Requirements Of Real-time Detection Research Articles

Intelligent Detection of Muskmelon Ripeness in Greenhouse Environment Based on YOLO-RFEW

Accurate detection of muskmelon fruit ripeness is crucial to ensure fruit quality, optimize picking time, and enhance economic benefits. This study proposes an improved lightweight YOLO-RFEW model based on YOLOv8n, aiming to address the challenges of low efficiency in muskmelon fruit ripeness detection and the complexity of deploying a target detection model to a muskmelon picking robot. Firstly, the RFAConv replaces the Conv in the backbone part of YOLOv8n, allowing the network to focus more on regions with significant contributions in feature extraction. Secondly, the feature extraction and fusion capability are enhanced by improving the C2f module into a C2f-FE module based on FasterNet and an Efficient Multi-Scale attention (EMA) mechanism within the lightweight model. Finally, Weighted Intersection over Union (WIoU) is optimized as the loss function to improve target frame prediction capability and enhance target detection accuracy. The experimental results demonstrate that the YOLO-RFEW model achieves high accuracy, with precision, recall, F1 score, and mean Average Precision (mAP) values of 93.16%, 83.22%, 87.91%, and 90.82%, respectively. Moreover, it maintains a lightweight design and high efficiency with a model size of 4.75 MB and an inference time of 1.5 ms. Additionally, in the two types of maturity tests (M-u and M-r), APs of 87.70% and 93.94% are obtained, respectively, by the YOLO-RFEW model. Compared to YOLOv8n, significant improvements in detection accuracy have been achieved while reducing both model size and computational complexity using the proposed approach for muskmelon picking robots’ real-time detection requirements. Furthermore, when compared to lightweight models such as YOLOv3-Tiny, YOLOv4-Tiny, YOLOv5s, YOLOv7-Tiny, YOLOv8s, and YOLOv8n, the YOLO-RFEW model demonstrates superior performance with only 28.55%, 22.42%, 24.50%, 40.56%, 22.12%, and 79.83% of their respective model sizes, respectively, while achieving the highest F1 score and mAP values among these seven models. The feasibility and effectiveness of our improved scheme are verified through comparisons between thermograms generated by YOLOv8n and YOLO-RFEW as well as detection images. In summary, the YOLO-RFEW model not only improves the accuracy rate of muskmelon ripeness detection but also successfully realizes the lightweight and efficient performance, which has important theoretical support and application value in the field of muskmelon picking robot development.

Establishment and validation of an artificial intelligence-based model for real-time detection and classification of colorectal adenoma

Colorectal cancer (CRC) prevention requires early detection and removal of adenomas. We aimed to develop a computational model for real-time detection and classification of colorectal adenoma. Computationally constrained background based on real-time detection, we propose an improved adaptive lightweight ensemble model for real-time detection and classification of adenomas and other polyps. Firstly, we devised an adaptive lightweight network modification and effective training strategy to diminish the computational requirements for real-time detection. Secondly, by integrating the adaptive lightweight YOLOv4 with the single shot multibox detector network, we established the adaptive small object detection ensemble (ASODE) model, which enhances the precision of detecting target polyps without significantly increasing the model's memory footprint. We conducted simulated training using clinical colonoscopy images and videos to validate the method's performance, extracting features from 1148 polyps and employing a confidence threshold of 0.5 to filter out low-confidence sample predictions. Finally, compared to state-of-the-art models, our ASODE model demonstrated superior performance. In the test set, the sensitivity of images and videos reached 87.96% and 92.31%, respectively. Additionally, the ASODE model achieved an accuracy of 92.70% for adenoma detection with a false positive rate of 8.18%. Training results indicate the effectiveness of our method in classifying small polyps. Our model exhibits remarkable performance in real-time detection of colorectal adenomas, serving as a reliable tool for assisting endoscopists.

YOLOv8-RMDA: Lightweight YOLOv8 Network for Early Detection of Small Target Diseases in Tea.

In order to efficiently identify early tea diseases, an improved YOLOv8 lesion detection method is proposed to address the challenges posed by the complex background of tea diseases, difficulty in detecting small lesions, and low recognition rate of similar phenotypic symptoms. This method focuses on detecting tea leaf blight, tea white spot, tea sooty leaf disease, and tea ring spot as the research objects. This paper presents an enhancement to the YOLOv8 network framework by introducing the Receptive Field Concentration-Based Attention Module (RFCBAM) into the backbone network to replace C2f, thereby improving feature extraction capabilities. Additionally, a mixed pooling module (Mixed Pooling SPPF, MixSPPF) is proposed to enhance information blending between features at different levels. In the neck network, the RepGFPN module replaces the C2f module to further enhance feature extraction. The Dynamic Head module is embedded in the detection head part, applying multiple attention mechanisms to improve multi-scale spatial location and multi-task perception capabilities. The inner-IoU loss function is used to replace the original CIoU, improving learning ability for small lesion samples. Furthermore, the AKConv block replaces the traditional convolution Conv block to allow for the arbitrary sampling of targets of various sizes, reducing model parameters and enhancing disease detection. the experimental results using a self-built dataset demonstrate that the enhanced YOLOv8-RMDA exhibits superior detection capabilities in detecting small target disease areas, achieving an average accuracy of 93.04% in identifying early tea lesions. When compared to Faster R-CNN, MobileNetV2, and SSD, the average precision rates of YOLOv5, YOLOv7, and YOLOv8 have shown improvements of 20.41%, 17.92%, 12.18%, 12.18%, 10.85%, 7.32%, and 5.97%, respectively. Additionally, the recall rate (R) has increased by 15.25% compared to the lowest-performing Faster R-CNN model and by 8.15% compared to the top-performing YOLOv8 model. With an FPS of 132, YOLOv8-RMDA meets the requirements for real-time detection, enabling the swift and accurate identification of early tea diseases. This advancement presents a valuable approach for enhancing the ecological tea industry in Yunnan, ensuring its healthy development.

Fast and practical intrusion detection system based on federated learning for VANET

VANET facilitates communication between vehicles and roadside units, thereby enhancing traffic safety and efficiency. However, it also introduces several attack vectors, compromising security and privacy. To enhance the practicality and precision of existing VANET intrusion detection systems, we propose a novel hybrid algorithm named VAN-IDS. This algorithm combines packet analysis and physical feature analysis. Temporal properties of packets are analyzed using Bi-LSTM, while physical attributes of vehicles are evaluated using LightGBM. Predictive outputs from both models are merged using the Dempster–Shafer theory. Data is collected from the F2MD simulation environment, and experiments are conducted to evaluate the efficacy of VAN-IDS. Results show that VAN-IDS achieves an accuracy exceeding 98.5% in detecting DoS and Sybil attacks, surpassing existing VANET IDSs and meeting real-time detection requirements. Federated learning is introduced, with VAN-FED-IDS designed to accelerate model training and updates, while protecting the privacy of the model and dataset. Roadside units (RSUs) serve as edge computing nodes for local model training, while cloud services aggregate models for collaborative training of detection algorithms. In these experiments, the open-source federated learning frameworks Flower and FedTree are used to assess communication overhead and training duration in both single-machine simulation and multi-machine deployment scenarios. This demonstrates the viability of federated learning, which can protect local data privacy, expedite model training and updates within the IDS, and maintain the original model’s detection accuracy.

GDPs-YOLO: an improved YOLOv8s for coal gangue detection

ABSTRACT In response to the issues of low detection accuracy, slow speed, excessively large models, and difficult deployment in existing coal gangue recognition algorithms, a coal gangue target detection network based on an inverted residual structure is proposed. By conducting in-depth research on advanced edge computing networks, DPsP structure and DsP structure have been devised in this paper, while incorporating GhostModule to construct the GDPs-YOLO network within the YOLOv8s. The experimental results demonstrate the superior performance of the GDPs-YOLO network compared to both the baseline network and the control network. In comparison with the YOLOv5 series, YOLOv8 series, and four advanced edge computing networks, an increase in detection accuracy for coal gangue targets by a maximum of 2.5%, 1.6%, and 3.3% is observed, respectively. The model simultaneously exhibits enhanced speed and reduced model size, with a speed increase ranging from 12.5% to 86.85% compared to the control network. The compressibility of the model ranges from 24.07% to 94%. The inference latency measures approximately 2.8 ms, while the image processing speed reaches around 357 images per second, thereby satisfying the requirements for real-time detection.

Research on Surface Defect Detection of Strip Steel Based on Improved YOLOv7.

Surface defect detection of strip steel is an important guarantee for improving the production quality of strip steel. However, due to the diverse types, scales, and texture structures of surface defects on strip steel, as well as the irregular distribution of defects, it is difficult to achieve rapid and accurate detection of strip steel surface defects with existing methods. This article proposes a real-time and high-precision surface defect detection algorithm for strip steel based on YOLOv7. Firstly, Partial Conv is used to replace the conventional convolution blocks of the backbone network to reduce the size of the network model and improve the speed of detection; Secondly, The CA attention mechanism module is added to the ELAN module to enhance the ability of the network to extract detect features and improve the effectiveness of detect detection in complex environments; Finally, The SPD convolution module is introduced at the output end to improve the detection performance of small targets with surface defects on steel. The experimental results on the NEU-DET dataset indicate that the mean average accuracy (mAP@IoU = 0.5) is 80.4%, which is 4.0% higher than the baseline network. The number of parameters is reduced by 8.9%, and the computational load is reduced by 21.9% (GFLOPs). The detection speed reaches 90.9 FPS, which can well meet the requirements of real-time detection.

Steel strip surface defect detection based on multiscale feature sensing and adaptive feature fusion

A surface defect detection method for hot-rolled steel strips was proposed to address the challenges of detecting small target defects, significant differences in morphology, and unclear defect characteristics. This method is based on multiscale feature perception and adaptive feature fusion. First, based on the spatial distribution characteristics of the steel strip image, redundant background interference is removed using automatic gamma correction and Otsu thresholding. Second, based on the characteristics of surface defects in steel strips, this paper proposes TDB-YOLO (YOLO with a small target detection layer), a Bidirectional Feature Pyramid Network (BiFPN), and Double Cross Stage Partial (CSP) Bottleneck with three convolutions (DC3). To detect small object defects, a small target detection layer with a smaller receptive field focuses on fine-grained features, reducing the model’s probability of missed detection. In terms of feature extraction, DC3 enhances the interaction of feature information from different spatial scales, enabling the model to effectively handle features of varying scales. In terms of feature fusion, the BiFPN is used to adaptively fuse deep-level and shallow-level feature information, enhancing the semantic richness of the feature information. Ultimately, the proposed model in this paper achieved an accuracy of 90.3% and a recall rate of 88.0% for surface defects in steel strips. The mean average precision was 90.4%, and the frames per second was 33. The detection performance of this model outperformed those of other detection models, demonstrating its ability to effectively meet the real-time detection requirements of surface defects in industrial scenarios on steel strips.

YOLOv5s-MEE: A YOLOv5-based Algorithm for Abnormal Behavior Detection in Central Control Room

Aiming to quickly and accurately detect abnormal behaviors of workers in central control rooms, such as playing mobile phone and sleeping, an abnormal behavior detection algorithm based on improved YOLOv5 is proposed. The technique uses SRGAN to reconstruct the input image to improve the resolution and enhance the detailed information. Then, the MnasNet is introduced to replace the backbone feature extraction network of the original YOLOv5, which could achieve the lightweight of the model. Moreover, the detection accuracy of the whole network is enhanced by adding the ECA-Net attention mechanism into the feature fusion network structure of YOLOv5 and modifying the loss function as EIOU. The experimental results in the custom dataset show that compared with the original YOLOv5 algorithm, the algorithm proposed in this paper improves thedetection speed to 75.50 frames/s under the condition of high detection accuracy, which meets the requirements of real-time detection. Meanwhile, compared with other mainstream behavior detection algorithms, this algorithm also shows better detection performance.

High-Performance Defect Detection Methods for Real-Time Monitoring of Ceramic Additive Manufacturing Process Based on Small-Scale Datasets

Vat photopolymerization is renowned for its high flexibility, efficiency, and precision in ceramic additive manufacturing. However, due to the impact of random defects during the recoating process, ensuring the yield of finished products is challenging. At present, the industry mainly relies on manual visual inspection to detect defects; this is an inefficient method. To address this limitation, this paper presents a method for ceramic vat photopolymerization defect detection based on a deep learning framework. The framework innovatively adopts a dual-branch object detection approach, where one branch utilizes a fully convolution network to extract the features from fused images and the other branch employs a differential Siamese network to extract the differential information between two consecutive layer images. Through the design of the dual branches, the decoupling of image feature layers and image spatial attention weights is achieved, thereby alleviating the impact of a few abnormal points on training results and playing a crucial role in stabilizing the training process, which is suitable for training on small-scale datasets. Comparative experiments are implemented and the results show that using a Resnet50 backbone for feature extraction and a HED network for the differential Siamese network module yields the best detection performance, with an obtained F1 score of 0.89. Additionally, as a single-stage defect object detector, the model achieves a detection frame rate of 54.01 frames per second, which meets the real-time detection requirements. By monitoring the recoating process in real-time, the manufacturing fluency of industrial equipment can be effectively enhanced, contributing to the improvement of the yield of ceramic additive manufacturing products.

Lightweight Arc Fault Detection Method Based on Adam-Optimized Neural Network and Hardware Feature Algorithm

Arc faults are the main cause of electrical fires according to national fire data statistics. Intensive studies of artificial intelligence-based arc fault detection methods have been carried out and achieved a high detection accuracy. However, the computational complexity of the artificial intelligence-based methods hinders their application for arc fault detection devices. This paper proposes a lightweight arc fault detection method based on the discrimination of a novel feature for lower current distortion conditions and the Adam-optimized BP neural network for higher distortion conditions. The novel feature is the pulse signal number per unit cycle, reflecting the zero-off phenomena of the arc current. Six features, containing the novel feature, are chosen as the inputs of the neural network, reducing the computational complexity. The model achieves a high detection accuracy of 99.27% under various load types recommended by the IEC 62606 standard. Finally, the proposed lightweight method is implemented on hardware based on the STM32 series microcontroller unit. The experimental results show that the average detection accuracy is 98.33%, while the average detection time is 45 ms and the average tripping time is 72–201 ms under six types of loads, which can fulfill the requirements of real-time detection for commercial arc fault detection devices.

Small-Scale Foreign Object Debris Detection Using Deep Learning and Dual Light Modes

The intrusion of foreign objects on airport runways during aircraft takeoff and landing poses a significant safety threat to air transportation. Small-scale Foreign Object Debris (FOD) cannot be ruled out on time by traditional manual inspection, and there is also a potential risk of secondary foreign body intrusion. A deep-learning-based intelligent detection method is proposed to solve the problem of low accuracy and low efficiency of small-scale FOD detection. Firstly, a dual light camera system is utilized for the collection of FOD data. It generates a dual light FOD dataset containing both infrared and visible light images. Subsequently, a multi-attention mechanism and a bidirectional feature pyramid are integrated into the baseline network YOLOv5. This integration prioritizes the extraction of foreign object features and boosts the network’s ability to distinguish FOD from complex backgrounds. Additionally, it enhances the fusion of higher-level features to improve the representation of multi-scale objects. To ensure fast and accurate localization and recognition of targets, the Complete-IoU (CIoU) loss function is used to optimize the bounding boxes’ positions. The experimental results indicate that the proposed model achieves a detection speed of 36.3 frame/s, satisfying real-time detection requirements. The model also attains an average accuracy of 91.1%, which is 7.4% higher than the baseline network. Consequently, this paper verifies the effectiveness and practical utility of our algorithm for the detection of small-scale FOD targets.

A multiscale carotid plaque detection method based on two-stage analysis

To develop a method for accurate identification of multiscale carotid plaques in ultrasound images. We proposed a two-stage carotid plaque detection method based on deep convolutional neural network (SM-YOLO).A series of algorithms such as median filtering, histogram equalization, and Gamma transformation were used to preprocess the dataset to improve image quality. In the first stage of the model construction, a candidate plaque set was built based on the YOLOX_l target detection network, using multiscale image training and multiscale image prediction strategies to accommodate carotid artery plaques of different shapes and sizes. In the second stage, the Histogram of Oriented Gradient (HOG) features and Local Binary Pattern (LBP) features were extracted and fused, and a Support Vector Machine (SVM) classifier was used to screen the candidate plaque set to obtain the final detection results. This model was compared quantitatively and visually with several target detection models (YOLOX_l, SSD, EfficientDet, YOLOV5_l, Faster R-CNN). SM-YOLO achieved a recall of 89.44%, an accuracy of 90.96%, a F1-Score of 90.19%, and an AP of 92.70% on the test set, outperforming other models in all performance indicators and visual effects. The constructed model had a much shorter detection time than the Faster R-CNN model (only one third of that of the latter), thus meeting the requirements of real-time detection. The proposed carotid artery plaque detection method has good performance for accurate identification of carotid plaques in ultrasound images.

A real-time and accurate convolutional neural network for fabric defect detection

As a practical and challenging task, deep learning-based methods have achieved effective results for fabric defect detection, however, most of them mainly target detection accuracy at the expense of detection speed. Therefore, we propose a fabric defect detection method called PEI-YOLOv5. First, Particle Depthwise Convolution (PDConv) is proposed to extract spatial features more efficiently while reducing redundant computations and memory access, reducing model computation and improving detection speed. Second, Enhance-BiFPN(EB) is proposed based on the structure of BiFPN to enhance the attention of spatial and channel feature maps and the fusion of information at different scales. Third, we improve the loss function and propose IN loss, which improves the problem that the original IOU loss is weak in detecting small targets while speeding up the convergence of the model. Finally, five more common types of defects were selected for training in the GuangDong TianChi fabric defect dataset, and using our proposed PEI-YOLOv5 with only 0.2 Giga Floating Point Operations (GFLOPs) increase, the mAP improved by 3.61%, reaching 87.89%. To demonstrate the versatility of PEI-YOLOv5, we additionally evaluated this in the NEU surface defect database, with the mAP of 79.37%. The performance of PEI-YOLOv 5 in these two datasets surpasses the most advanced fabric defect detection methods at present. We deployed the model to the NVIDIA Jetson TX2 embedded development board, and the detection speed reached 31 frames per second (Fps), which can fully meet the speed requirements of real-time detection.

Headland Identification and Ranging Method for Autonomous Agricultural Machines

Headland boundary identification and ranging are the key supporting technologies for the automatic driving of intelligent agricultural machinery, and they are also the basis for controlling operational behaviors such as autonomous turning and machine lifting. The complex, unstructured environments of farmland headlands render traditional image feature extraction methods less accurate and adaptable. This study utilizes deep learning and binocular vision technologies to develop a headland boundary identification and ranging system built upon the existing automatic guided tractor test platform. A headland image annotation dataset was constructed, and the MobileNetV3 network, notable for its compact model structure, was employed to achieve binary classification recognition of farmland and headland images. An improved MV3-DeeplabV3+ image segmentation network model, leveraging an attention mechanism, was constructed, achieving a high mean intersection over union (MIoU) value of 92.08% and enabling fast and accurate detection of headland boundaries. Following the detection of headland boundaries, binocular stereo vision technology was employed to measure the boundary distances. Field experiment results indicate that the system’s average relative errors of distance in ranging at distances of 25 m, 20 m, and 15 m are 6.72%, 4.80%, and 4.35%, respectively. This system is capable of meeting the real-time detection requirements for headland boundaries.

Improved Deep Learning Model for Workpieces of Rectangular Pipeline Surface Defect Detection

This study introduces a novel approach to address challenges in workpiece surface defect identification. It presents an enhanced Single Shot MultiBox Detector model, incorporating attention mechanisms and multi-feature fusion. The research methodology involves carefully curating a dataset from authentic on-site factory production, enabling the training of a model with robust real-world generalization. Leveraging the Single Shot MultiBox Detector model lead to improvements integrating channel and spatial attention mechanisms in the feature extraction network. Diverse feature extraction methods enhance the network’s focus on crucial information, improving its defect detection efficacy. The proposed model achieves a significant Mean Average Precision (mAP) improvement, reaching 99.98% precision, a substantial 3% advancement over existing methodologies. Notably, the proposed model exhibits a tendency for the values of the P-R curves in object detection for each category to approach 1, which allows a better balance between the requirements of real-time detection and precision. Within the threshold range of 0.2 to 1, the model maintains a stable level of precision, consistently remaining between 0.99 and 1. In addition, the average running speed is 2 fps lower compared to other models, and the reduction in detection speed after the model improvement is kept within 1%. The experimental results indicate that the model excels in pixel-level defect identification, which is crucial for precise defect localization. Empirical experiments validate the algorithm’s superior performance. This research represents a pivotal advancement in workpiece surface defect identification, combining technological innovation with practical efficacy.

Integration of ShuffleNet V2 and YOLOv5s Networks for a Lightweight Object Detection Model of Electric Bikes within Elevators

The entry of electric bikes into elevators poses safety risks. This article proposes a lightweight object detection model for edge deployment in elevator environments specifically designed for electric bikes. Based on the YOLOv5s network, the backbone network replaces the original CSPDarknet53 with a lightweight multilayer ShuffleNet V2 convolutional neural network, achieving a lightweight backbone network. Swin Transformer modules are introduced between layers to enhance the feature expression capability of images, and a SimAM attention mechanism is applied at the end layer to further improve the feature extraction capability of the backbone network. In the neck network, lightweight and depth-balanced GSConv and VoV-GSCSP modules replace several Conv and C3 basic convolutional modules, reducing the parameter count while enhancing the cross-scale connection and fusion capabilities of feature maps. The prediction network uses the faster-converging and more accurate EIOU error function as the position loss function for iterative training. This article conducts various lightweighting comparison experiments and ablation experiments on the improved object detection model. The experimental results demonstrate that the proposed object detection model, with a model size of only 2.6 megabytes and 1.1 million parameters, achieves a frame rate of 106 frames per second and a detection accuracy of 95.5%. This represents an 84.8% reduction in computational load compared to the original YOLOv5s model. The model’s volume and parameter count are reduced by 81.0% and 84.3%, respectively, with only a 0.9% decrease in mAP. The improved object detection model proposed in this paper can meet the real-time detection requirements for electric bikes in elevator scenarios, providing a feasible technical solution for its deployment on edge devices within elevators.

Multi-hidden target detection of transmission line based on improved YOLOv5s and its hardware implementation

Aiming at the problems of poor accuracy of insulator defects, bird’s nests and foreign objects detection in transmission lines, and the difficulty of algorithm hardware deployment, this paper proposes an improved YOLOv5s multi-hidden target detection algorithm for transmission lines, firstly, in backbone, the CA attention(Coordinate attention) mechanism is integrated into the C3 module to form the C3CA module, which replaces the C3 module of the sixth and the eighth layers, and enhances the feature fusion capability; secondly, in the neck, the GSConv convolution and VoVGSCSP modules are used to replace the standard convolution and C3 modules to form a BiFPN network, which reduces the floating-point operations of the network; finally, the improved algorithm is deployed into Raspberry Pi and accelerated by OpenVINO to realize the hardware deployment of the algorithm, which is demonstrated by experiments that: the mAP value of the algorithm is comparable to that of YOLOv3, YOLOv5 and YOLOv7 by 4.7%, 1.1%, and 1.2%, respectively. The model size is 14.2MB, and the average time to detect an image in Raspberry Pi is 78.2 milliseconds, which meets the real-time detection requirements.

Application of lightweight YOLOv5 for walnut kernel grade classification and endogenous foreign body detection

The appearance quality grading of walnut kernels is extremely important in the deep processing of walnuts. Foreign body pollution in food is also a challenging problem that has been troubling food companies. Therefore, it is necessary to propose an efficient and non-destructive detection method for walnut kernels and their endogenous foreign bodies. To improve the quality and safety of walnut deep-processed products, this paper proposes an improved detection model based on the original YOLO V5. The improved model achieves a reduction in memory consumption by 38% and computational workload by 34%. Additionally, it increases the average precision of the model by 1.1% and improves CPU speed by 52%. When compared to other lightweight networks, our model demonstrates optimal overall performance. Moreover, our algorithm significantly enhances the precision of detecting small targets and target selection, as compared to the original model.By reducing the input image size of the model, it is able to meet the requirements of real-time detection of walnut kernels and their endogenous foreign bodies on the edge device Raspberry Pi. This provides a technical reference for the non-destructive detection of food quality and its endogenous foreign bodies.

YOLOv5s-MC: Lightweight road target detection network

For the problem of large number of target detection algorithm parameters, a lightweight real-time detection algorithm YOLOv5s-MC based on improved YOLOv5s road scenes is proposed. firstly, CA attention is added to the model to improve the sensitivity of the network to detect targets; secondly, in the feature fusion network, add adaptive weight parameters using AS-Concat structure are added to better fuse the feature information of different layers and improve the detection accuracy of the algorithm ; adding a small target detection layer to improve the detection accuracy of tiny targets; finally introducing Mobilnetv2, a lightweight network, as the overall backbone layer to realize the lightweight requirement of the network; to verify the advantages of the proposed algorithm, experiments were conducted on the kitti dataset. The experimental results show that the proposed algorithm, compared with the original network, improves the average accuracy by 0.2% with 55.8% less parameters and 33.7% less computation, and the detection speed reaches 35 FPS, which meets the requirements of real-time detection and improves the ability of algorithm deployment in weak hardware computing power scenarios to a certain extent.

Detection of the Corn Kernel Breakage Rate Based on an Improved Mask Region-Based Convolutional Neural Network

Real-time knowledge of kernel breakage during corn harvesting plays a significant role in the adjustment of operational parameters of corn kernel harvesters. (1) Transfer learning by initializing the DenseNet121 network with pre-trained weights for training and validating a dataset of corn kernels was adopted. Additionally, the feature extraction capability of DenseNet121 was improved by incorporating the attention mechanism of a Convolutional Block Attention Module (CBAM) and a Feature Pyramid Network (FPN) structure. (2) The quality of intact and broken corn kernels and their pixels were found to be coupled, and a linear regression model was established using the least squares method. The results of the test showed that: (1) The MAPb50 and MAPm50 of the improved Mask Region-based Convolutional Neural Network (RCNN) model were 97.62% and 98.70%, in comparison to the original Mask Region-based Convolutional Neural Network (RCNN) model, which were improved by 0.34% and 0.37%, respectively; the backbone FLOPs and Params were 3.09 GMac and 9.31 M, and the feature extraction time was 206 ms; compared to the original backbone, these were reduced by 3.87 GMac and 17.32 M, respectively. The training of the obtained prediction weights for the detection of a picture of the corn kernel took 76 ms, so compared to the Mask RCNN model, it was reduced by 375 ms; based on the concept of transfer learning, the improved Mask RCNN model converged twice as quickly with the loss function using pre-training weights than the loss function without pre-training weights during training. (2) The coefficients of determination R2 of the two models, when the regression models of the pixels and the quality of intact and broken corn kernels were analyzed, were 0.958 and 0.992, respectively. These findings indicate a strong correlation between the pixel characteristics and the quality of corn kernels. The improved Mask RCNN model was used to segment mask pixels to calculate the corn kernel breakage rate. The verified error between the machine vision and the real breakage rate ranged from −0.72% to 0.65%, and the detection time of the corn kernel breakage rate was only 76 ms, which could meet the requirements for real-time detection. According to the test results, the improved Mask RCNN method had the advantages of a fast detection speed and high accuracy, and can be used as a data basis for adjusting the operation parameters of corn kernel harvesters.