Recognition Speed Research Articles

Research on multi-source information collaborative anti-interference technology

This paper focuses on addressing the slow recognition speed and tracking deviation issues in anti-infrared operations. It proposes a method that utilizes multi-source information from the infrared seeker and carrier data link to combat interference. The paper analyses existing methods and expands upon them by investigating full-dimensional motion information correlation. The interference recognition effect is compared across different approaches. The paper further simulates and compares the anti-interference effects of various strategies under different interference conditions, considering recognition speed, accuracy rate, and guidance precision. Overall, the paper investigates anti-infrared interference strategies, addresses existing drawbacks, and provides valuable insights for air counter-measures through simulation-based comparisons.

Ghost imaging object recognition based on self-attention mechanism network

A network model based on the self-attention mechanism is proposed to address the difficulties in extracting features from ghost imaging targets, low recognition efficiency, and potential errors. First, a ghost imaging detection system is constructed using a laser, spatial light modulator, bucket detector, etc. The object is illuminated with speckles generated by the spatial light modulator. The detected data are then input into the self-attention mechanism network model for training. Experimental results show that for the handwritten digits in the experimental dataset, the highest accuracy and average accuracy of the self-attention mechanism network are 99.13% and 96.41%, respectively. This experiment demonstrates the potential of using the self-attention mechanism network for target recognition in ghost imaging, improving the speed of target recognition and significantly enhancing the accuracy of recognition.

YOLO v7-CS: A YOLO v7-Based Model for Lightweight Bayberry Target Detection Count

In order to estimate bayberry yield, a lightweight bayberry target detection count model, YOLOv7-CS, based on YOLOv7, was proposed to address the issues of slow detection and recognition speed, as well as low recognition rate, of high-density bayberry targets under complex backgrounds. In this study, 8990 bayberry images were used for experiments. The training set, validation set, and test set were randomly recreated in a ratio of 8:1:1. The new network was developed with SPD-Conv detection head modules to extract features at various scales, to better capture small and indistinct bayberry targets. To improve accuracy and achieve a lightweight design, a CNxP module that replaces the backbone’s ELAN structure is proposed. We propose a global attention mechanism (GAM) in the intermediate layers of the network, to enhance cross-dimensional interactions, and a new pyramid pooling module called SPPFCSPC, to extend the field of perception and improve boundary detection accuracy. Finally, we combine the Wise-IoU function to enhance the network’s ability to identify overlapping and occluded objects. Compared with the SSD, Faster-RCNN, DSSD, and YOLOv7X target detection algorithms, YOLOv7-CS increases mAP 0.5 by 35.52%, 56.74%, 12.36%, and 7.05%. Compared with basic YOLOv7, mAP 0.5 increased from 5.43% to 90.21%, while mAP 0.95 increased from 13.2% to 54.67%. This parameter is reduced by 17.3 m. Ablation experiments further show that the designed module improves the accuracy of bayberry detection, reduces parameter counts, and makes bayberry image detection more accurate and effective.

Diagnosis of cryptocaryoniasis in large yellow croaker (Larimichthys crocea) by real-time object detection based on YOLOv3

With the introduction and deepening of the concept of sustainable aquaculture, the traditional aquaculture practices are gradually being supplemented and even replaced by advanced systems based on new technology. We here present an automated diagnostic method for diagnosis of cryptocaryoniasis in industrial marine aquaculture. It is based on computer image recognition technology targeting the typical clinical disease sign, white skin spots. A total of 800 images of healthy (400) and Cryptocaryon irritans infected (400) large yellow croaker (Larimichthys crocea) were obtained by cameras, and each type of image was enhanced to 1000. Based on the algorithm YOLOv3, the weights of the trained model yolov3.pt. were used to perform transfer learning on the enhanced image data set to establish the diagnosis model YOLOv3 of cryptocaryoniasis of L. crocea. Then, a visual real-time monitoring system for cryptocaryoniasis was developed. The results show that transfer learning could be well-applied to the training of the cryptocaryoniasis detection model. The accuracy of the final model was about 2% higher than that of the source model (average accuracy of YOLOv3 was 92%, recognition speed 36 frames/s). The algorithm YOLOv3 allows effective discrimination and recognition of cryptocaryoniasis in large yellow croaker. The visual real-time monitoring system allows the automatic and accurate diagnosis of cryptocaryoniasis in L. crocea aquaculture. The results illustrate the applicability of artificial intelligence for reduction of manpower expenditure in diagnostic work, shortening of detection time and elevation of accuracy and timeliness of problem recognition.

A lightweight efficient semantic segmentation with encoder-decoder for arc interference in robotic arc welding

Recognizing laser stripes under conditions of arc interference is a persistent challenge faced by linear structured light sensors due to their similarity with noise in morphological characteristics. In this paper, a symmetrical encoder-decoder semantic segmentation model named LSRNet (lightweight stripe recognition network) is proposed that enables real-time detection of laser stripes in environments with strong arc interference. It analyzes the difference between arc and laser stripe from the semantic point of view. Firstly, to facilitate quick and accurate recognition of laser stripes, we designed a Depthwise-separable Factorized Module that is both efficient and scalable with a larger receptive field. Moreover, due to the difficulty in distinguishing laser stripes from arcs in a local context, a Multi-scale Depthwise-separable Factorized Module is designed to capture more context information. Secondly, the Unified Attention Fusion Module is used to enhance the feature representation of the laser stripe. Additionally, The combination of DiceLoss(dice coefficient loss) and CELoss(cross-entropy loss) is introduced to optimize the loss, which addresses the pixel imbalance challenge that the pixels of the laser stripe are much less than the background pixels. Finally, based on the images collected in the industrial field, our ArcDataset is created for model training. Experimental results show that the proposed method achieves the highest intersection over union of 88.0% in laser stripe segmentation and a recognition speed of 101.3 FPS(frames per second).

Research on Lightweight-Based Algorithm for Detecting Distracted Driving Behaviour

In order to solve the existing distracted driving behaviour detection algorithms’ problems such as low recognition accuracy, high leakage rate, high false recognition rate, poor real-time performance, etc., and to achieve high-precision real-time detection of common distracted driving behaviours (mobile phone use, smoking, drinking), this paper proposes a driver distracted driving behaviour recognition algorithm based on YOLOv5. Firstly, to address the problem of poor real-time identification, the computational and parametric quantities of the network are reduced by introducing a lightweight network, Ghostnet. Secondly, the use of GSConv reduces the complexity of the algorithm and ensures that there is a balance between the recognition speed and accuracy of the algorithm. Then, for the problem of missed and misidentified cigarettes during the detection process, the Soft-NMS algorithm is used to reduce the problems of missed and false detection of cigarettes without changing the computational complexity. Finally, in order to better detect the target of interest, the CBAM is utilised to enhance the algorithm’s attention to the target of interest. The experiments show that on the homemade distracted driving behaviour dataset, the improved YOLOv5 model improves the mAP@0.5 of the YOLOv5s by 1.5 percentage points, while the computational volume is reduced by 7.6 GFLOPs, which improves the accuracy of distracted driving behaviour recognition and ensures the real-time performance of the detection speed.

A CNN-SVM Study Based on the Fusion of Spectrogram and Thermal Imaging Heterogeneous Features for Pig Cough Recognition in Field Situation

Accurate identification of pig cough is essential for comprehensive monitoring and diagnosis of the respiratory health status of pigs. It contributes to stress-free animal health management, reduces pig mortality and improves the economics of farming. Creating a representative multisource signal signature of pig cough is a critical step in achieving automatic recognition of pig cough. For this reason, in this paper, we propose a feature fusion classification method that combines the spectrogram deep features and thermal image deep features to be fed into a support vector machine (SVM) classifier to accomplish cough classification. First, we use a time–frequency transformation algorithm to convert a one-dimensional cough sound signal into a two-dimensional acoustic spectrogram. Then, the corresponding heterogeneous deep features are extracted from the cough spectrogram and thermal image by fine-tuning Lenet-5 and a customized CoughRNet shallow convolutional neural network. Finally, we employ an early fusion technique to align and splice the extracted heterogeneous deep features and feed them into an SVM for the automatic classification task of pig cough. Our study evaluates the classification performance, recognition speed and model size of the proposed deep feature fusion classification network with satisfactory results. Experimental results show that the method achieves 99.77% accuracy in pig cough recognition. This further demonstrates the effectiveness of combining abstract heterogeneous sound and thermal image deep features as a method for automated detection of pig respiratory health.

S2F-YOLO: An Optimized Object Detection Technique for Improving Fish Classification

<p>The current emergence of deep learning has enabled state-of-the-art approaches to achieve a major breakthrough in various fields such as object detection. However, the popular object detection algorithms like YOLOv3, YOLOv4 and YOLOv5 are computationally inefficient and need to consume a lot of computing resources. The experimental results on our fish datasets show that YOLOv5x has a great performance at accuracy which the best mean average precision (mAP) can reach 90.07% and YOLOv5s is conspicuous in recognition speed compared to other models. In this paper, a lighter object detection model based on YOLOv5(Referred to as S2F-YOLO) is proposed to overcome these deficiencies. Under the premise of ensuring a small loss of accuracy, the object recognition speed is greatly accelerated. The S2F-YOLO is applied to commercial fish species detection and the other popular algorithms comparison, we obtained incredible results when the mAP is 2.24% lower than that of YOLOv5x, the FPS reaches 216M, which is nearly half faster than YOLOv5s. When compared with other detectors, our algorithm also shows better overall performance, which is more suitable for actual applications.</p> <p> </p>

A lightweight speech recognition method with target-swap knowledge distillation for Mandarin air traffic control communications

Miscommunications between air traffic controllers (ATCOs) and pilots in air traffic control (ATC) may lead to catastrophic aviation accidents. Thanks to advances in speech and language processing, automatic speech recognition (ASR) is an appealing approach to prevent misunderstandings. To allow ATCOs and pilots sufficient time to respond instantly and effectively, the ASR systems for ATC must have both superior recognition performance and low transcription latency. However, most existing ASR works for ATC are primarily concerned with recognition performance while paying little attention to recognition speed, which motivates the research in this article. To address this issue, this article introduces knowledge distillation into the ASR for Mandarin ATC communications to enhance the generalization performance of the light model. Specifically, we propose a simple yet effective lightweight strategy, named Target-Swap Knowledge Distillation (TSKD), which swaps the logit output of the teacher and student models for the target class. It can mitigate the potential overconfidence of the teacher model regarding the target class and enable the student model to concentrate on the distillation of knowledge from non-target classes. Extensive experiments are conducted to demonstrate the effectiveness of the proposed TSKD in homogeneous and heterogeneous architectures. The experimental results reveal that the generated lightweight ASR model achieves a balance between recognition accuracy and transcription latency.

Skin lesion recognition via global-local attention and dual-branch input network

Owing to the deficiency of training data, the variety of skin lesion shapes for different patients, inter-class similarity, and intra-class variation, the recognition accuracy and speed in skin lesion recognition based on deep learning remain challenging. To solve the above issues, we propose a Dual-Branch and Global-Local Attention network based on ResNet50 (DGLA-ResNet50) to reduce model parameters and improve identification accuracy. For inter-class and intra-class problems, a global-local attention mechanism is designed to obtain the dependency information of query points in horizontal and vertical directions in turn for obtaining the global information indirectly. And we choose to obtain the local information through multiple convolutions simultaneously. Aiming at insufficient samples, the attention mechanism is lightened from the perspectives of reducing query points and the points associated with them, so as to reduce parameter redundancy. In addition, we present a dual-branch input network to deal with the problem of image variety, in which two branches are used to extract image features with different resolutions for fusion, so as to expand the network receptive field. We evaluated DGLA-ResNet50 on ISIC2018 and ISIC2019. The experimental results on ISIC2018 demonstrate that DGLA-ResNet50 has a recognition accuracy of 90.71%, while the parameters of the model are only 104.2M and the FLOPs value is 15.6G. Compared with the common models, our model obtains significantly better performance. The results indicate that DGLA-ResNet50 can improve the accuracy well while ensuring the lightweight of the model, and can prospectively assist doctors in the rapid diagnosis of skin lesions.

A Metaverse text recognition model based on character-level contrastive learning

Accurate and efficient text recognition can enhance the accuracy and time efficiency of human–computer interaction and information exchange in noise Metaverse scenarios. For example, it can improve the safety of digital twin-based intelligent transportation and the intelligence of Non-Player Characters. Robust features play a vital role in the performance of scene text recognition models in noise Metaverse situations. To extract robust features, and improve the accuracy and time efficiency of scene text recognition, we propose a Character level text recognition model in Metaverse applications, called MetaChara. It contains two main components: a lightweight text feature extraction module (LightFeature), and a robust character recognition module (RobChara). LightFeature leverages the advantage of global feature aggregation in the primitive representation learning network to handle irregular text images.RobChara incorporates the capability of contrastive learning from the momentum contrast method, improving the robustness of feature extraction in MetaChara. It structures a feature queue for organized storage. By optimizing the similarity of intra-character features and maximizing inter-character differences, it makes the model better adapted to scene text recognition tasks in Metaverse. Experiment results demonstrate that MetaChara is light with 29.14 million parameters and time efficient with an average recognition speed of 1.73 s. It also achieves excellent performance in terms of FLoating-point Operations (FLOPs), registering only 59.60 billion times for each operation. MetaChara achieves an average accuracy of 0.969 for character recognition. We present a case study where MetaChara quickly and accurately recognizes scene texts within the context of autonomous driving in the Metaverse. This demonstrates how MetaChara enhances safety and improves time efficiency for intelligent transportation systems.

Improved ShuffleNetV2 for Action Recognition in BPPV Treatment

In clinical examination and repositioning for BPPV(benign paroxysmal positional vertigo), analyzing the head position trajectory at the algorithm level to obtain information on each examination and repositioning posture helps to provide guidance for subsequent treatment, which has important practical value in clinical applications. This paper uses the improved ShuffleNetV2 on the basic the data obtained by the swivel chair for action recognition, and locates the interval where the action occurs. Specific network improvements include: the introduction of the SE channel attention block, which improves the performance of the network with a small amount of parameters and computation; the Hardswish activation function is used instead of ReLU in the original network; by reducing the layers in the network, deleting the second 1*1 convolution in the right branch of the downsampling block, and changing the kernel size of the DW convolution, the network can be lightweight while maximizing the capability of action recognition. The network’s performance has been enhanced, resulting in an accuracy of 98.53% with only 71,444 parameters and 15.76M FLOPs, while maintaining a recognition speed of 97.1 images per second. It achieves a good balance between speed and accuracy, enabling it to effectively accomplish the task of action recognition.

Application of dynamic time warping optimization algorithm in speech recognition of machine translation

Speech recognition is the foundation of human-computer interaction technology and an important aspect of speech signal processing, with broad application prospects. Therefore, it is very necessary to recognize speech. At present, speech recognition has problems such as low recognition rate, slow recognition speed, and severe interference from other factors. This paper studied speech recognition based on dynamic time warping (DTW) algorithm. By introducing speech recognition, the specific steps of speech recognition were understood. Before performing speech recognition, the speech that needs to be recognized needs to be converted into a speech sequence using an acoustic model. Then, the DTW algorithm was used to preprocess speech recognition, mainly by sampling and windowing the speech. After preprocessing, speech feature extraction was carried out. After feature extraction was completed, speech recognition was carried out. Through experiments, it can be found that the recognition rate of speech recognition on the basis of DTW algorithm was very high. In a quiet environment, the recognition rate was above 93.85 %, and the average recognition rate of the 10 selected testers was 95.8 %. In a noisy environment, the recognition rate was above 91.4 %, and the average recognition rate of the 10 selected testers was 93 %. In addition to high recognition rate, DTW based speech recognition also had a very fast speed for vocabulary recognition. Based on the DTW algorithm, speech recognition not only has a high recognition rate, but also has a faster recognition speed.

Exploration on automatic identification algorithm of transmission line mountain fire based on image recognition technology

In recent years, many places have experienced frequent mountain fires, which have become one of the main disasters in the operation of power transmission lines. However, traditional manual inspection and video monitoring methods can only detect a small amount of mountain fires, and require a large amount of manpower and material resources. In this paper, image recognition technology was used to study the automatic identification algorithm of transmission line mountain fires, and image recognition technology was used to denoise the extracted images. After that, feature extraction was performed on the successfully denoised image, and the image was enhanced to improve the clarity of the image and prepare for improving the recognition accuracy of mountain fires. Through experiments, it can be found that using image recognition technology to identify mountain fires not only has high accuracy and recognition speed, but also has a lower error rate compared to using satellite meteorological data. The recognition accuracy of image recognition technology was above 95 %, while the recognition accuracy of using satellite meteorological data was below 92 %.

A lightweight license plate detection algorithm based on deep learning

AbstractLicense plate detection is an important task in Intelligent Transportation Systems (ITS) and has a wide range of applications in vehicle management, traffic control, and public safety. In order to improve the accuracy and speed of mobile recognition, an improved lightweight YOLOv5s model is proposed for license plate detection. First, an improved Stemblock network is used to replace the original Focus layer in the network, which ensures strong feature expression capability and reduces a large number of parameters to lower the computational complexity; then, an improved lightweight network, ShuffleNetv2, is used to replace the backbone network of the YOLOv5s, which makes the model lighter and ensures the detection accuracy at the same time. Then, a feature enhancement module is designed to reduce the information loss caused by the rearrangement of the backbone network channels, which facilitates the information interaction in the feature fusion process; finally, the low‐, medium‐ and high‐level features in the Shufflenetv2 network structure are fused to form the final high‐level output features. Experimental results on the CCPD dataset show that compared to other methods this paper obtains better performance and faster speed in the license plate detection task, in which the average precision mean value reaches 96.6%, and can achieve a detection speed of 43.86 frame/s, and the parameter volume is reduced to 5.07 M.

Research on feature vector construction and classification recognition of typical mine microseismic waveforms

In the realm of mining seismology, the identification of microseismic waveforms is a critical step for enhancing the precision of microseismic event localization. Addressing the complexities and diverse sources of noise in subterranean mining environments, this study has developed a novel methodology for the automated categorization and recognition of characteristic microseismic waveforms. Initially, a comprehensive database for mining-induced microseismic waveforms was established, catering to their non-stationary and nonlinear attributes. Based on the distinct features of different microseismic waveforms, this study introduces an approach for classification and identification that relies on waveform characteristics. A feature selection model, KNN-LOO (K-Nearest Neighbor - Leave-One-Out), was employed to optimize the feature vectors, in addition to the utilization of Principal Component Analysis (PCA) for dimensionality reduction of the feature vectors. Ultimately, an enhanced BT-SVM (Binary Tree-Support Vector Machine) model was developed to accomplish the automated classification and identification of mining-induced microseismic waveforms. Experimental results indicate that, compared to conventional SVM classification methods, the proposed methodology not only exhibits theoretical and mechanistic advancements but also significantly boosts performance in practical applications. Specifically, the average misclassification rate for each category of waveforms is reduced to less than 5%, and the overall accuracy has increased by 20%. This considerably elevates both the accuracy and speed of microseismic waveform classification and recognition, thereby providing valuable insights for monitoring and analyzing microseismic activities within mining operations as well as enhancing the safety protocols for mineral extraction.

Research on road damage recognition and classification based on improved VGG-19

In recent years, methods of road damage detection, recognition and classification have achieved remarkable results, but there are still problems of efficient and accurate damage detection, recognition and classification. In order to solve this problem, this paper proposes a road damage VGG-19 model construction method that can be used for road damage detection. The road damage image is processed by digital image processing technology (DIP), and then combined with the improved VGG-19 network model to study the method of improving the recognition speed and accuracy of VGG-19 road damage model. Based on the performance evaluation index of neural network model, the feasibility of the improved VGG-19 method is verified. The results show that compared with the traditional VGG-19 model, the road damage VGG-19 road damage recognition model proposed in this paper shortens the training time by 79 % and the average test time by 68 %. In the performance evaluation of the neural network model, the comprehensive performance index is improved by 2.4 % compared with the traditional VGG-19 network model. The research is helpful to improve the model performance of VGG-19 road damage identification network model and its fit to road damages.

Aircraft target type recognition technology based on deep learning and structure feature matching

In order to solve the problems with the traditional aircraft target type recognition algorithm, such as difficulty in feature selection, weak generalization ability, slow recognition speed, and low recognition accuracy, this paper put forward a new method that could detect and recognize aircraft targets in aerial images quickly and accurately. The aircraft targets in the images were detected rapidly and located through YOLOv3-tiny, and after image denoising, shadow detection, and positioning, then we used the Sobel operator to calculate the edge gradient of the target; the image of the aircraft target was segmented by using the region growth method, and then the principal component analysis (PCA)was used to obtain the central axis of the aircraft target. The projected distance from the edge contour to the central axis was sampled at equal intervals along the direction of the central axis, and its ratio to the length of the central axis was calculated to construct the feature vector. Finally, the Spearman rank correlation method was used to match the feature vectors to realize the recognition of the aircraft type. Experiments showed that the proposed method had strong adaptability and small computation and could quickly detect and accurately recognize aircraft targets in aerial images.

Online Intention Recognition With Incomplete Information Based on a Weighted Contrastive Predictive Coding Model in Wargame.

The incomplete and imperfect essence of the battlefield situation results in a challenge to the efficiency, stability, and reliability of traditional intention recognition methods. For this problem, we propose a deep learning architecture that consists of a contrastive predictive coding (CPC) model, a variable-length long short-term memory network (LSTM) model, and an attention weight allocator for online intention recognition with incomplete information in wargame (W-CPCLSTM). First, based on the typical characteristics of intelligence data, a CPC model is designed to capture more global structures from limited battlefield information. Then, a variable-length LSTM model is employed to classify the learned representations into predefined intention categories. Next, a weighted approach to the training attention of CPC and LSTM is introduced to allow for the stability of the model. Finally, performance evaluation and application analysis of the proposed model for the online intention recognition task were carried out based on four different degrees of detection information and a perfect situation of ideal conditions in a wargame. Besides, we explored the effect of different lengths of intelligence data on recognition performance and gave application examples of the proposed model to a wargame platform. The simulation results demonstrate that our method not only contributes to the growth of recognition stability, but it also improves recognition accuracy by 7%-11%, 3%-7%, 3%-13%, and 3%-7%, the recognition speed by 6-32x, 4-18x, 13-*x, and 1-6x compared with the traditional LSTM, classical FCN, OctConv, and OctFCN models, respectively, which characterizes it as a promising reference tool for command decision-making.

Multi-layer capsule network with joint dynamic routing for fire recognition

Fire recognition has emerged as a critical concern in the field of fire safety. Deep learning techniques, specifically convolutional neural networks (CNNs), have found widespread application in fire recognition tasks. The capsule network, a higher-level variant of CNN, offers distinct advantages in terms of enhanced recognition accuracy, making it suitable for fire recognition applications. However, the capsule network faces challenges in effectively determining the presence or absence of fire objects due to the idiosyncrasies of its dynamic routing algorithm. To address this issue and enable effective fire recognition, we propose a novel approach that involves a multi-layer capsule network. Within this framework, we introduce a joint dynamic routing algorithm that computes output values during forward propagation within the multi-layer capsule network. Additionally, we present a new loss function and a fully connected auxiliary training layer designed to train the multi-layer capsule networks effectively. Comparative evaluations against conventional CNN architectures and recent state-of-the-art fire recognition methods demonstrate that the enhanced multi-layer capsule network achieves higher test accuracy, even with limited training samples and fewer training iterations. Furthermore, owing to its reduced model parameter scale, the multi-layer capsule network exhibits faster recognition speeds compared to the aforementioned methods.