Image Feature Extraction Research Articles

Open-Vocabulary Part-Level Detection and Segmentation for Human–Robot Interaction

Object detection and segmentation have made great progress in robotic application missions. However, intelligent agents require fine-grained recognition algorithms rather than object-level and language instructions to enhance the interaction between humans and robots. To improve the robot’s interactivity in the process of the robot response to language instructions, we propose a method for part-level detection and segmentation by exploiting vision language models. In this approach, Swin Transformer is introduced in the image encoder for extracting image features, and FPNs (Feature Pyramid Networks) are modified to better process the features from Swin Transformer. Next, the image decoder is proposed for model aligning between the image features and text embeddings for achieving human–robot interaction via language. Finally, we verify that the text embeddings are impacted by the command of input and that different prompt templates also affect classification. The method proposed in this paper, which is validated on two datasets (PartImagePart and Pascal Part), possesses the ability to understand and execute part-level missions and accurately segments and detects parts compared with existing interactive methods.

Study on the Determination of Flavor Value of Rice Based on Grid Iterative Search Swarm Optimization Support Vector Machine Model and Hyperspectral Imaging.

In the field of rice processing and cultivation, it is crucial to adopt efficient, rapid and user-friendly techniques to detect the flavor values of various rice varieties. The conventional methods for flavor value assessment mainly rely on chemical analysis and technical evaluation, which not only deplete the rice resources but also incur significant time and labor costs. In this study, hyperspectral imaging technology was utilized in combination with an improved Particle Swarm Optimization Support Vector Machine (PSO-SVM) algorithm, i.e., the Grid Iterative Search Particle Swarm Optimization Support Vector Machine (GISPSO-SVM) algorithm, introducing a new non-destructive technique to determine the flavor value of rice. The method captures the hyperspectral feature data of different rice varieties through image acquisition, preprocessing and feature extraction, and then uses these features to train a model using an optimized machine learning algorithm. The results show that the introduction of GIS algorithms in a PSO-optimized SVM is very effective and can improve the parameter finding ability. In terms of flavor value prediction accuracy, the Principal Component Analysis (PCA) combined with the GISPSO-SVM algorithm achieved 96% accuracy, which was higher than the 93% of the Competitive Adaptive Weighted Sampling (CARS) algorithm. And the introduction of the GIS algorithm in different feature selection can improve the accuracy to different degrees. This novel approach helps to evaluate the flavor values of new rice varieties non-destructively and provides a new perspective for future rice flavor value detection methods.

Spindle Detection Based on Elastic Time Window and Spatial Pyramid Pooling.

Sleep spindles have emerged as valuable biomarkers for assessing cognitive abilities and related disorders, underscoring the importance of their detection in clinical research. However, template matching-based algorithms using fixed templates may not be able to fully adapt to spindles of different durations. Moreover, inspired by the multiscale feature extraction of images, the use of multiscale feature extraction methods can be used to better adapt to spindles of different frequencies and durations. Therefore, this study proposes a novel automatic spindle detection algorithm based on elastic time windows and spatial pyramid pooling (SPP) for extracting multiscale features. The algorithm utilizes elastic time windows to segment electroencephalogram (EEG) signals, enabling the extraction of features across multiple scales. This approach accommodates significant variations in spindle duration and polarization positioning during different EEG epochs. Additionally, spatial pyramid pooling is integrated into a depthwise separable convolutional (DSC) network to perform multiscale pooling on the segmented spindle signal features at different scales. Compared with existing template matching algorithms, this algorithm's spindle wave polarization positioning is more consistent with the real situation. Experimental results conducted on the public dataset DREAMS show that the average accuracy of this algorithm reaches 95.75%, with an average negative predictive value (NPV) of 96.55%, indicating its advanced performance. The effectiveness of each module was verified through thorough ablation experiments. More importantly, the algorithm shows strong robustness when faced with changes in different experimental subjects. This feature makes the algorithm more accurate at identifying sleep spindles and is expected to help experts automatically detect spindles in sleep EEG signals, reduce the workload and time of manual detection, and improve efficiency.

A Wind Power Combination Forecasting Method Based on GASF Image Representation and UniFormer

In the field of wind power prediction, traditional methods typically rely on one-dimensional time-series data for feature extraction and prediction. In this study, we propose an innovative short-term wind power forecasting approach using a “visual” 2D image prediction method that effectively utilizes spatial pattern information in time-series data by combining wind power series and related environmental features into a 2D GASF image. Firstly, the wind power data are decomposed using the ICEEMDAN algorithm optimized by the BWO (Beluga Whale Optimization) algorithm, extracting the submodal IMF (Intrinsic Mode Function) components with different frequencies. Then, modal reconstruction is performed on the basis of the permutation entropy value of the IMF components, selecting meteorological features highly correlated with reconstructed components through Spearman correlation analysis for data splicing and superposition before converting them into GASF images. Finally, the GASF images are input into the UniFormer model for wind power sequence prediction. By leveraging wind power data predictions from a coastal wind farm in East China and Sotavento in Spain, this study demonstrates the significant benefits and potential applications of this methodology for precise wind power forecasting. This research combines the advantages of image feature extraction and time-series prediction to offer novel perspectives and tools for predicting renewable energy sources such as wind power.

Dual-Mode Fluorescent/Intelligent Lateral Flow Immunoassay Based on Machine Learning Algorithm for Ultrasensitive Analysis of Chloroacetamide Herbicides.

Given the harmful effect of pesticide residues, it is essential to develop portable and accurate biosensors for the analysis of pesticides in agricultural products. In this paper, we demonstrated a dual-mode fluorescent/intelligent (DM-f/DM-i) lateral flow immunoassay (LFIA) for chloroacetamide herbicides, which utilized horseradish peroxidase-IgG conjugated time-resolved fluorescent nanoparticle probes as both a signal label and amplification tool. With the newly developed LFIA in the DM-f mode, the limits of detection (LODs) were 0.08 ng/mL of acetochlor, 0.29 ng/mL of metolachlor, 0.51 ng/mL of Propisochlor, and 0.13 ng/mL of their mixture. In the DM-i mode, machine learning (ML) algorithms were used for image segmentation, feature extraction, and correlation analysis to obtain multivariate fitted equations, which had high reliability in the regression model with R2 of 0.95 in the range of 2 × 102-2 × 105 pg/mL. Importantly, the practical applicability was successfully validated by determining chloroacetamide herbicides in the corn sample with good recovery rates (85.4 to 109.3%) that correlate well with the regression model. The newly developed dual-mode LFIA with reduced detection time (12 min) holds great potential for pesticide monitoring in equipment-limited environments using a portable test strip reader and laboratory conditions using ML algorithms.

Towards automatic forecasting of lung nodule diameter with tabular data and CT imaging

Objective:This study aims to forecast the progression of lung cancer by estimating the future diameter of lung nodules. Methods:This approach uses as input the tabular data, axial images from tomography scans, and both data types, employing a ResNet50 model for image feature extraction and direct analysis of patient information for tabular data. The data are processed through a neural network before prediction. In the training phase, class weights are assigned based on the rarity of different types of nodules within the dataset, in alignment with nodule management guidelines. Results:Tabular data alone yielded the most accurate results, with a mean absolute deviation of 0.99 mm. For malignant nodules, the best performance, marked by a deviation of 2.82 mm, was achieved using tabular data applying Lung-RADS class weights during training. The tabular data results highlight the influence of using the initial nodule size as an input feature. These results surpass the literature reference of 348-day volume doubling time for malignant nodules. Conclusion:The developed predictive model is optimized for integration into a clinical workflow after detecting, segmenting, and classifying nodules. It provides accurate growth forecasts, establishing a more objective basis for determining follow-up intervals. Significance:With lung cancer’s low survival rates, the capacity for precise nodule growth prediction represents a significant breakthrough. This methodology promises to revolutionize patient care and management, enhancing the chances for early risk assessment and effective intervention.

Detection Method of Manipulator Grasp Pose Based on RGB-D Image

In order to better solve the visual detection problem of manipulator grasping non-cooperative targets, we propose a method of grasp pose detection based on pixel point and feature fusion. By using the improved U2net network as the backbone for feature extraction and feature fusion of the input image, and the grasp prediction layer detects the grasp pose on each pixel. In order to adapt the U2net to grasp pose detection and improve its detection performance, we improve detection speed and control sampling depth by simplifying its network structure, while retaining some shallow features in feature fusion to enhance its feature extraction capability. We introduce depthwise separable convolution in the grasp prediction layer, further fusing the features extracted from the backbone to obtain predictive feature maps with stronger feature expressiveness. FocalLoss is selected as the loss function to solve the problem of unbalanced positive and negative samples in network training. We use the Cornell dataset for training and testing, perform pixel-level labeling on the image, and replace the labels that are not conducive to the actual grasping. This adaptation helps the dataset better suit the network training and testing while meeting the real-world grasping requirements of the manipulator. The evaluation results on image-wise and object-wise are 95.65% and 91.20% respectively, and the detection speed is 0.007 s/frame. We also used the method for actual manipulator grasping experiments. The results show that our method has improved accuracy and speed compared with previous methods, and has strong generalization ability and portability.

AMIKOMNET: Novel Structure for a Deep Learning Model to Enhance COVID-19 Classification Task Performance

Since early 2020, coronavirus has spread extensively throughout the globe. It was first detected in Wuhan, a province in China. Many researchers have proposed various models to solve problems related to COVID-19 detection. As traditional medical approaches take a lot of time to detect the virus and require specific laboratory tests, the adoption of artificial intelligence (AI), including machine learning, might play an important role in handling the problem. A great deal of research has seen the adoption of AI succeed in the early detection of COVID-19 using X-ray images. Unfortunately, the majority of deep learning adoption for COVID-19 detection has the shortcomings of high error detection and high computation costs. In this study, we employed a hybrid model using an auto-encoder (AE) and a convolutional neural network (CNN) (named AMIKOMNET) with a small number of layers and parameters. We implemented an ensemble learning mechanism in the AMIKOMNET model using Adaboost with the aim of reducing error detection in COVID-19 classification tasks. The experimental results for the binary class show that our model achieved high effectiveness, with 96.90% accuracy, 95.06% recall, 94.67% F1-score, and 96.03% precision. The experimental result for the multiclass achieved 95.13% accuracy, 94.93% recall, 95.75% F1-score, and 96.19% precision. The adoption of Adaboost in AMIKOMNET for the binary class increased the effectiveness of the model to 98.45% accuracy, 96.16% recall, 95.70% F1-score, and 96.87% precision. The adoption of Adaboost in AMIKOMNET in the multiclass classification task also saw an increase in performance, with an accuracy of 96.65%, a recall of 94.93%, an F1-score of 95.76%, and a precision of 96.19%. The implementation of AE to handle image feature extraction combined with a CNN used to handle dimensional image feature reduction achieved outstanding performance when compared to previous work using a deep learning platform. Exploiting Adaboost also increased the effectiveness of the AMIKOMNET model in detecting COVID-19.

An IoT vehicle management framework based on optimized license plate recognition

With the continuous development of urban traffic and the increasing number of vehicles, vehicle management has become increasingly crucial. The Harmony-based IoT vehicle management system, leveraging Internet of Things (IoT) technology, offers an effective solution. This paper introduces the concept and principles of the Harmony-based IoT vehicle management system, focusing on optimized license plate recognition. Firstly, the principles and optimization methods of license plate recognition technology are elaborately described, encompassing aspects such as image processing, feature extraction, and pattern recognition. Subsequently, the paper explores the application of advanced YOLOv7 license plate recognition technology in the Harmony-based IoT vehicle management system, incorporating discussions on interlinking with devices like gate control systems.

Latent Diffusion Models with Image-Derived Annotations for Enhanced AI-Assisted Cancer Diagnosis in Histopathology.

Artificial Intelligence (AI)-based image analysis has immense potential to support diagnostic histopathology, including cancer diagnostics. However, developing supervised AI methods requires large-scale annotated datasets. A potentially powerful solution is to augment training data with synthetic data. Latent diffusion models, which can generate high-quality, diverse synthetic images, are promising. However, the most common implementations rely on detailed textual descriptions, which are not generally available in this domain. This work proposes a method that constructs structured textual prompts from automatically extracted image features. We experiment with the PCam dataset, composed of tissue patches only loosely annotated as healthy or cancerous. We show that including image-derived features in the prompt, as opposed to only healthy and cancerous labels, improves the Fréchet Inception Distance (FID) by 88.6. We also show that pathologists find it challenging to detect synthetic images, with a median sensitivity/specificity of 0.55/0.55. Finally, we show that synthetic data effectively train AI models.

Depth Prior-Guided 3D Voxel Feature Fusion for 3D Semantic Estimation from Monocular Videos

Existing 3D semantic scene reconstruction methods utilize the same set of features extracted from deep learning networks for both 3D semantic estimation and geometry reconstruction, ignoring the differing requirements of semantic segmentation and geometry construction tasks. Additionally, current methods allocate 2D image features to all voxels along camera rays during the back-projection process, without accounting for empty or occluded voxels. To address these issues, we propose separating the features for 3D semantic estimation from those for 3D mesh reconstruction. We use a pretrained vision transformer network for image feature extraction and depth priors estimated by a pretrained multi-view stereo-network to guide the allocation of image features within 3D voxels during the back-projection process. The back-projected image features are aggregated within each 3D voxel via averaging, creating coherent voxel features. The resulting 3D feature volume, composed of unified voxel feature vectors, is fed into a 3D CNN with a semantic classification head to produce a 3D semantic volume. This volume can be combined with existing 3D mesh reconstruction networks to produce a 3D semantic mesh. Experimental results on real-world datasets demonstrate that the proposed method significantly increases 3D semantic estimation accuracy.

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique.

Abdominal multi-organ segmentation is one of the most important topics in the field of medical image analysis, and it plays an important role in supporting clinical workflows such as disease diagnosis and treatment planning. In this study, an efficient multi-organ segmentation method called Swin-PSAxialNet based on the nnU-Net architecture is proposed. It was designed specifically for the precise segmentation of 11 abdominal organs in CT images. The proposed network has made the following improvements compared to nnU-Net. Firstly, Space-to-depth (SPD) modules and parameter-shared axial attention (PSAA) feature extraction blocks were introduced, enhancing the capability of 3D image feature extraction. Secondly, a multi-scale image fusion approach was employed to capture detailed information and spatial features, improving the capability of extracting subtle features and edge features. Lastly, a parameter-sharing method was introduced to reduce the model's computational cost and training speed. The proposed network achieves an average Dice coefficient of 0.93342 for the segmentation task involving 11 organs. Experimental results indicate the notable superiority of Swin-PSAxialNet over previous mainstream segmentation methods. The method shows excellent accuracy and low computational costs in segmenting major abdominal organs.

Image Feature Extraction Using Symbolic Data of Cumulative Distribution Functions

Symbolic data analysis is an emerging field in statistics with great potential to become a standard inferential technique. This research introduces a new approach to image feature extraction using the empirical cumulative distribution function (ECDF) and distribution function of distribution values (DFDV) as symbolic data. The main objective is to reduce the dimension of huge pixel data by organizing them into more coherent pixel-intensity distributions. We propose a partitioning method with different breakpoints to capture pixel intensity variations effectively. This results in an ECDF representing the proportion of pixel intensities and a DFDV representing the probability distribution at specific points. The novelty of this approach lies in using ECDF and DFDV as symbolic features, thus summarizing the data and providing a more informative representation of the pixel value distribution, facilitating image classification analysis based on intensity distribution. The experimental results underscore the potential of this method in distinguishing image characteristics among existing image classes. Image features extracted using this approach promise image classification analysis with more informative image representations. In addition, theoretical insights into the properties of DFDV distribution functions are gained.

A High-Precision Identification Method for Maize Leaf Diseases and Pests Based on LFMNet under Complex Backgrounds.

Maize, as one of the most important crops in the world, faces severe challenges from various diseases and pests. The timely and accurate identification of maize leaf diseases and pests is of great significance for ensuring agricultural production. Currently, the identification of maize leaf diseases and pests faces two key challenges: (1) In the actual process of identifying leaf diseases and pests, complex backgrounds can interfere with the identification effect. (2) The subtle features of diseases and pests are difficult to accurately extract. To address these challenges, this study proposes a maize leaf disease and pest identification model called LFMNet. Firstly, the localized multi-scale inverted residual convolutional block (LMSB) is proposed to perform preliminary down-sampling on the image, preserving important feature information for the subsequent extraction of fine disease and pest features in the model structure. Then, the feature localization bottleneck (FLB) is proposed to improve the model's ability to focus on and locate disease and pest characteristics and to reduce interference from complex backgrounds. Subsequently, the multi-hop local-feature fusion architecture (MLFFA) is proposed, which effectively addresses the problem of extracting subtle features by enhancing the extraction and fusion of global and local disease and pest features in images. After training and testing on a dataset containing 19,451 images of maize leaf diseases and pests, the LFMNet model demonstrated excellent performance, with an average identification accuracy of 95.68%, a precision of 95.91%, a recall of 95.78%, and an F1 score of 95.83%. Compared to existing models, it exhibits significant advantages, offering robust technical support for the precise identification of maize diseases and pests.

A privacy-preserving image retrieval scheme with access control based on searchable encryption in media cloud

With the popularity of the media cloud computing industry, individuals and organizations outsource image computation and storage to the media cloud server to reduce the storage burden. Media images usually contain a large amount of private information. To prevent disclosure of privacy of the image owners, media images are encrypted before uploading to the server. However, this operation will greatly limit the utilization of the image for the user, such as content-based image retrieval. We propose an efficient similarity query algorithm with access control based on Bkd-tree in this paper, in which a searchable encryption scheme is designed for similarity image retrieval, and the encrypted image is used to extract image features by a pre-trained CNN model. The Bkd-tree is utilized to generate an index tree for the image features to speed up retrieval and make it faster than linear indexing. Finally, the security performances of the proposed scheme is analyzed and the performance of this scheme is evaluated by experiments. The results show that the security of the image content and image features can be ensured, and it has a shorter retrieval time and higher retrieval efficiency.

Integrating lipid metabolite analysis with MRI-based transformer and radiomics for early and late stage prediction of oral squamous cell carcinoma

BackgroundOral Squamous Cell Carcinoma (OSCC) presents significant diagnostic challenges in its early and late stages. This study aims to utilize preoperative MRI and biochemical indicators of OSCC patients to predict the stage of tumors.MethodsThis study involved 198 patients from two medical centers. A detailed analysis of contrast-enhanced T1-weighted (ceT1W) and T2-weighted (T2W) MRI were conducted, integrating these with biochemical indicators for a comprehensive evaluation. Initially, 42 clinical biochemical indicators were selected for consideration. Through univariate analysis and multivariate analysis, only those indicators with p-values less than 0.05 were retained for model development. To extract imaging features, machine learning algorithms in conjunction with Vision Transformer (ViT) techniques were utilized. These features were integrated with biochemical indicators for predictive modeling. The performance of model was evaluated using the Receiver Operating Characteristic (ROC) curve.ResultsAfter rigorously screening biochemical indicators, four key markers were selected for the model: cholesterol, triglyceride, very low-density lipoprotein cholesterol and chloride. The model, developed using radiomics and deep learning for feature extraction from ceT1W and T2W images, showed a lower Area Under the Curve (AUC) of 0.85 in the validation cohort when using these imaging modalities alone. However, integrating these biochemical indicators improved the model’s performance, increasing the validation cohort AUC to 0.87.ConclusionIn this study, the performance of the model significantly improved following multimodal fusion, outperforming the single-modality approach.Clinical relevance statementThis integration of radiomics, ViT models, and lipid metabolite analysis, presents a promising non-invasive technique for predicting the staging of OSCC.

Large-scale parameters framework with large convolutional kernel for encoding visual fMRI activity information.

Visual encoding models often use deep neural networks to describe the brain's visual cortex response to external stimuli. Inspired by biological findings, researchers found that large receptive fields built with large convolutional kernels improve convolutional encoding model performance. Inspired by scaling laws in recent years, this article investigates the performance of large convolutional kernel encoding models on larger parameter scales. This paper proposes a large-scale parameters framework with a sizeable convolutional kernel for encoding visual functional magnetic resonance imaging activity information. The proposed framework consists of three parts: First, the stimulus image feature extraction module is constructed using a large-kernel convolutional network while increasing channel numbers to expand the parameter size of the framework. Second, enlarging the input data during the training stage through the multi-subject fusion module to accommodate the increase in parameters. Third, the voxel mapping module maps from stimulus image features to functional magnetic resonance imaging signals. Compared to sizeable convolutional kernel visual encoding networks with base parameter scale, our visual encoding framework improves by approximately 7% on the Natural Scenes Dataset, the dedicated dataset for the Algonauts 2023 Challenge. We further analyze that our encoding framework made a trade-off between encoding performance and trainability. This paper confirms that expanding parameters in visual coding can bring performance improvements.

Machine Learning for Extraction of Image Features Associated with Progression of Geographic Atrophy

Background: Several studies have investigated various features and models in order to understand the growth and progression of the ocular disease geographic atrophy (GA). Commonly assessed features include age, sex, smoking, alcohol consumption, sedentary lifestyle, hypertension, and diabetes. There have been inconsistencies regarding which features correlate with GA progression. Chief amongst these inconsistencies is whether the investigated features are readily available for analysis across various ophthalmic institutions. Methods:In this study, we focused our attention on the association of fundus autofluorescence (FAF) imaging features and GA progression. Our method included feature extraction using radiomic processes and feature ranking by machine learning incorporating the algorithm XGBoost to determine the best-ranked features. This led to the development of an image-based linear mixed-effects model, which was designed to account for slope change based on within-subject variability and inter-eye correlation. Metrics used to assess the linear mixed-effects model included marginal and conditional R2, Pearson’s correlation coefficient (r), root mean square error (RMSE), mean error (ME), mean absolute error (MAE), mean absolute deviation (MAD), the Akaike Information Criterion (AIC), the Bayesian Information Criterion (BIC), and loglikelihood. Results: We developed a linear mixed-effects model with 15 image-based features. The model results were as follows: R2 = 0.96, r = 0.981, RMSE = 1.32, ME = −7.3 × 10−15, MAE = 0.94, MAD = 0.999, AIC = 2084.93, BIC = 2169.97, and log likelihood = −1022.46. Conclusions: The advantage of our method is that it relies on the inherent properties of the image itself, rather than the availability of clinical or demographic data. Thus, the image features discovered in this study are universally and readily available across the board.

Predictive [18F]-FDG PET/CT-Based Radiogenomics Modelling of Driver Gene Mutations in Non-small Cell Lung Cancer

Rationale and objectivesTo investigate whether [18F]-FDG PET/CT-derived radiomics may correlate with driver gene mutations in non-small cell lung cancer (NSCLC) patients. Materials and MethodsIn this IRB-approved retrospective study, 203 patients with surgically treated NSCLC who underwent subsequent genomic analysis of the primary tumour at our institution between December 2004 and January 2014 were identified. Of those, 128 patients (mean age 62.4±10.8 years; range: 35-84) received preoperative [18F]-FDG PET/CT as part of their initial staging and thus were included in the study. PET and CT image segmentation and feature extraction were performed semi-automatically with an open-source software platform (LIFEx, Version 6.30, lifexsoft.org). Molecular profiles using different next-generation sequencing (NGS) panels were collected from a web-based resource (cBioPortal.ca for Cancer genomics). Two statistical models were then built to evaluate the predictive ability of [18F]-FDG PET/CT-derived radiomics features for driver gene mutations in NSCLC. ResultsMore than half (68/128, 53%) of all tumour samples harboured three or more gene mutations. Overall, 55% of tumour samples demonstrated a mutation in TP53, 26% of samples had alterations in KRAS and 17% in EGFR. Extensive statistical analysis resulted in moderate to good predictive ability. The highest Youden Index for TP53 was achieved using combined PET/CT features (0.70), for KRAS using PET features only (0.57) and for EGFR using CT features only (0.60). ConclusionOur study demonstrated a moderate to good correlation between radiomics features and driver gene mutations in NSCLC, indicating increased predictive ability of genomic profiles using combined [18F]-FDG PET/CT-derived radiomics features.

Multi-Target Recognition of Substation Infrared Image Based on Improved Faster RCNN

Abstract This study presents a multi-target recognition approach for substation infrared images based on enhanced Faster RCNN, which addresses the challenge of identifying several high-voltage electrical equipment in substation infrared images simultaneously. This method uses VGG16 to extract image features of a variety of electrical equipment in infrared images. Generate regional suggestions through the regional suggestion network and adjust the regional suggestions through border regression. ROI Pooling maps regional suggestions of different scales to fixed-size output vectors and sends them to Softmax for classification, and corrects the incorrectly identified parts categories according to the inclusion relationship of the regional suggestions. In the experiment, 27586 infrared photos are chosen to create an infrared data set in the voc207 format. Then, statistical analysis is performed on the recognition outcomes of 5517 infrared images in the test set. Based on the testing data, the upgraded rapid RCNN has a 92.8% recognition accuracy, which is 9.7% higher than that before, and has higher engineering practical value.