Intelligent deformed small target recognition algorithm in aliased images based on detector multiplexing and Field-of-View shape modulation coding

Small target recognition is a classic challenge in the field of target recognition. In this paper, an improved algorithm based on Yolo V3 is proposed for ship detection in remote sensing images. In order to solve the problem that the input satellite image size is too large, the window sliding segmentation technology is used to cut the large image into several small images; because the detection target only has a single kind of ship, K-means algorithm is used to re cluster anchor Box, to improve the detection accuracy of the algorithm; in view of the small ship target in the ocean background, the multi-level feature extraction method is used to highlight the feature vector of small target to improve the recognition ability of small target. Through the above-mentioned methods, using the data set of Airbus ship detection provided by kaggle, the ship target detection has achieved a better comprehensive accuracy rate, which is higher than the accuracy and recall rate of similar target detection algorithms.

Feature extraction is a crucial step for any automatic target recognition process, especially in the interpretation of synthetic aperture radar (SAR) imagery. In order to obtain distinctive features, this paper proposes a feature fusion algorithm for SAR target recognition based on a stacked autoencoder (SAE). The detailed procedure presented in this paper can be summarized as follows: firstly, 23 baseline features and Three-Patch Local Binary Pattern (TPLBP) features are extracted. These features can describe the global and local aspects of the image with less redundancy and more complementarity, providing richer information for feature fusion. Secondly, an effective feature fusion network is designed. Baseline and TPLBP features are cascaded and fed into a SAE. Then, with an unsupervised learning algorithm, the SAE is pre-trained by greedy layer-wise training method. Capable of feature expression, SAE makes the fused features more distinguishable. Finally, the model is fine-tuned by a softmax classifier and applied to the classification of targets. 10-class SAR targets based on Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset got a classification accuracy up to 95.43%, which verifies the effectiveness of the presented algorithm.

As a popular target detection algorithm, yolov3 has high detection speed and detection accuracy. However, compared with other target detection algorithms, yolov3 has poor performance in small target recognition, with higher missed detection rates and higher false detection rates. In response to the above problems, this paper draws on the idea of adaptive spatial feature fusion (ASFF), and makes full use of the semantic information of high-level features and the fine-grained, edge, and texture features of low-level features to fuse high-level feature maps and shallow feature maps. Secondly, the K-means clustering algorithm is used to generate a more suitable anchor frame, which is conducive to further improving the recognition accuracy of the model, and finally the network structure is further improved. Through training and recognition in the NWPU vhr-10 dataset, the mAP of the improved yolov3 algorithm is 79.89%, and the mAP of the unimproved yolov3 algorithm is 78.26%. After the improvement, the mAP of 1.63% is increased, and the improvement can solve the problem of low target recognition rate of yolov3 to a certain extent.

The positioning function of unmanned aerial vehicles (UAVs) is a challenging and fundamental research topic and is the premise for UAVs to realize autonomous navigation. The disappearance of satellite signals makes it challenging to achieve accurate positioning. Thus, visual positioning algorithms based on computer vision have been proposed in recent years and these algorithms have produced good results. However, these algorithms have relatively simple functions and cannot perceive the environment. Their versatility is poor, and mismatching often occurs, which affects the positioning accuracy. Aiming to address the need for integrated target recognition, target matching, and positioning of UAVs, we propose an algorithm that integrates the target recognition, matching, and positioning functions by combining the single-shot multibox detector (SSD) algorithm with the deep feature matching algorithm. This algorithm is based on the idea of pseudo-Siamese networks and the SSD algorithm, introducing a deep feature matching method to directly calculate the correspondence between two images. The main idea is to use the VGG network trained by the SSD target recognition algorithm to extract deep features, without any special training for feature matching. Finally, by sharing neural network weights, the integrated design of target recognition and image-matching localization algorithms is achieved. Mismatches between the real-time and reference images are addressed by introducing the grid-based motion statistics algorithm to optimize the matching result and improve the correct matching efficiency of the target. The University-Release dataset was used to compare and analyze the performance of the proposed algorithm to verify its superiority and feasibility. The results show that the matching accuracy of the PSiamRML algorithm is generally good and that it significantly compensates for changes in the contrast, scale, brightness, blur, deformation, and so on, apart from improving the stability and robustness. Finally, a matching test scenario with aerial images captured by an S1000 six-rotor UAV served to verify the effectiveness and practicability of the PSiamRML algorithm.

Research on hybrid information recognition algorithm and quality of golf swing

Deep learning has seen significant success in several fields of artificial intelligence research during the last decade. This technique, which arose from prior research on artificial neural networks, has outperformed conventional machine learning algorithms in image and speech recognition, natural language processing, and others. The first wave of deep learning applications in pharmaceutical research appeared in recent years. Its value has expanded beyond bioactivity predictions to address a wide range of drug development challenges. Bioactivity prediction, de novo molecule design, synthesis prediction, and biological image analysis will be addressed as examples.

<para xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> License plate recognition (LPR) algorithms in images or videos are generally composed of the following three processing steps: 1) extraction of a license plate region; 2) segmentation of the plate characters; and 3) recognition of each character. This task is quite challenging due to the diversity of plate formats and the nonuniform outdoor illumination conditions during image acquisition. Therefore, most approaches work only under restricted conditions such as fixed illumination, limited vehicle speed, designated routes, and stationary backgrounds. Numerous techniques have been developed for LPR in still images or video sequences, and the purpose of this paper is to categorize and assess them. Issues such as processing time, computational power, and recognition rate are also addressed, when available. Finally, this paper offers to researchers a link to a public image database to define a common reference point for LPR algorithmic assessment. </para>

In recent years, the vehicle safety detection system is a common information management method of vehicle safety detection in various ports and forts. However, it is generally unable to accurately identify by the system, and still needs manual re-inspection. In this paper, the image algorithm is comprehensively utilized after the functions of automatic identification, display storage and foreign object comparison. A large number of image processing, target recognition, depth learning and other technologies are used to realize the accurate identification of abnormal objects. According to the difference between the normal image and the current image in the database, the vehicle bottom image will be detected for the presence of abnormal objects. From the intelligent point of view, the processing level and accuracy of the detection system can be greatly improved to more than 99.1% and the human intervention and foreign object investment can be reduced to the greatest extent. From the perspective of image processing methods, this paper introduces a new safety detection method of vehicle bottom image data identification.

For modern radar systems, small unmanned aerial vehicles (UAVs) belong to a typical types of targets with ‘low, slow, and small’ characteristics. In complex combat environments, the functional requirements of radar systems are not only limited to achieving stable detection and tracking performance but also to effectively complete the recognition of small UAV targets. In this paper, a multi-dimensional feature fusion framework for small UAV target recognition utilizing a small-sized and low-cost high-resolution radar is proposed, which can fully extract and combine the geometric structure features and the micro-motion features of small UAV targets. For the performance analysis, the echo data of different small UAV targets was measured and collected with a millimeter-wave radar, and the dataset consists of high-resolution range profiles (HRRP) and micro-Doppler time–frequency spectrograms was constructed for training and testing. The effectiveness of the proposed method was demonstrated by a series of comparison experiments, and the overall accuracy of the proposed method can reach 98.5%, which demonstrates that the proposed multi-dimensional feature fusion method can achieve better recognition performance than that of classical algorithms and higher robustness than that of single features for small UAV targets.

Radar target recognition is an important research direction in the field of radar information processing. Low resolution radar ground target classification and recognition still has broad application prospects in modern military and civil fields. Convolutional neural network (CNN) has attracted more and more attention in the field of radar automatic target recognition, because it does not need Feature Engineering and has superior classification performance. The optimization algorithm of neural network is proposed, and the effects of different network structures on the recognition effect are compared, in this paper. The results show that the multi-scale wide residual network multi-target classification algorithm based on optimized auto-encoder has better recognition effect in low resolution radar target recognition.

This article presents a synthetic aperture radar (SAR) imaging algorithm based on a compressed sensing (CS) reconstruction approach, which is suitable for the detection of foreign object debris (FOD) located in a multilayered circular dielectric structure for nondestructive testing (NDT) application. The method proposed considers the refraction model at the boundaries between each two adjacent layers. This method is different from free space as imaging background assumption in previous CS-based SAR imaging applications. In addition, the prior information that the FOD is displayed with a sparse distribution is applied. Therefore, the method proposed could obtain better focus on effectiveness than time-reversal imaging algorithm with the same measurement points. Further, the CST simulations and the experiment were conducted by taking two small metallic targets as FOD embedded in the three-layered circular dielectric structure. The results of simulations and experiment demonstrated that the proposed method has better effect than previous methods.

Microaneurysm is a kind of small targets in color retinal image, and it is an essential work to recognize the small target for the early diagnosis of diabetic retinopathy. This paper proposes an efficient method to accurately recognize microaneurysm. A symmetric extended curvature Gabor wavelet is presented to generate candidate objects, where some novel features are extracted for classification. A kind of statistic features is generated to distinguish between microaneurysm and thin vessels, in terms of the shape similarity of cross-section profiles. Furthermore, the visual attention-based features are proposed to compute local contrast of small targets in complex background. Random undersampling with AdaBoost (RUSBoost) classifier is employed to discriminate true microaneurysm from an overwhelming amount of candidate objects. Experimental results demonstrate that the proposed method achieves significant sensitivity and accuracy on the public datasets, in comparison to the state-of-the-arts.

Single source images do not contain the comprehensive information of the target and the target recognition rate is low. Targeting to these problems, a new target recognition method based on fusing features of the target in Visible (VIS), Middle Wave Infrared (MWIR) and Long Wave Infrared (LWIR) images is proposed. First, typical features of the target in VIS, MWIR and LWIR images are extracted. The fused feature vector is subsequently obtained by feature selection based on Fisher discriminant analysis. Finally, target recognition is realized through Support Vector Machine (SVM). The target recognition performance of the proposed method and five other target recognition algorithms were tested and compared on VIS, MWIR and LWIR images. Experimental results illustrate that the target recognition rate of the proposed algorithm is higher than that of the five other algorithms tested. The proposed algorithm also has high operational efficiency and robustness.

Mass production of high-quality synthetic SAR training imagery is essential for boosting the performance of deep-learning (DL)-based SAR automatic target recognition (ATR) algorithms in an open-world environment. To address this problem, we exploit both the widely used Moving and Stationary Target Acquisition and Recognition (MSTAR) SAR dataset and the Synthetic and Measured Paired Labeled Experiment (SAMPLE) dataset, which consists of selected samples from the MSTAR dataset and their computer-generated synthetic counterparts. A series of data augmentation experiments are carried out. First, the sparsity of the scattering centers of the targets is exploited for new target pose synthesis. Additionally, training data with various clutter backgrounds are synthesized via clutter transfer, so that the neural networks are better prepared to cope with background changes in the test samples. To effectively augment the synthetic SAR imagery in the SAMPLE dataset, a novel contrast-based data augmentation technique is proposed. To improve the robustness of neural networks against out-of-distribution (OOD) samples, the SAR images of ground military vehicles collected by the self-developed MiniSAR system are used as the training data for the adversarial outlier exposure procedure. Simulation results show that the proposed data augmentation methods are effective in improving both the target classification accuracy and the OOD detection performance. The purpose of this work is to establish the foundation for large-scale, open-field implementation of DL-based SAR-ATR systems, which is not only of great value in the sense of theoretical research, but is also potentially meaningful in the aspect of military application.

Research on Image Segmentation Algorithm Based on Orthogonal Nystr&o&m Algorithm in Target Recognition