Developing a Portable Fluorescence Imaging Device for Fish Freshness Detection.

Rapid detection of fish freshness is of vital importance to ensuring the safety of aquatic product consumption. Currently, the widely used optical detecting methods of fish freshness are faced with multiple challenges, including low detecting efficiency, high cost, large size and low integration of detecting equipment. This research aims to address these issues by developing a low-cost portable fluorescence imaging device for rapid fish freshness detection. The developed device employs ultraviolet-light-emitting diode (UV-LED) lamp beads (365 nm, 10 W) as excitation light sources, and a low-cost field programmable gate array (FPGA) board (model: ZYNQ XC7Z020) as the master control unit. The fluorescence images captured by a complementary metal oxide semiconductor (CMOS) camera are processed by the YOLOv4-Tiny model embedded in FPGA to obtain the ultimate results of fish freshness. The circuit for the YOLOv4-Tiny model is optimized to make full use of FPGA resources and to increase computing efficiency. The performance of the device is evaluated by using grass carp fillets as the research object. The average accuracy of freshness detection reaches up to 97.10%. Moreover, the detection time of below 1 s per sample and the overall power consumption of 47.1 W (including 42.4 W light source power consumption) indicate that the device has good real-time performance and low power consumption. The research provides a potential tool for fish freshness evaluation in a low-cost and rapid manner.

Research on duck egg recognition algorithm based on improved YOLOv4.

1. The following study addressed the problem of small duck eggs as challenging to detect and identify for pick up in complex free-range duck farm environments. It introduces improvements to the YOLOv4 convolutional neural network target detection algorithm, based on the working conditions of egg-picking robots.2. Specifically, one scale of anchor boxes was removed from the prediction network, and a duck egg labelling dataset was established to make the improved algorithm YOLOv4-ours better match the working state of egg-picking robots and enhance detection performance.3. Through multiple comparative experiments, the YOLOv4-ours object detection algorithm exhibited superior overall performance, achieving a precision of 98.85%, recall of 96.67%, and an average precision of 98.60% and F1 score increased to 97%. Compared to the original YOLOv4 model, these improvements represented increases of 1.89%, 3.41%, 1.32%, and 1.04%, respectively. Furthermore, detection time was reduced from 0.26 seconds per image to 0.20 seconds.4. The enhanced model accurately detected duck eggs in free-range duck housing, effectively meeting the real-time egg identification and picking requirements.

Automatic Detection of Meniscus Tears Using Backbone Convolutional Neural Networks on Knee MRI.

BACKGROUND: Timely diagnosis of meniscus injuries is key for preventing knee joint dysfunction and improving patient outcomes because it decreases morbidity and facilitates treatment planning. PURPOSE: To train and evaluate a deep learning model for automated detection of meniscus tears on knee magnetic resonance imaging (MRI). STUDY TYPE: Bicentric retrospective study. SUBJECTS: In total, 584 knee MRI studies, divided among training (n = 234), testing (n = 200), and external validation (n = 150) data sets, were used in this study. The public data set MRNet was used as a second external validation data set to evaluate the performance of the model. SEQUENCE: A 3 T, coronal, and sagittal images from T1-weighted proton density (PD) fast spin-echo (FSE) with fat saturation and T2-weighted FSE with fat saturation sequences. ASSESSMENT: The detection system for meniscus tear was based on the improved YOLOv4 model with Darknet-53 as the backbone. The performance of the model was also compared with that of three radiologists of varying levels of experience. The determination of the presence of a meniscus tear from surgery reports was used as the ground truth for the images. STATISTICAL TESTS: Sensitivity, specificity, prevalence, positive predictive value, negative predictive value, accuracy, and receiver operating characteristic curve were used to evaluate the performance of the detection model. Two-way analysis of variance, Wilcoxon signed-rank test, and Tukey's multiple tests were used to evaluate differences in performance between the model and radiologists. RESULTS: The overall accuracies for detecting meniscus tears using our model on the internal testing, internal validation, and external validation data sets were 95.4%, 95.8%, and 78.8%, respectively. One radiologist had significantly lower performance than our model in detecting meniscal tears (accuracy: 0.9025 ± 0.093 vs. 0.9580 ± 0.025). DATA CONCLUSION: The proposed model had high sensitivity, specificity, and accuracy for detecting meniscus tears on knee MRIs. EVIDENCE LEVEL: 3 TECHNICAL EFFICACY: Stage 2.

Tile-based microscopic image processing for malaria screening using a deep learning approach.

BACKGROUND: Manual microscopic examination remains the golden standard for malaria diagnosis. But it is laborious, and pathologists with experience are needed for accurate diagnosis. The need for computer-aided diagnosis methods is driven by the enormous workload and difficulties associated with manual microscopy based examination. While the importance of computer-aided diagnosis is increasing at an enormous pace, fostered by the advancement of deep learning algorithms, there are still challenges in detecting small objects such as malaria parasites in microscopic images of blood films. The state-of-the-art (SOTA) deep learning-based object detection models are inefficient in detecting small objects accurately because they are underrepresented on benchmark datasets. The performance of these models is affected by the loss of detailed spatial information due to in-network feature map downscaling. This is due to the fact that the SOTA models cannot directly process high-resolution images due to their low-resolution network input layer. METHODS: In this study, an efficient and robust tile-based image processing method is proposed to enhance the performance of malaria parasites detection SOTA models. Three variants of YOLOV4-based object detectors are adopted considering their detection accuracy and speed. These models were trained using tiles generated from 1780 high-resolution P. falciparum-infected thick smear microscopic images. The tiling of high-resolution images improves the performance of the object detection models. The detection accuracy and the generalization capability of these models have been evaluated using three datasets acquired from different regions. RESULTS: The best-performing model using the proposed tile-based approach outperforms the baseline method significantly (Recall, [95.3%] vs [57%] and Average Precision, [87.1%] vs [76%]). Furthermore, the proposed method has outperformed the existing approaches that used different machine learning techniques evaluated on similar datasets. CONCLUSIONS: The experimental results show that the proposed method significantly improves P. falciparum detection from thick smear microscopic images while maintaining real-time detection speed. Furthermore, the proposed method has the potential to assist and reduce the workload of laboratory technicians in malaria-endemic remote areas of developing countries where there is a critical skill gap and a shortage of experts.

Detection of pulpal calcifications on bite-wing radiographs using deep learning.

OBJECTIVES: Pulpal calcifications are discrete hard calcified masses of varying sizes in the dental pulp cavity. This study is aimed at measuring the performance of the YOLOv4 deep learning algorithm to automatically determine whether there is calcification in the pulp chambers in bite-wing radiographs. MATERIALS AND METHODS: In this study, 2000 bite-wing radiographs were collected from the faculty database. The oral radiologists labeled the pulp chambers on the radiographs as "Present" and "Absent" according to whether there was calcification. The data were randomly divided into 80% training, 10% validation, and 10% testing. The weight file for pulpal calcification was obtained by training the YOLOv4 algorithm with the transfer learning method. Using the weights obtained, pulp chambers and calcifications were automatically detected on the test radiographs that the algorithm had never seen. Two oral radiologists evaluated the test results, and performance criteria were calculated. RESULTS: The results obtained on the test data were evaluated in two stages: detection of pulp chambers and detection of pulpal calcification. The detection performance of pulp chambers was as follows: recall 86.98%, precision 98.94%, F1-score 91.60%, and accuracy 86.18%. Pulpal calcification "Absent" and "Present" detection performance was as follows: recall 86.39%, precision 85.23%, specificity 97.94%, F1-score 85.49%, and accuracy 96.54%. CONCLUSION: The YOLOv4 algorithm trained with bite-wing radiographs detected pulp chambers and calcification with high success rates. CLINICAL RELEVANCE: Automatic detection of pulpal calcifications with deep learning will be used in clinical practice as a decision support system with high accuracy rates in diagnosing dentists.

A Lightweight Algorithm for Insulator Target Detection and Defect Identification.

The accuracy of insulators and their defect identification by UAVs (unmanned aerial vehicles) in transmission-line inspection needs to be further improved, and the model size of the detection algorithm is significantly reduced to make it more suitable for edge-end deployment. In this paper, the algorithm uses a lightweight GhostNet module to reconstruct the backbone feature extraction network of the YOLOv4 model and employs depthwise separable convolution in the feature fusion layer. The model is lighter on the premise of ensuring the effect of image information extraction. Meanwhile, the ECA-Net channel attention mechanism is embedded into the feature extraction layer and PANet (Path Aggregation Network) to improve the recognition accuracy of the model for small targets. The experimental results show that the size of the improved model is reduced from 244 MB to 42 MB, which is only 17.3% of the original model. At the same time, the mAp of the improved model is 0.77% higher than that of the original model, reaching 95.4%. Moreover, the mAP compared with YOLOv5-s and YOLOX-s, respectively, is improved by 1.98% and 1.29%. Finally, the improved model is deployed into Jetson Xavier NX and run at a speed of 8.8 FPS, which is 4.3 FPS faster than the original model.

Lightweight Helmet Detection Algorithm Using an Improved YOLOv4.

Safety helmet wearing plays a major role in protecting the safety of workers in industry and construction, so a real-time helmet wearing detection technology is very necessary. This paper proposes an improved YOLOv4 algorithm to achieve real-time and efficient safety helmet wearing detection. The improved YOLOv4 algorithm adopts a lightweight network PP-LCNet as the backbone network and uses deepwise separable convolution to decrease the model parameters. Besides, the coordinate attention mechanism module is embedded in the three output feature layers of the backbone network to enhance the feature information, and an improved feature fusion structure is designed to fuse the target information. In terms of the loss function, we use a new SIoU loss function that fuses directional information to increase detection precision. The experimental findings demonstrate that the improved YOLOv4 algorithm achieves an accuracy of 92.98%, a model size of 41.88 M, and a detection speed of 43.23 pictures/s. Compared with the original YOLOv4, the accuracy increases by 0.52%, the model size decreases by about 83%, and the detection speed increases by 88%. Compared with other existing methods, it performs better in terms of precision and speed.

Every Vessel Counts: Neural Network Based Maritime Traffic Counting System.

Monitoring and counting maritime traffic is important for efficient port operations and comprehensive maritime research. However, conventional systems such as the Automatic Identification System (AIS) and Vessel Traffic Services (VTS) often do not provide comprehensive data, especially for the diverse maritime traffic in Mediterranean ports. The paper proposes a real-time vessel counting system using land-based cameras is proposed for maritime traffic monitoring in ports, such as the Port of Split, Croatia. The system consists of a YOLOv4 Convolutional Neural Network (NN), trained and validated on the new SPSCD dataset, that classifies the vessels into 12 categories. Further, the Kalman tracker with Hungarian Assignment (HA) algorithm is used as a multi-target tracker. A stability assessment is proposed to complement the tracking algorithm to reduce false positives by unwanted objects (non-vessels). The evaluation results show that the system has an average counting accuracy of 97.76% and an average processing speed of 31.78 frames per second, highlighting its speed, robustness, and effectiveness. In addition, the proposed system captured 386% more maritime traffic data than conventional AIS systems, highlighting its immense potential for supporting comprehensive maritime research.

VV-YOLO: A Vehicle View Object Detection Model Based on Improved YOLOv4.

Vehicle view object detection technology is the key to the environment perception modules of autonomous vehicles, which is crucial for driving safety. In view of the characteristics of complex scenes, such as dim light, occlusion, and long distance, an improved YOLOv4-based vehicle view object detection model, VV-YOLO, is proposed in this paper. The VV-YOLO model adopts the implementation mode based on anchor frames. In the anchor frame clustering, the improved K-means++ algorithm is used to reduce the possibility of instability in anchor frame clustering results caused by the random selection of a cluster center, so that the model can obtain a reasonable original anchor frame. Firstly, the CA-PAN network was designed by adding a coordinate attention mechanism, which was used in the neck network of the VV-YOLO model; the multidimensional modeling of image feature channel relationships was realized; and the extraction effect of complex image features was improved. Secondly, in order to ensure the sufficiency of model training, the loss function of the VV-YOLO model was reconstructed based on the focus function, which alleviated the problem of training imbalance caused by the unbalanced distribution of training data. Finally, the KITTI dataset was selected as the test set to conduct the index quantification experiment. The results showed that the precision and average precision of the VV-YOLO model were 90.68% and 80.01%, respectively, which were 6.88% and 3.44% higher than those of the YOLOv4 model, and the model's calculation time on the same hardware platform did not increase significantly. In addition to testing on the KITTI dataset, we also selected the BDD100K dataset and typical complex traffic scene data collected in the field to conduct a visual comparison test of the results, and then the validity and robustness of the VV-YOLO model were verified.

Waste Detection System Based on Data Augmentation and YOLO_EC.

The problem of waste classification has been a major concern for both the government and society, and whether waste can be effectively classified will affect the sustainable development of human society. To perform fast and efficient detection of waste targets in the sorting process, this paper proposes a data augmentation + YOLO_EC waste detection system. First of all, because of the current shortage of multi-objective waste classification datasets, the heavy workload of human data collection, and the limited improvement of data features by traditional data augmentation methods, DCGAN (deep convolution generative adversarial networks) was optimized by improving the loss function, and an image-generation model was established to realize the generation of multi-objective waste images; secondly, with YOLOv4 (You Only Look Once version 4) as the basic model, EfficientNet is used as the backbone feature extraction network to realize the light weight of the algorithm, and at the same time, the CA (coordinate attention) attention mechanism is introduced to reconstruct the MBConv module to filter out high-quality information and enhance the feature extraction ability of the model. Experimental results show that on the HPU_WASTE dataset, the proposed model outperforms other models in both data augmentation and waste detection.

YOLOv4 with Deformable-Embedding-Transformer Feature Extractor for Exact Object Detection in Aerial Imagery.

The deep learning method for natural-image object detection tasks has made tremendous progress in recent decades. However, due to multiscale targets, complex backgrounds, and high-scale small targets, methods from the field of natural images frequently fail to produce satisfactory results when applied to aerial images. To address these problems, we proposed the DET-YOLO enhancement based on YOLOv4. Initially, we employed a vision transformer to acquire highly effective global information extraction capabilities. In the transformer, we proposed deformable embedding instead of linear embedding and a full convolution feedforward network (FCFN) instead of a feedforward network in order to reduce the feature loss caused by cutting in the embedding process and improve the spatial feature extraction capability. Second, for improved multiscale feature fusion in the neck, we employed a depth direction separable deformable pyramid module (DSDP) rather than a feature pyramid network. Experiments on the DOTA, RSOD, and UCAS-AOD datasets demonstrated that our method's average accuracy (mAP) values reached 0.728, 0.952, and 0.945, respectively, which were comparable to the existing state-of-the-art methods.

Advanced Computer Vision-Based Subsea Gas Leaks Monitoring: A Comparison of Two Approaches.

Recent years have witnessed the increasing risk of subsea gas leaks with the development of offshore gas exploration, which poses a potential threat to human life, corporate assets, and the environment. The optical imaging-based monitoring approach has become widespread in the field of monitoring underwater gas leakage, but the shortcomings of huge labor costs and severe false alarms exist due to related operators' operation and judgment. This study aimed to develop an advanced computer vision-based monitoring approach to achieve automatic and real-time monitoring of underwater gas leaks. A comparison analysis between the Faster Region Convolutional Neural Network (Faster R-CNN) and You Only Look Once version 4 (YOLOv4) was conducted. The results demonstrated that the Faster R-CNN model, developed with an image size of 1280 × 720 and no noise, was optimal for the automatic and real-time monitoring of underwater gas leakage. This optimal model could accurately classify small and large-shape leakage gas plumes from real-world datasets, and locate the area of these underwater gas plumes.

Defect Inspection Using Modified YoloV4 on a Stitched Image of a Spinning Tool.

In Industry 4.0, automation is a critical requirement for mechanical production. This study proposes a computer vision-based method to capture images of rotating tools and detect defects without the need to stop the machine in question. The study uses frontal lighting to capture images of the rotating tools and employs scale-invariant feature transform (SIFT) to identify features of the tool images. Random sample consensus (RANSAC) is then used to obtain homography information, allowing us to stitch the images together. The modified YOLOv4 algorithm is then applied to the stitched image to detect any surface defects on the tool. The entire tool image is divided into multiple patch images, and each patch image is detected separately. The results show that the modified YOLOv4 algorithm has a recall rate of 98.7% and a precision rate of 97.3%, and the defect detection process takes approximately 7.6 s to complete for each stitched image.

A Novel Real-Time Autonomous Crack Inspection System Based on Unmanned Aerial Vehicles.

Traditional methods on crack inspection for large infrastructures require a number of structural health inspection devices and instruments. They usually use the signal changes caused by physical deformations from cracks to detect the cracks, which is time-consuming and cost-ineffective. In this work, we propose a novel real-time crack inspection system based on unmanned aerial vehicles for real-world applications. The proposed system successfully detects and classifies various types of cracks. It can accurately find the crack positions in the world coordinate system. Our detector is based on an improved YOLOv4 with an attention module, which produces 90.02% mean average precision (mAP) and outperforms the YOLOv4-original by 5.23% in terms of mAP. The proposed system is low-cost and lightweight. Moreover, it is not restricted by navigation trajectories. The experimental results demonstrate the robustness and effectiveness of our system in real-world crack inspection tasks.

TSR-YOLO: A Chinese Traffic Sign Recognition Algorithm for Intelligent Vehicles in Complex Scenes.

Recognizing traffic signs is an essential component of intelligent driving systems' environment perception technology. In real-world applications, traffic sign recognition is easily influenced by variables such as light intensity, extreme weather, and distance, which increase the safety risks associated with intelligent vehicles. A Chinese traffic sign detection algorithm based on YOLOv4-tiny is proposed to overcome these challenges. An improved lightweight BECA attention mechanism module was added to the backbone feature extraction network, and an improved dense SPP network was added to the enhanced feature extraction network. A yolo detection layer was added to the detection layer, and k-means++ clustering was used to obtain prior boxes that were better suited for traffic sign detection. The improved algorithm, TSR-YOLO, was tested and assessed with the CCTSDB2021 dataset and showed a detection accuracy of 96.62%, a recall rate of 79.73%, an F-1 Score of 87.37%, and a mAP value of 92.77%, which outperformed the original YOLOv4-tiny network, and its FPS value remained around 81 f/s. Therefore, the proposed method can improve the accuracy of recognizing traffic signs in complex scenarios and can meet the real-time requirements of intelligent vehicles for traffic sign recognition tasks.

An Infusion Containers Detection Method Based on YOLOv4 with Enhanced Image Feature Fusion.

The detection of infusion containers is highly conducive to reducing the workload of medical staff. However, when applied in complex environments, the current detection solutions cannot satisfy the high demands for clinical requirements. In this paper, we address this problem by proposing a novel method for the detection of infusion containers that is based on the conventional method, You Only Look Once version 4 (YOLOv4). First, the coordinate attention module is added after the backbone to improve the perception of direction and location information by the network. Then, we build the cross stage partial-spatial pyramid pooling (CSP-SPP) module to replace the spatial pyramid pooling (SPP) module, which allows the input information features to be reused. In addition, the adaptively spatial feature fusion (ASFF) module is added after the original feature fusion module, path aggregation network (PANet), to facilitate the fusion of feature maps at different scales for more complete feature information. Finally, EIoU is used as a loss function to solve the anchor frame aspect ratio problem, and this improvement allows for more stable and accurate information of the anchor aspect when calculating losses. The experimental results demonstrate the advantages of our method in terms of recall, timeliness, and mean average precision (mAP).

A Study on Object Detection Performance of YOLOv4 for Autonomous Driving of Tram.

Recently, autonomous driving technology has been in the spotlight. However, autonomous driving is still in its infancy in the railway industry. In the case of railways, there are fewer control elements than autonomous driving of cars due to the characteristics of running on railways, but there is a disadvantage in that evasive maneuvers cannot be made in the event of a dangerous situation. In addition, when braking, it cannot be decelerated quickly for the weight of the body and the safety of the passengers. In the case of a tram, one of the railway systems, research has already been conducted on how to generate a profile that plans braking and acceleration as a base technology for autonomous driving, and to find the location coordinates of surrounding objects through object recognition. In pilot research about the tram's automated driving, YOLOv3 was used for object detection to find object coordinates. YOLOv3 is an artificial intelligence model that finds coordinates, sizes, and classes of objects in an image. YOLOv3 is the third upgrade of YOLO, which is one of the most famous object detection technologies based on CNN. YOLO's object detection performance is characterized by ordinary accuracy and fast speed. For this paper, we conducted a study to find out whether the object detection performance required for autonomous trams can be sufficiently implemented with the already developed object detection model. For this experiment, we used the YOLOv4 which is the fourth upgrade of YOLO.

Embedded Sensing System for Recognizing Citrus Flowers Using Cascaded Fusion YOLOv4-CF + FPGA.

Florescence information monitoring is essential for strengthening orchard management activities, such as flower thinning, fruit protection, and pest control. A lightweight object recognition model using cascade fusion YOLOv4-CF is proposed, which recognizes multi-type objects in their natural environments, such as citrus buds, citrus flowers, and gray mold. The proposed model has an excellent representation capability with an improved cascade fusion network and a multi-scale feature fusion block. Moreover, separable deep convolution blocks were employed to enhance object feature information and reduce model computation. Further, channel shuffling was used to address missing recognition in the dense distribution of object groups. Finally, an embedded sensing system for recognizing citrus flowers was designed by quantitatively applying the proposed YOLOv4-CF model to an FPGA platform. The mAP@.5 of citrus buds, citrus flowers, and gray mold obtained on the server using the proposed YOLOv4-CF model was 95.03%, and the model size of YOLOv4-CF + FPGA was 5.96 MB, which was 74.57% less than the YOLOv4-CF model. The FPGA side had a frame rate of 30 FPS; thus, the embedded sensing system could meet the demands of florescence information in real-time monitoring.

Multi-Object Detection Method in Construction Machinery Swarm Operations Based on the Improved YOLOv4 Model.

To handle the problem of low detection accuracy and missed detection caused by dense detection objects, overlapping, and occlusions in the scenario of complex construction machinery swarm operations, this paper proposes a multi-object detection method based on the improved YOLOv4 model. Firstly, the K-means algorithm is used to initialize the anchor boxes to improve the learning efficiency of the depth features of construction machinery objects. Then, the pooling operation is replaced with dilated convolution to solve the problem that the pooling layer reduces the resolution of feature maps and causes a high missed detection rate. Finally, focus loss is introduced to optimize the loss function of YOLOv4 to improve the imbalance of positive and negative samples during the model training process. To verify the effectiveness of the above optimizations, the proposed method is verified on the Pytorch platform with a self-build dataset. The experimental results show that the mean average precision(mAP) of the improved YOLOv4 model for multi-object detection of construction machinery can reach 97.03%, which is 2.16% higher than that of the original YOLOv4 detection network. Meanwhile, the detection speed is 31.11 fps, and it is reduced by only 0.59 fps, still meeting the real-time requirements. The research lays a foundation for environment perception of construction machinery swarm operations and promotes the unmanned and intelligent development of construction machinery swarm operations.

MobileYOLO: Real-Time Object Detection Algorithm in Autonomous Driving Scenarios.

Object detection is one of the key tasks in an automatic driving system. Aiming to solve the problem of object detection, which cannot meet the detection speed and detection accuracy at the same time, a real-time object detection algorithm (MobileYOLO) is proposed based on YOLOv4. Firstly, the feature extraction network is replaced by introducing the MobileNetv2 network to reduce the number of model parameters; then, part of the standard convolution is replaced by depthwise separable convolution in PAnet and the head network to further reduce the number of model parameters. Finally, by introducing an improved lightweight channel attention modul-Efficient Channel Attention (ECA)-to improve the feature expression ability during feature fusion. The Single-Stage Headless (SSH) context module is introduced to the small object detection branch to increase the receptive field. The experimental results show that the improved algorithm has an accuracy rate of 90.7% on the KITTI data set. Compared with YOLOv4, the parameters of the proposed MobileYOLO model are reduced by 52.11 M, the model size is reduced to one-fifth, and the detection speed is increased by 70%.