Improved Faster R-CNN Research Articles

Detection of Residual Film on the Field Surface Based on Faster R-CNN Multiscale Feature Fusion

After the residual film recycling machine recovers the film, some small pieces of the film will remain on the surface of the field. To solve the problem of collecting small pieces of film, it is necessary to develop a piece of intelligent picking equipment. The detection of small pieces of film is the first problem to be solved. This study proposes a method of an object detection algorithm fusing multi-scale features (MFFM Faster R-CNN) based on improved Faster R-CNN. Based on the Faster R-CNN model, the feature pyramid network is added to solve the problem of multiscale change of residual film. The convolution block attention module is introduced to enhance the feature extraction ability of the model. The Soft-NMS algorithm is used instead of the NMS algorithm to improve the detection accuracy of the model in the RPN network. The experimental results show that the model is able to effectively detect surface residual film in complex environments, with an AP of 83.45%, F1-score of 0.89, and average detection time of 248.36 ms. The model is compared with SSD and YOLOv5 under the same experimental environment and parameters, and it is found that the model not only ensures high-precision detection but also ensures real-time detection. This lays the theoretical foundation for the subsequent development of field surface residual film intelligent picking equipment.

Aeroengine Blade Surface Defect Detection System Based on Improved Faster RCNN

Aiming at the difficulty of automatic blade detection and the discontinuous defects on the full image, an aeroengine blade surface defect detection system based on improved faster RCNN is designed. Firstly, a dataset of blade surface defects is constructed. To solve the problem that the original faster RCNN is hard to detect tiny defects, RoI align is adopted to replace RoI pooling in the improved faster RCNN and the feature pyramid networks (FPN) combined with ResNet-50 are introduced for feature extraction. To address the issue of discontinuous defects on the full image, the nonmaximum suppression (NMS) algorithm is improved to ensure the continuity of defects. A four-degree-of-freedom (4-DOF) motion platform and an industrial camera are used to collect images of blade surfaces. The detection results generated by the improved faster RCNN are compared with the results of the unimproved method. The experimental results prove that the defect detection system based on the improved faster RCNN can realize automatic defect detection on the blade surface with high accuracy. It also solves the issues of tiny defect detection and discontinuous defects on the full result image of the blade.

MAM Faster R-CNN: Improved Faster R-CNN based on Malformed Attention Module for object detection on X-ray security inspection

X-ray security inspection machine is currently the most widely used security inspection technology in our country. It is widely used in urban rail transit, railways, airports, key venues, logistics delivery and other scenarios. Using artificial intelligence technology to assist front-line security inspectors in X-ray security inspection can effectively reduce problems such as missed reports due to personnel fatigue or inattention. However, in actual scenes, the detection accuracy is not high due to the diversity of item types, the particularity of imaging angles, and the limitations of detection algorithms. In order to solve related problems, we propose MAM Faster R-CNN. First, in order to expand the receptive field of the feature map and effectively extract the regional features of the target object with shape distortion in the feature map, we propose the Malformed Attention Module (MAM). Secondly, the Large Kernel Attention (LKA) block is used to connect the corresponding backbone output feature layer to use the adaptive selection feature of self-attention module to better focus on the effective feature information in the feature map. Finally, for the neck part, we replace feature pyramid network (FPN) with path aggregation network (PAN), and add the Conv-MLP block to the bottom-up feature fusion part on the right side of the PAN network to reduce the loss of some low-level details. In this paper, the Faster R-CNN benchmark model with ResNet50 as the backbone network is used to evaluate our proposed MAM Faster R-CNN model on HiXray and OPIXray datasets, and the results show that it outperforms the SOTA detection method. We do ablation experiments on the HiXray dataset, and the results show that our proposed MAM Faster R-CNN improves about 2.0%, compared to baseline model (Faster R-CNN).

Wafer Surface Defect Detection Based on Background Subtraction and Faster R-CNN.

Concerning the problem that wafer surface defects are easily confused with the background and are difficult to detect, a new detection method for wafer surface defects based on background subtraction and Faster R-CNN is proposed. First, an improved spectral analysis method is proposed to measure the period of the image, and the substructure image can then be obtained on the basis of the period. Then, a local template matching method is adopted to position the substructure image, thereby reconstructing the background image. Then, the interference of the background can be eliminated by an image difference operation. Finally, the difference image is input into an improved Faster R-CNN network for detection. The proposed method has been validated on a self-developed wafer dataset and compared with other detectors. The experimental results show that compared with the original Faster R-CNN, the proposed method increases the mAP effectively by 5.2%, which can meet the requirements of intelligent manufacturing and high detection accuracy.

L-dwarf Detection from SDSS Images using Improved Faster R-CNN

We present a data-driven approach to automatically detect L dwarfs from Sloan Digital Sky Survey (SDSS) images using an improved Faster R-CNN framework based on deep learning. The established L-dwarf automatic detection (LDAD) model distinguishes L dwarfs from other celestial objects and backgrounds in SDSS field images by learning the features of 387 SDSS images containing L dwarfs. Applying the LDAD model to the SDSS images containing 93 labeled L dwarfs in the test set, we successfully detected 83 known L dwarfs with a recall rate of 89.25% for known L dwarfs. Several techniques are implemented in the LDAD model to improve its detection performance for L dwarfs, including the deep residual network and the feature pyramid network. As a result, the LDAD model outperforms the model of the original Faster R-CNN, whose recall rate of known L dwarfs is 80.65% for the same test set. The LDAD model was applied to detect L dwarfs from a larger validation set including 843 labeled L dwarfs, resulting in a recall rate of 94.42% for known L dwarfs. The newly identified candidates include L dwarfs, late M and T dwarfs, which were estimated from color (i − z) and spectral type relation. The contamination rates for the test candidates and validation candidates are 8.60% and 9.27%, respectively. The detection results indicate that our model is effective to search for L dwarfs from astronomical images.

Semi-Supervised Gastrointestinal Stromal Tumor Detection via Self-Training

The clinical diagnosis of gastrointestinal stromal tumors (GISTs) requires time-consuming tumor localization by physicians, while automated detection of GIST can help physicians develop timely treatment plans. Existing GIST detection methods based on fully supervised deep learning require a large amount of labeled data for the model training, but the acquisition of labeled data is often time-consuming and labor-intensive, hindering the optimization of the model. However, the semi-supervised learning method can perform better than the fully supervised learning method with only a small amount of labeled data because of the full use of unlabeled data, which effectively compensates for the lack of labeled data. Therefore, we propose a semi-supervised gastrointestinal stromal tumor (GIST) detection method based on self-training using the new selection criterion to guarantee the quality of pseudo-labels and adding the pseudo-labeled data to the training set together with the labeled data after linear mixing. In addition, we introduce the improved Faster RCNN with the multiscale module and the feature enhancement module (FEM) for semi-supervised GIST detection. The multiscale module and the FEM can better fit the characteristics of GIST and obtain better detection results. The experiment results showed that our approach achieved the best performance on our GIST image dataset with the joint optimization of the self-training framework, the multiscale module, and the FEM.

Infrared Image Target Detection of Substation Electrical Equipment Using an Improved Faster R-CNN

Infrared camera can be used to monitor the condition of substation electrical equipment. Fast and accurate target detection algorithm is the key for infrared intelligent on-line routing inspection. However, the performance of traditional detection algorithm is poor due to the complex background of substation. To solve this problem, this paper proposes a target detection model based on the improved faster region-based convolutional neural networks (Faster R-CNN), which can be used for automatic detection of five kinds of electrical equipment in substations. The feature extraction network of this model is improved based on VGG16 by abandoning some high-level convolutions to accelerate the training and testing speed. Meanwhile, the 1:3 and 3:1 aspect ratio of anchor are added to improve the detection accuracy of elongated equipment. Experiments are performed on an infrared image dataset of substation to detect five types of equipment. The robustness tests of our model are carried out, too. The results show that our model performs well in detection accuracy and speed, achieving a mean detected accuracy of 95.32% and running at 11 frame/second. In addition, our model is robust to noise and lightness, which is suitable to other substations. Comparing to other models, our model has the highest mAP@0.5 of 92.78%.

A High-Precision Detection Method of Apple Leaf Diseases Using Improved Faster R-CNN

Apple leaf diseases seriously affect the sustainable production of apple fruit. Early infection monitoring of apple leaves and timely disease control measures are the key to ensuring the regular growth of apple fruits and achieving a high-efficiency economy. Consequently, disease detection schemes based on computer vision can compensate for the shortcomings of traditional disease detection methods that are inaccurate and time-consuming. Nowadays, to solve the limitations ranging from complex background environments to dense and small characteristics of apple leaf diseases, an improved Faster region-based convolutional neural network (Faster R-CNN) method was proposed. The advanced Res2Net and feature pyramid network architecture were introduced as the feature extraction network for extracting reliable and multi-dimensional features. Furthermore, RoIAlign was also employed to replace RoIPool so that accurate candidate regions will be produced to address the object location. Moreover, soft non-maximum suppression was applied for precise detection performance of apple leaf disease when making inferences to the images. The improved Faster R-CNN structure behaves effectively in the annotated apple leaf disease dataset with an accuracy of 63.1% average precision, which is higher than other object detection methods. The experiments proved that our improved Faster R-CNN method provides a highly precise apple leaf disease recognition method that could be used in real agricultural practice.

Cervical cell classification with deep-learning algorithms.

Cervical cancer is a serious threat to the lives and health of women. The accurate analysis of cervical cell smear images is an important diagnostic basis for cancer identification. However, pathological data are often complex and difficult to analyze accurately because pathology images contain a wide variety of cells. To improve the recognition accuracy of cervical cell smear images, we propose a novel deep-learning model based on the improved Faster R-CNN, shallow feature enhancement networks, and generative adversarial networks. First, we used a global average pooling layer to enhance the robustness of the data feature transformation. Second, we designed a shallow feature enhancement network to improve the localization and recognition of weak cells. Finally, we established a data augmentation network to improve the detection capability of the model. The experimental results demonstrate that our proposed methods are superior to CenterNet, YOLOv5, and Faster R-CNN algorithms in some aspects, such as shorter time consumption, higher recognition precision, and stronger adaptive ability. Its maximum accuracy is 99.81%, and the overall mean average precision is 89.4% for the SIPaKMeD and Herlev datasets. Our method provides a useful reference for cervical cell smear image analysis. The missed diagnosis rate and false diagnosis rate are relatively high for cervical cell smear images of different pathologies and stages. Therefore, our algorithms need to be further improved to achieve a better balance. We will use a hyperspectral microscope to obtain more spectral data of cervical cells and input them into deep-learning models for data processing and classification research. First, we sent training samples of cervical cells into our proposed deep-learning model. Then, we used the proposed model to train eight types of cervical cells. Finally, we utilized the trained classifier to test the untrained samples and obtained the classification results. Fig 1. Deep-learning cervical cell classification framework.

Detection of abnormal chicken droppings based on improved Faster R-CNN

The characteristics of chicken droppings are closely related to the health of chickens. Veterinarians often judge the health of a chicken by looking at whether the chicken poop is normal. At present, the inspection of abnormal chicken droppings in chicken coops relies on manual observation, which is inefficient, accurate varies from person to person, labor-intensive, and has the risk of cross-infection. To achieve efficient, accurate, and intelligent identification of abnormal chicken droppings, an abnormal chicken droppings detection method based on improved Faster Region-based Convolutional Neural Network (Faster R-CNN) was proposed in this study. In the feature extraction network stage, deformable convolution was used and combined with Path Augmentation-Feature Pyramid Network (PA-FPN) to improve the extraction ability of features at different scales. In the Region Proposal Network (RPN) stage, the K-means++ algorithm was used to cluster the dataset and obtain the Anchor-ratio which is more suitable for the chicken poop object, and the FocalLoss classification loss function was used to improve the classification ability of difficult samples. In the regional convolutional network stage, the region of interest calibration algorithm was used instead to obtain more accurate localization information. The experimental results show that the improved Faster R-CNN structure can reach an accuracy of 98.8% for abnormal chicken poop detection, and the average accuracy mean value was improved by 27.8%. The results can provide a key core technology support for establishing an efficient abnormal chicken droppings online detection system. Keywords: abnormal chicken droppings, Faster R-CNN, detection, non-destructive monitoring, PA-FPN DOI: 10.25165/j.ijabe.20231601.7732 Citation: Zhu J H, Cui Z H, Wang H Y, Zhou M, Sun X Q. Detection of abnormal chicken droppings based on improved Faster R-CNN. Int J Agric & Biol Eng, 2023; 16(1): 243–249.

In-Situ Detection Method of Jellyfish Based on Improved Faster R-CNN and FP16

In-Situ Detection Method of Jellyfish Based on Improved Faster R-CNN and FP16

A Novel Pressure Relief Hole Recognition Method of Drilling Robot Based on SinGAN and Improved Faster R-CNN

The drilling robot is the key equipment for pressure relief in rockburst mines, and the accurate recognition of a pressure relief hole is the premise for optimizing the layout of pressure relief holes and intelligent drilling. In view of this, a pressure relief hole recognition method for a drilling robot, based on single-image generative adversarial network (SinGAN) and improved faster region convolution neural network (Faster R-CNN), is proposed. Aiming at the problem of insufficient sample generation diversity and poor performance of the traditional SinGAN model, some improvement measures including image size adjustment, multi-stage training, and dynamically changing iteration times are designed as an improved SinGAN for the generation of pressure relief hole images. In addition, to solve the problem that the traditional depth neural network is not ideal for small-size target recognition, an improved Faster R-CNN based on multi-scale image input and multi-layer feature fusion is designed with the improved SqueezeNet as the framework, and the sample data collected from ground experiments are used for comparative analysis. The results indicate that the improved SinGAN model can improve the diversity of generated images on the premise of ensuring the quality of image samples, and can greatly improve the training speed of the model. The accuracy and recall rate of the improved Faster R-CNN model were able to reach 90.09% and 98.32%, respectively, and the average detection time was 0.19 s, which verifies the superiority of the improved Faster R-CNN model. To further verify the practicability of the proposed method, some field images were collected from the underground rockburst relief area in the coal mine, and a corresponding test analysis was carried out. Compared with three YOLO models, the accuracy and recall rate of improved Faster R-CNN model improved significantly, although the training time and recognition time increased to a certain extent, which proves the feasibility and effectiveness of the proposed method.

Defect Detection of Composite Material Terahertz Image Based on Faster Region-Convolutional Neural Networks

Terahertz (THz) nondestructive testing (NDT) technology has been increasingly applied to the internal defect detection of composite materials. However, the THz image is affected by background noise and power limitation, leading to poor THz image quality. The recognition rate based on traditional machine vision algorithms is not high. The above methods are usually unable to determine surface defects in a timely and accurate manner. In this paper, we propose a method to detect the internal defects of composite materials by using terahertz images based on a faster region-convolutional neural networks (faster R-CNNs) algorithm. Terahertz images showing internal defects in composite materials are first acquired by a terahertz time-domain spectroscopy system. Then the terahertz images are filtered, the blurred images are removed, and the remaining images are enhanced with data and annotated with image defects to create a dataset consistent with the internal defects of the material. On the basis of the above work, an improved faster R-CNN algorithm is proposed in this paper. The network can detect various defects in THz images by changing the backbone network, optimising the training parameters, and improving the prior box algorithm to improve the detection accuracy and efficiency of the network. By taking the commonly used composite sandwich structure as a representative, a sample with typical defects is designed, and the image data are obtained through the test. Comparing the proposed method with other existing network methods, the former proves to have the advantages of a short training time and high detection accuracy. The results show that the mean average precision (mAP) without data enhancement reached 95.50%, and the mAP with data enhancement reached 98.35% and exceeded the error rate of human eye detection (5%). Compared with the original faster R-CNN algorithm of 84.39% and 85.12%, the improvement is 11.11% and 10.23%, respectively, which demonstrates superb feature extraction capability and reduces the occurrence of network errors and omissions.

An improved faster R-CNN algorithm for assisted detection of lung nodules

The morbidity and mortality of lung cancer are increasing rapidly in every country in the world, and pulmonary nodules are the main symptoms of lung cancer in the early stage. If we can diagnose pulmonary nodules in time at the early stage and follow up and treat suspicious patients, we can effectively reduce the incidence of lung cancer. CT (Computed Tomography) has been applied to the screening of many diseases because of its high resolution. Pulmonary nodules show white round shadows in CT images. With the popularity of CT equipment, doctors need to review a large number of imaging results every day. Doctors will misjudge and miss the lesions because of reviewing CT scanning results for a long time. At this time, the method of automatic detection of pulmonary nodules by computer can relieve the pressure of doctors in reviewing CT scan results.Traditional lung nodule detection methods, such as gray threshold method and region growing method, divide the detection process into two steps: extracting candidate regions and eliminating false regions. In addition, the traditional detection method can only operate on a single image, which leads to the inability of this method to detect the batch scanning results in real time. With the continuous development of computer equipment performance and artificial intelligence, the relationship between medical image processing and deep learning is getting closer and closer. In deep learning, object detection methods such as Faster R-CNN、YOLO can complete parallel detection of batch images, and deep structure can fully extract the features of input images. Compared with traditional lung nodule detection methods, it has the characteristics of high efficiency and high precision. Faster R-CNN is a classical and high-precision two-stage object detection method. In this paper, an improved Faster R-CNN model is proposed. On the basis of Faster R-CNN, multi-scale training strategy is used to fully mine the features of different scale spaces and perform path augmentation on lower-dimensional features, which improves the small object detection ability of the model. Through Online Hard Example Mining (OHEM), the loss value is used to quantify the difficulty of candidate region detection, and the training times of the region to be detected are adaptively adjusted. Make full use of prior information to customize the size and proportion of preset boundary anchor boxes. Using deformable convolution to improve the visual field to enhance the global features and enhance the ability to extract the feature information of pulmonary nodules in the same scale space.The new model was tested on LUNA16 (Lung Nodule Analysis 2016) dataset. The detection precision of the improved Faster R-CNN model for pulmonary nodules increased from 76.4% to 90.7%, and the recall rate increased from 40.1% to 56.8% Compared with the mainstream object detection algorithms YOLOv3 and Cascade R-CNN, the improved model is superior to the above models in every index.

Wafer Surface Defect Detection Based on Feature Enhancement and Predicted Box Aggregation

For wafer surface defect detection, a new method based on improved Faster RCNN is proposed here to solve the problems of missing detection due to small objects and multiple boxes detection due to discontinuous objects. First, focusing on the problem of small objects missing detection, a feature enhancement module (FEM) based on dynamic convolution is proposed to extract high-frequency image features, enrich the semantic information of shallow feature maps, and improve detection performance for small-scale defects. Second, for the multiple boxes detection caused by discontinuous objects, a predicted box aggregation method is proposed to aggregate redundant predicted boxes and fine-tune real predicted boxes to further improve positioning accuracy. Experimental results show that the mean average precision of the proposed method, when validated on a self-developed dataset, reached 87.5%, and the detection speed was 0.26 s per image. The proposed method has a certain engineering application value.

Remote sensing landslide target detection method based on improved Faster R-CNN

To timely detect landslide hazards to start emergency rescue, an improved Faster R-CNN algorithm is proposed for remote sensing image landslide detection. First, the gamma transform and Gaussian filtering methods of image enhancement are used to improve the quality of the images. Second, the effect of batchsize size on the model is eliminated using the group normalization method. Finally, multiscale feature fusion is performed by adding a feature pyramid network structure to optimize the extracted landslide small target features, and then the backbone network is set as deep residual shrinkage network 50 to make the model more focused on information useful for landslide detection. The experimental results show that the improved model improves the accuracy rate as well as the average precision by 8.8% and 8.4%, respectively, compared with the unimproved Faster R-CNN, and compared with the first-stage models, such as you only look once version 4 and single-shot detector, which verify the superiority of the model in our study and can detect landslide targets well.

Research on Laying Hens Feeding Behavior Detection and Model Visualization Based on Convolutional Neural Network

The feeding behavior of laying hens is closely related to their health and welfare status. In large-scale breeding farms, monitoring the feeding behavior of hens can effectively improve production management. However, manual monitoring is not only time-consuming but also reduces the welfare level of breeding staff. In order to realize automatic tracking of the feeding behavior of laying hens in the stacked cage laying houses, a feeding behavior detection network was constructed based on the Faster R-CNN network, which was characterized by the fusion of a 101 layers-deep residual network (ResNet101) and Path Aggregation Network (PAN) for feature extraction, and Intersection over Union (IoU) loss function for bounding box regression. The ablation experiments showed that the improved Faster R-CNN model enhanced precision, recall and F1-score from 84.40%, 72.67% and 0.781 to 90.12%, 79.14%, 0.843, respectively, which could enable the accurate detection of feeding behavior of laying hens. To understand the internal mechanism of the feeding behavior detection model, the convolutional kernel features and the feature maps output by the convolutional layers at each stage of the network were then visualized in an attempt to decipher the mechanisms within the Convolutional Neural Network(CNN) and provide a theoretical basis for optimizing the laying hens’ behavior recognition network.

Railway Catenary Insulator Recognition Based on Improved Faster R-CNN

Railway Catenary Insulator Recognition Based on Improved Faster R-CNN

Detection Method of Marine Floating Garbage based on Improved Faster R-CNN

Traditional marine floating garbage cleaning is implemented manually. Workers have to suffer from the poor environment and intensive tasks, which reduce their efficiency. Neural network can help automate the process, and thus free workers from the heavy labor. This paper proposes a neural network network-based method to improve the accuracy of garbage identification and classification, especially for the small-sized garbage. The method combines the improved Faster R-CNN target detection model and Resnet50. According to the characteristics of marine floating garbage, the parameters of fast r-cnn are determined through repeated experiments, which improves the accuracy of small target detection. Experimental results show that the method provides a comprehensive recognition rate of up to 79,36%.

Scheme to implement moving target detection of coastal defense radar in complicated sea conditions

Although the data on a particular complicated sea conditions are available, it is difficult to collect the data on various complicated sea conditions simultaneously. When the sea conditions change, the test results of the detection network based on the data of simple sea conditions may be unacceptable. It is proposed that the VGG16, pix2pixHD, and cycleGAN methods should be applied to establish related datasets of different complicated sea conditions. After the unified image quality assessment indicators are determined, it is found that the images generated by the VGG16 network are most in line with the subsequent target detection standards. The real images of complicated sea conditions have the smallest root-mean-square error, the largest peak signal-to-noise ratio, and the best regression coefficient (R2). Meanwhile, the improved Faster R-CNN is introduced for target detection of small sample datasets. First, the ResNet50_FPN module, as the backbone feature extractor, is used to improve the detection performance of small-sized objects. Moreover, because there are many small target objects to be detected, the ROI Align module is preferred, for it is more accurate. Finally, the Softer-NMS algorithm is selected to significantly improve the positioning accuracy through confidence estimation. Compared with some previous Faster R-CNN methods, the accuracy and missed detection rate of the proposed method outperform other networks, with a mean average precision of 85.11%.