rate being improved by 65.854% and 17.073% compared with the original DETR and you only look once(Yolo)-V5,respectively.This algorithm verifies the applicability of the transformer architecture target detection algorithm for casting defect detection tasks and provides new ideas for detecting other similar application scenarios.