YOLOv3 Algorithm Research Articles

An Object Detection Model for Paint Surface Detection Based on Improved YOLOv3

To solve the problem of poor performance of the target detection algorithm and false detection in the detection of paint surface defects of office chairs five-star feet, we propose a defect detection method based on the improved YOLOv3 algorithm. Firstly, a new feature fusion structure is designed to reduce the missed detection rate of small targets. Then we used the CIOU loss function to improve the positioning accuracy. At the same time, a parallel version of the k-means++ initialization algorithm (K-means||) is used to optimize and determine the parameters of the a priori anchor so as to improve the matching degree between the a priori anchor and the feature layer. We constructed a dataset of paint surface defects on the five-star feet of office chairs and performed optimization training, and used multiple algorithms and different datasets to conduct comparative experiments to validate the algorithm. The experimental results show that the improved YOLOv3 algorithm is effective in that the average precision on the self-made dataset reaches 88.3%, which is 5.8% higher than the original algorithm. At the same time, it has also been verified based on the Aliyun Tianchi competition aluminum dataset, and the average precision has reached 89.2%. This method realizes the real-time detection of the paint surface defects of the five-star feet of the office chair very well.

An outstanding adaptive multi-feature fusion YOLOv3 algorithm for the small target detection in remote sensing images

An outstanding adaptive multi-feature fusion YOLOv3 algorithm for the small target detection in remote sensing images

Object Detection Algorithm for Surface Defects Based on a Novel YOLOv3 Model

The surface defects of industrial structural parts have the characteristics of a large-scale span and many small objects, so a novel YOLOv3 model, the YOLOv3-ALL algorithm, is proposed in this paper to solve the problem of precise defect detection. The K-means++ algorithm is combined with the intersection-over-union (IoU) and comparison of the prior box for clustering, which improves the clustering effect. The convolutional block attention module (CBAM) is embedded in the network, thus improving the ability of the network to obtain key information in the image. By adding fourth-scale prediction, the detection capability of a YOLOv3 network for small-object defects is greatly improved. A loss function is designed, which adds the generalized intersection-over-union (GIoU) loss combined with focal loss to solve the problems of L2 loss and class imbalance in samples. Experiments regarding contour-defect detection for stamping parts show that the mean average precision (mAP) of the YOLOV3-ALL algorithm reaches 75.05% in defect detection, which is 25.16% higher than that of the YOLOv3 algorithm. The average detection time is 39 ms/sheet. This proves that the YOLOv3-ALL algorithm has good real-time detection efficiency and high detection accuracy.

Material identification of construction machinery based on multisource sensor information fusion

In order to improve the recognition accuracy of construction machinery and equipment and materials in low contrast scenes, a construction machinery material recognition algorithm based on multisource sensor information fusion is proposed. In the paper, the millimeter wave radar is fused with the camera considering its strong penetration ability in rainy and foggy days and dim environments. Firstly, the spatial coordinates of radar and camera are unified by establishing a spatial fusion model of millimeter wave and camera; then the target acquired by millimeter wave is projected onto the image and the detection frame intersection and ratio model is used to generate the region of interest of the camera; finally, the improved YOLOv2 algorithm is used to identify the region of interest, and in the improved idea, the low-level information is first connected with the high-level information in multilayer depth. At the same time, a multiscale feature pyramid network structure is used to achieve recognition of objects of different scales. This model effectively reduces interference from other feature categories while improving the recognition efficiency of the system. The algorithm can effectively improve the recognition accuracy of mechanical materials in low-contrast scenes, as demonstrated by the validation of different scenes.

Social Distancing Detector Using Deep Learning

The paper presents a methodology for social distancing detection using deep learning to evaluate the distance between people to mitigate the impact of this coronavirus pandemic. The detection tool was developed to alert people to maintain a safe distance with each other by evaluating a video feed. The video frame from the camera was used as input, and the open-source object detection pre-trained model based on the YOLOv3 algorithm was employed for pedestrian detection. Later, the video frame was transformed into top-down view for distance measurement from the 2D plane. The distance between people can be estimated and any noncompliant pair of people in the display will be indicated with a red frame and red line. The proposed method was validated on a pre-recorded video of pedestrians walking on the street. The result shows that the proposed method is able to determine the social distancing measures between multiple people in the video. The developed technique can be further developed as a detection tool in real time application.

Gesture recognition based on modified Yolov5s

With the development of artificial intelligence technology, human–computer interaction technology through gestures, images and voices has gradually become a hot topic for discussion. A modified Yolov5s gesture recognition method is proposed in the field of human–computer cooperation by optimizing the network structure of Yolov5s backbone, CNN is replaced by Ghostbottleneck module to increase the target occlusion recognition rate. Secondly, tensor stitching is added to the output of Ghostbottleneck module for up sampling to strengthen the reuse of image features. Finally, the detection ability of the improved model in the face of complex environment is verified on the self-made data set. Experimental results show that, the mAP@0.5 (mean average precision) of the modified Yolov5s is 94.49%, the AP (average precision) is 94.2%. By comparing the Yolov5s algorithm, Yolov4 algorithm,Yolov3 algorithm and SSD algorithm, the detection accuracy of the modified method has been significantly improved, which can fully meet the application requirements of real-time detection of gesture-controlled robots.

Attention-Enhanced One-Stage Algorithm for Traffic Sign Detection and Recognition

Detection and recognition of traffic signs are the keys to creating advanced driving assistance systems. Making highly precise maps also requires the identification and extraction of such road elements as traffic signs. Traditional detection and recognition methods no longer meet today’s needs, and object recognition algorithms based on deep learning have become the mainstream solution. However, current algorithms have limitations. The recognition speed of one-stage strategy algorithms is fast, but recognition accuracy is not satisfactory especially for small objects. The accuracy of two-stage algorithms is higher, but the recognition speed is extremely slow. This paper solves these problems with a proposed parallel attention convolution module, a channel attention pyramid network, and a loss function diagonal and center point IoU based on the YOLOv3 algorithm. The improved models in this paper are compared with SSD, YOLOv3, and Faster RCNN. Experimental results show that the proposed models have some improvement over the above models: the mAP of the models with PACM, CAFPN, and DCPIoU was 76.02%, compared with SSD300, SSD500, Faster RCNN, and YOLOv3, which had improvements of 9.27%, 6.93%, 2.94, and 5.3%, respectively. And the FPS of the improved model is basically the same as the original YOLOv3, without reducing the real-time performance.

Text-Based Traffic Panels Detection using the Tiny YOLOv3 Algorithm

Text-Based Traffic Panels Detection using the Tiny YOLOv3 Algorithm by Saba Kheirinejad 1,* , Noushin Riahi 2, Reza Azmi 2 1 Center for Ubiquitous Computing, University of Oulu, Oulu, Finland 2 Department of Computer Engineering, Faculty of Engineering, Alzahra University, Tehran, Iran * Author to whom correspondence should be addressed. Journal of Engineering Research and

Identity Card Detection System using YOLOv3 and Image Rectification

— In the age of modern technology like today, object detection is something that is really needed. Object detection is done by considering the type of data collected. This research focused on Identity card detection from an input image taken by a smartphone camera. The Identity card detection is a preliminary step toward automatic identity data collection. Identity data collection is usually performed in a conventional way. This way leads to several problems such as bad data result, unreliable data verification, and long duration on confirming data validity. In this project, we will make an object detection system with YOLOv3 algorithm, and then the result will be used for an edge detection with Canny algorithm and image rectification. The testing result show that YOLOv3 algorithm could reach 92.59 mAP with 5s detection time. While the corner detection for image rectification manage to get an average error of 37.06 pixels. The establishment of this model has important practical significance for improving Identity Card detection process. Keywords—Identity Card Detection, Object Detection, YOLOv3 Model, Corner Detection, Image Rectification

Deep Learning Algorithms for Human Fighting Action Recognition

— Human action recognition using skeletons has been employed in various applications, including healthcare robots, human-computer interaction, and surveillance systems. Recently, deep learning systems have been used in various applications, such as object classification. In contrast to conventional techniques, one of the most prominent convolutional neural network deep learning algorithms extracts image features from its operations. Machine learning in computer vision applications faces many challenges, including human action recognition in real time. Despite significant improvements, videos are typically shot with at least 24 frames per second, meaning that the fastest classification technologies take time. Object detection algorithms must correctly identify and locate essential items, but they must also be speedy at prediction time to meet the real-time requirements of video processing. The fundamental goal of this research paper is to recognize the real-time state of human fighting to provide security in organizations by discovering and identifying problems through video surveillance. First, the images in the videos are investigated to locate human fight scenes using the YOLOv3 algorithm, which has been updated in this work. Our improvements to the YOLOv3 algorithm allowed us to accelerate the exploration of a group of humans in the images. The center locator feature in this algorithm was adopted as an essential indicator for measuring the safety distance between two persons. If it is less than a specific value specified in the code, they are tracked. Then, a deep sorting algorithm is used to track people. This framework is filtered to process and classify whether these two people continue to exceed the programmatically defined minimum safety distance. Finally, the content of the filter frame is categorized as combat scenes using the OpenPose technology and a trained VGG-16 algorithm, which classifies the situation as walking, hugging, or fighting. A dataset was created to train these algorithms in the three categories of walking, hugging, and fighting. The proposed methodology proved successful, exhibiting a classification accuracy for walking, hugging, and fighting of 95.0%, 87.4%, and 90.1%, respectively.

Vehicle detection method with low-carbon technology in haze weather based on deep neural network

AbstractVehicle detection based on deep learning achieves excellent results in normal environments, but it is still challenging to detect objects in low-quality picture obtained in hazy weather. Existing methods tend to ignore favorable latent information and it is difficult to balance speed and accuracy, etc. Therefore, the existing deep neural network is studied, and the YOLOv3 algorithm is improved based on ResNet. Aiming at the problem of low utilization of shallow features, DensNet is added in the feature extraction stage to reduce feature loss and increase utilization. An attention module is added in the feature extraction and fusion stage to better focus on potential information and improve the detection accuracy in haze weather. In view of the difficulty of vehicle detection in haze weather, focal loss is introduced to give more weights to difficult samples, balance the number of difficult and easy samples and improve detection accuracy. The experimental results show that the recognition accuracy of the improved network for vehicles reaches 75%, which proves the effectiveness of the method.

Construction and Multicenter Diagnostic Verification of Intelligent Recognition System for Endoscopic Images From Early Gastric Cancer Based on YOLO-V3 Algorithm.

IntroductionEndoscopy is an important tool for the diagnosis of early gastric cancer. Therefore, a combination of artificial intelligence and endoscopy has the ability to increase the speed and efficiency of early gastric cancer diagnosis. YOU ONLY LOOK ONCE (YOLO) is an advanced object detection depth neural network algorithm that has not been widely used in gastrointestinal image recognition.ObjectiveWe developed an artificial intelligence system herein referred to as “EGC-YOLO” for the rapid and accurate diagnosis of endoscopic images from early gastric cancer.MethodsMore than 40000 gastroscopic images from 1653 patients in Yixing people’s Hospital were used as the training set for the system, while endoscopic images from the other two hospitals were used as external validation test sets. The sensitivity, specificity, positive predictive value, Youden index and ROC curve were analyzed to evaluate detection efficiencies for EGC-YOLO.ResultsEGC-YOLO was able to diagnose early gastric cancer in the two test sets with a high superiority and efficiency. The accuracy, sensitivity, specificity and positive predictive value for Test Sets 1 and 2 were 85.15% and 86.02%, 85.36% and 83.02%, 84.41% and 92.21%, and 95.22% and 95.65%, respectively. In Test Sets 1 and 2, the corresponding Threshold-values were 0.02, 0.16 and 0.17 at the maximum of the Youden index. An increase in Threshold-values was associated with a downward trend in sensitivity and accuracy, while specificity remained relatively stable at more than 80%.ConclusionsThe EGC-YOLO system is superior for the efficient, accurate and rapid detection of early gastric cancer lesions. For different data sets, it is important to select the appropriate threshold-value in advance to achieve the best performance of the EGC-YOLO system.

VGGCOV19-NET: automatic detection of COVID-19 cases from X-ray images using modified VGG19 CNN architecture and YOLO algorithm.

X-ray images are an easily accessible, fast, and inexpensive method of diagnosing COVID-19, widely used in health centers around the world. In places where there is a shortage of specialist doctors and radiologists, there is need for a system that can direct patients to advanced health centers by pre-diagnosing COVID-19 from X-ray images. Also, smart computer-aided systems that automatically detect COVID-19 positive cases will support daily clinical applications. The study aimed to classify COVID-19 via X-ray images in high precision ratios with pre-trained VGG19 deep CNN architecture and the YOLOv3 detection algorithm. For this purpose, VGG19, VGGCOV19-NET models, and the original Cascade models were created by feeding these models with the YOLOv3 algorithm. Cascade models are the original models fed with the lung zone X-ray images detected with the YOLOv3 algorithm. Model performances were evaluated using fivefold cross-validation according to recall, specificity, precision, f1-score, confusion matrix, and ROC analysis performance metrics. While the accuracy of the Cascade VGGCOV19-NET model was 99.84% for the binary class (COVID vs. no-findings) data set, it was 97.16% for the three-class (COVID vs. no-findings vs. pneumonia) data set. The Cascade VGGCOV19-NET model has a higher classification performance than VGG19, Cascade VGG19, VGGCOV19-NET and previous studies. Feeding the CNN models with the YOLOv3 detection algorithm decreases the training test time while increasing the classification performance. The results indicate that the proposed Cascade VGGCOV19-NET architecture was highly successful in detecting COVID-19. Therefore, this study contributes to the literature in terms of both YOLO-aided deep architecture and classification success.

AUTOMATIC FISH DETECTION FROM DIFFERENT MARINE ENVIRONMENTS VIDEO USING DEEP LEARNING

Abstract. The marine environment provides many ecosystems that support habitats biodiversity. Benthic habitats and fish species associations are investigated using underwater gears to secure and manage these marine ecosystems in a sustainable manner. The current study evaluates the possibility of using deep learning methods in particular the You Only Look Once version 3 algorithm to detect fish in different environments such as; different shading, low light, and high noise within images and by each frame within an underwater video, recorded in the Atlantic Coast of Morocco. The training dataset was collected from Open Images Dataset V6, a total of 1295 Fish images were captured and split into a training set and a test set. An optimization approach was applied to the YOLOv3 algorithm which is data augmentation transformation to provide more learning samples. The mean average precision (mAP) metric was applied to measure the YOLOv3 model’s performance. Results of this study revealed with a mAP of 91,3% the proposed method is proved to have the capability of detecting fish species in different natural marine environments also it has the potential to be applied to detect other underwater species and substratum.

Deep-learning-based in-field citrus fruit detection and tracking.

Fruit yield estimation is crucial for establishing fruit harvest and marketing strategies. Recently, computer vision and deep learning techniques have been used to estimate citrus fruit yield and have exhibited notable fruit detection ability. However, computer-vision-based citrus fruit counting has two key limitations: inconsistent fruit detection accuracy and double-counting of the same fruit. Using oranges as the experimental material, this paper proposes a deep-learning-based orange counting algorithm using video sequences to help overcome these problems. The algorithm consists of two sub-algorithms, OrangeYolo for fruit detection and OrangeSort for fruit tracking. The OrangeYolo backbone network is partially based on the YOLOv3 algorithm, which has been improved upon to detect small objects (fruits) at multiple scales. The network structure was adjusted to detect small-scale targets while enabling multiscale target detection. A channel attention and spatial attention multiscale fusion module was introduced to fuse the semantic features of the deep network with the shallow textural detail features. OrangeYolo can achieve mean Average Precision (mAP) values of 0.957 in the citrus dataset, higher than the 0.905, 0.911, and 0.917 achieved with the YOLOv3, YOLOv4, and YOLOv5 algorithms. OrangeSort was designed to alleviate the double-counting problem associated with occluded fruits. A specific tracking region counting strategy and tracking algorithm based on motion displacement estimation were established. Six video sequences taken from two fields containing 22 trees were used as the validation dataset. The proposed method showed better performance (Mean Absolute Error (MAE) = 0.081, Standard Deviation (SD) = 0.08) than video-based manual counting and produced more accurate results than the existing standards Sort and DeepSort (MAE = 0.45 and 1.212; SD = 0.4741 and 1.3975).

A New Multiface Target Detection Algorithm for Students in Class Based on Bayesian Optimized YOLOv3 Model

Deep learning theory is widely used in face recognition. Combined with the needs of classroom attendance and students’ learning status monitoring, this article analyzes the YOLO (You Only Look Once) face recognition algorithms based on regression method. Aiming at the problem of small target missing detection in the YOLOv3 network structure, an improved YOLOv3 algorithm based on Bayesian optimization is proposed. The algorithm uses deep separable convolution instead of conventional convolution to improve the Darknet-53 basic network, and it reduces the amount of calculation and parameters of the network. A multiscale feature pyramid is built, and an attention guidance module is designed to strengthen multiscale fusion, detecting different sizes of targets. The loss function is improved to solve the imbalance of positive and negative sample distribution and the imbalance between simple samples and difficult samples. The Bayesian function is adopted to optimize the classifier and improve the classification efficiency and accuracy, ensuring the accuracy of small target detection. Five groups of comparative experiments are carried out on public COCO and VOC2012 datasets and self-built datasets. The experimental results show that the proposed improved YOLOv3 model can effectively improve the detection accuracy of multiple faces and small targets. Compared with the traditional YOLOv3 model, the mean mAP of the target is improved by more than 1.2%.

Real-time fall detection system based on deep learning and infrared array sensors

In this paper, a novel fall detection algorithm based infrared image is proposed. Firstly, the RetinexNet algorithm is adopted for the infrared image pre-processing and enhancement, then the YOLOv3 algorithm is improved by adding three bounding boxes to achieve the task of falling posture detection and recognition, finally a fall data set collected by ourselves is utilized to train and test the algorithm. The experimental results shows that our proposed algorithm achieves excellent fall detection accuracy result and outperforms the traditional YOLOv3 algorithm, the average accuracy of our proposed algorithm is more than 90.86%, which meets the requirements of the fall detection task quite well.

AI-enhanced vision system for dispensing process monitoring and quality control in manufacturing of large parts

Assembly is one of the cornerstones of today’s manufacturing; thus, efficient automated assembly systems have become a necessity in the recent past. Challenges that have traditionally been present in such systems involve positioning accuracy, stable gripping, accommodation of several variants by the same resources and prevention of error aggregation. In robot-based applications the detection of parts and their components is a common task, but when it comes to large objects which cannot be portrayed in single camera frames, the complexity becomes significantly larger. This paper presents an AI based perception system which employs a 3D vision sensor to implement a smart dispensing application and perform online process quality control of large parts assembly. The aim of the system is to provide execution autonomy for a robotic manipulator that is responsible for glue dispensing on different types of aluminium profiles of varying cross-sections, length, and associated glue patterns. By using an eye-in-hand RGB-D camera and employing deep learning methods (Yolov3 algorithm), the framework recognizes the type of profile that is going to be processed, and depth information is used to extract the profile’s points (starting-ending points) on which glue must be dispensed. Point Cloud manipulation (DBSCAN clustering, plane segmentation) and 2D image-based processing were tested during the quality inspection, in order to validate the success and accuracy of the process (detection of glue discontinuities, calculation of the glue volume level). The system has been deployed on a case study involving the assembly of components on buses and the results indicate that a robust recognition and adhesive application can be obtained throughout each operation cycle.

Performance analysis towards GUI-based vehicle detection and tracking using YOLOv3 and SORT algorithm

Performance analysis towards GUI-based vehicle detection and tracking using YOLOv3 and SORT algorithm

Waste Collection and Transportation Supervision Based on Improved YOLOv3 Model

Supervising the process of garbage collection and transportation is a very crucial task with significance implication to the reusing and the recycle of the garbage. Previous works mainly focus on the detection of certain kind of garbage instead of overseeing the whole process. This paper proposed a supervision approach based on the improved YOLOv3 to decrease the incidence of unexpected mixing of the different kinds of garbage during the transportation and the collection which will cause the inferior performance of waste classification. Firstly, to reduce the parameters and arithmetic operations of YOLOv3 and improving the model’s detection speed, we displaced the standard convolution in YOLOv3 by depth-wise separable convolution. Secondly, to solve the problem that YOLOv3 has poor location accuracy and performs poorly in muti-targets, triplet attention is introduced into the backbone, which increases almost no parameters to automatically learn cross-dimensional interactions, enhance the effective feature channel weights, and strengthen the feature extraction capability. Finally, we built a dataset of waste classification supervision using the images provided by a city environmental protection bureau on which we did massive experiments. The experimental result shows that compared with other detection algorithms, the improved YOLO v3 algorithm has better performance. The mAP is 98.5%, which is 0.7% and 1.1% higher than the YOLOv5l and the EfficientDet-B0, respectively, and the average detection speed of the model is 14.6ms/it, which meets the requirements of regulatory real-time and environment complexity of the supervision system.