YOLOv3 Algorithm Research Articles

Deep learning based channel estimation optimization in VLC systems

This paper aims to improve the channel estimation (CE) in the indoor visible light communication system. The proposal of this paper deals with a system that depends on a comparison between Deep Neural Network (DNN), Yolo v3, and Kalman filter (KF) algorithm, for two optical modulation techniques; asymmetrically clipped optical-orthogonal frequency-division multiplexing (ACO-OFDM) and direct current optical-orthogonal frequency division multiplexing (DCO-OFDM). The CE can be evaluated by the error rates in the received bits, where increased error means a performance decrease of the system and vice versa. Receiving less errors at the receiver indicates improved CE and system performance. Hence, the main aim of our work is to decrease the error rate by using different estimators. Furthermore, we apply automatic hyper-parameter approach and Bayesian optimization, to Yolo v3 model to improve the system performance and reduce the positioning error. The metric parameter of bit error rate (BER) aims to determine the improvement ratio in different systems. The model in this paper is based on training with OFDM samples of signal with labels which are received and are corresponding to the signals of OFDM. At a BER = 10−3 with DCO-OFDM, the DNN outperforms KF with 1.7 dB (8.09%) at the bit energy per noise (E_{b} {/}N_{o} ) axis. Also, for ACO-OFDM at BER = 10−3, the DNN achieves better results than KF by about 1.9 dB (11.8%) at the (E_{b} {/}N_{o} ){ } axis. For different values of M in QAM, the DNN outperforms KF for ACO-OFDM by average improvement of ~ 1.2 dB (~ 13%).

Damaged apple detection with a hybrid YOLOv3 algorithm

This paper proposes an improved You Only Look Once (YOLOv3) algorithm for automatically detecting damaged apples to promote the automation of the fruit processing industry. In the proposed method, a clustering method based on Rao-1 algorithm is introduced to optimize anchor box sizes. The clustering method uses the intersection over the union to form the objective function and the most representative anchor boxes are generated for normal and damaged apple detection. To verify the feasibility and effectiveness of the proposed method, real apple images collected from the Internet are employed. Compared with the generic YOLOv3 and Fast Region-based Convolutional Neural Network (Fast R-CNN) algorithms, the proposed method yields the highest mean average precision value for the test dataset. Therefore, it is practical to apply the proposed method for intelligent apple detection and classification tasks.

Implementation of Object Detection With You Only Look Once Algorithm in Limited Face-To-Face Times in Pandemic

Covid-19 has hit many countries in the world, including Indonesia. The rapid and deadly spread of Covid-19 reached Indonesia in early 2020. This pandemic of course had a detrimental impact on the Indonesian people in terms of health, economy, education and others. The Indonesian government certainly does not remain silent, the government is aggressively making efforts to break the Covid-19 chain in various ways, one of the efforts made is to continuously inform about the health protocols recommended by the government to prevent transmission. The Indonesian Ministry of Health (in Mardhia et al., 2020) Efforts that can be made in the prevention phase by each individual include: Wearing a mask, Wearing gloves, Using hand sanitizer/disinfectant, Washing hands with soap, Avoiding touching the face, Avoid shaking hands, Avoid gatherings or long queues, Avoid touching objects/object surfaces in public areas, Avoid taking public transportation, Maintain a distance of at least two meters from other people when outside the house, and If you show symptoms of illness, immediately notify the people around. Even though they have been informed about the prevention of Covid-19, the public tends to be negligent in implementing health protocols, one of which is the application of Social Distancing. Therefore, this study will create a distance detector using the YOLOv3 algorithm as one of the detection objects for the implementation of community activity restrictions

Vehicle detection and masking in UAV images using YOLO to improve photogrammetric products

Abstract Photogrammetric products obtained by processing data acquired with Unmanned Aerial Vehicles (UAVs) are used in many fields. Various structures are analysed, including roads. Many roads located in cities are characterised by heavy traffic. This makes it impossible to avoid the presence of cars in aerial photographs. However, they are not an integral part of the landscape, so their presence in the generated photogrammetric products is unnecessary. The occurrence of cars in the images may also lead to errors such as irregularities in digital elevation models (DEMs) in roadway areas and the blurring effect on orthophotomaps. The research aimed to improve the quality of photogrammetric products obtained with the Structure from Motion algorithm. To fulfil this objective, the Yolo v3 algorithm was used to automatically detect cars in the images. Neural network learning was performed using data from a different flight to ensure that the obtained detector could also be used in independent projects. The photogrammetric process was then carried out in two scenarios: with and without masks. The obtained results show that the automatic masking of cars in images is fast and allows for a significant increase in the quality of photogrammetric products such as DEMs and orthophotomaps.

Traffic Sign Recognition Based on the YOLOv3 Algorithm

Traffic sign detection is an essential component of an intelligent transportation system, since it provides critical road traffic data for vehicle decision-making and control. To solve the challenges of small traffic signs, inconspicuous characteristics, and low detection accuracy, a traffic sign recognition method based on improved (You Only Look Once v3) YOLOv3 is proposed. The spatial pyramid pooling structure is fused into the YOLOv3 network structure to achieve the fusion of local features and global features, and the fourth feature prediction scale of 152 × 152 size is introduced to make full use of the shallow features in the network to predict small targets. Furthermore, the bounding box regression is more stable when the distance-IoU (DIoU) loss is used, which takes into account the distance between the target and anchor, the overlap rate, and the scale. The Tsinghua-Tencent 100K (TT100K) traffic sign dataset's 12 anchors are recalculated using the K-means clustering algorithm, while the dataset is balanced and expanded to address the problem of an uneven number of target classes in the TT100K dataset. The algorithm is compared to YOLOv3 and other commonly used target detection algorithms, and the results show that the improved YOLOv3 algorithm achieves a mean average precision (mAP) of 77.3%, which is 8.4% higher than YOLOv3, especially in small target detection, where the mAP is improved by 10.5%, greatly improving the accuracy of the detection network while keeping the real-time performance as high as possible. The detection network's accuracy is substantially enhanced while keeping the network's real-time performance as high as possible.

Human Ear Recognition Algorithm of YOLOV3 Based on Attention Mechanism

To address the problems of false detection and the lack of accurate target bounding boxes in the process of detecting human ear recognition, a SE-YOLOv3 target detection algorithm with improved YOLOv3 is proposed. Based on the YOLOv3 algorithm, the effects of embedding the SE attention module into different positions of the model on the detection performance of the algorithm are studied and analyzed separately. It is proved that embedding the SE attention module in the parallel ResNet network in the backbone of the YOLOv3 model can effectively improve the detection accuracy of the algorithm. And it is experimentally demonstrated in CCU-DE and USTB human ear datasets.

Trichromatic ratiometric fluorescent sensor based on machine learning and smartphone for visual and portable monitoring of tetracycline antibiotics

In this work, a tri-color ratiometric fluorescent optical device integrated with machine learning-assisted smartphones is designed for the visual monitoring of tetracycline antibiotics. The trichromatic sensing probe consists of blue emitting carbon dots (BCDs) at 420 nm, and red-emitting bovine serum albumin-protected copper nanoclusters (BSA-Cu NCs) at 635 nm, as well as an emission peak at 520 nm, rises in the presence of tetracycline antibiotics (TCs), therefore, a three emission system is formed. BCDs/BSA-Cu NCs present three emission responses to TCs, which are based on the internal filtering effect (IFE) and the sensitization mechanisms with BSA. The reaction mechanism was verified by density functional theory (DFT) and a series of characterizations, such as infrared spectrum, ultraviolet absorption spectrum, and fluorescence lifetime. Interestingly, the fluorescence intensity of BCDs was quenched by TCs, and due to the sensitization between BSA and TCs, a green fluorescence rose at 520 nm, while the peak of BSA-Cu NCs remained stable, resulting in a significant color shift from red to cyan. Therefore, the ratiometric fluorescence intensity of I(635+520)/I420 can be used to determine TCs, and the colors change can be used to identify the quantitative analysis. In addition, the deep learning of the YOLO v3 algorithm assists the integrated tri-color portable optical device of smartphones, which can realize the visual detection of TCs. In general, the sensing system has many advantages, such as good stability, specificity, and rich color changes, which provide help for the visual detection of tetracycline residues.

Artificial Intelligence based Integrated and Distributed System for Preventing Covid-19 Spread Using Deep Learning

The COVID-19 pandemic is causing a worldwide emergency in healthcare. This virus mainly spreads through droplets which emerge from a person infected with coronavirus and poses a risk to others. The risk of transmission is highest in public places. Many measures have been suggested, such as maintaining a social distance, and wearing a face mask to avoid the spread of this virus. There are three modules in this work, in the first module a mask detection system which detects whether a person wears a mask or not using deep learning techniques such as MobileNet V2 architecture along with Facenet and Masknet. Accuracy of 98.6% is achieved in this module with one or two people in the frame. Barricade has been set which does not allow people who does not wear mask and allows people who wears a mask. LED light indicators and LCD displays are used as alerts, and they are programmed to provide information that is both worn and not worn, depending on the output. In the second module, a system has been designed which detects the temperature of the person and detects whose temperature is above normal body temperature and alerts accordingly. In the third module a social distancing system has been designed which detects people who does not follow social distancing protocol and alerts them using deep learning techniques. The YOLOv3 algorithm is used which creates a square box around people that displays green or red color box according to the measurement output. The transfer learning methodology is also implemented to increase the accuracy of this module. The accuracy of 98.2% is achieved for social distance detection module using YOLOv3 detection model with transfer learning. All three modules are integrated so it automatically monitors human body temperature, detects mask and social distancing at the barricade system.

Position Detection of Doors and Windows Based on DSPP-YOLO

Autonomous exploration of autonomous mobile robots in unknown environments is a hot topic at present. Object detection is an important research direction in improving the autonomous capability of autonomous mobile robots in unknown environments. In object detection, doors and windows have many similar features and are difficult to distinguish. Therefore, improving the detection accuracy of doors and windows is helpful to improve the autonomous ability of autonomous mobile robots. Aiming at the problem of insufficient doors and windows detection accuracy caused by the large difference between the receptive fields of doors and windows, this paper proposes DSPP-YOLO (DenseNet SPP) algorithm. Firstly, on the basis of deepening the network addition, to prevent the loss of shallow location feature information, some residual blocks in YOLOV3 are improved to dense blocks by using the idea of DenseNet. Secondly, the spatial pyramid pooling (SPP) structure is fused into the YOLOV3 feature extraction network to realize multiscale receptive field fusion. Finally, K-means ++ algorithm is used to re-cluster the size of candidate boxes to reduce the error caused by candidate boxes. DSPP-YOLO realizes the position detection of doors and windows by an autonomous robot in an unknown, complex environment. This method is tested. Under the condition of the same data set, the detection accuracy of the DSPP-YOLO algorithm is 77.4% for doors and 38.1% for windows. Compared with YOLOV3 algorithm, the calculation consumption time of the DSPP-YOLO algorithm does not increase, and the detection accuracy of doors is improved by 3.3%, the detection accuracy of windows is improved by 8.8%, and the average accuracy of various types is improved by 6.05%.

Multi-target trajectory tracking in multi-frame video images of basketball sports based on deep learning

INTRODUCTION: There is occlusion interference in the multi-target visual tracking process of basketball video images, which leads to poor accuracy of multi-target trajectory tracking. This paper studies the multi-target trajectory tracking method in multi-frame video images of basketball sports based on deep learning. OBJECTIVES: Aiming at the problem of target occlusion in the tracking process and the problem of trajectory tracking anomaly caused by target occlusion, a modified algorithm is proposed. METHODS: The method is divided into two parts: detection and tracking. In the detection part, the YOLOv3 algorithm in deep learning technology is used to detect each target in the video, and the original YOLOv3 backbone network Darknet-53 is replaced by the lightweight backbone network MobileNetV2 to extract the target features. RESULTS: Based on the target detection results, the Kalman filter is used to predict the next position and bounding box size of the target to obtain the target trajectory prediction results according to the current target position, then a hierarchical data association algorithm is designed, and multi-target tracking of the same category is completed based on the target appearance feature similarity and feature similarity. CONCLUSION: The experimental results show that the method can accurately detect the targets in multi-frame video images in basketball sports and obtain high-precision target trajectory tracking results.

Pedestrian detection based on YOLOv3 multimodal data fusion

Multi-sensor fusion has essential applications in the field of target detection. Considering the current actual demand for miniaturization of on-board computers for driverless vehicles, this paper uses the multimodal data YOLOv3 (MDY) algorithm for pedestrian detection on embedded devices. The MDY algorithm uses YOLOv3 as the basic framework to improve pedestrian detection accuracy by optimizing anchor frames and adding small target detection branches. Then the algorithm is accelerated by using TensorRT technology to improve the real-time performance in embedded devices. Finally, a hybrid fusion framework is used to fuse the LIDAR point cloud data with the improved YOLOv3 algorithm to compensate for the shortcomings of a single sensor and improve the detection accuracy while ensuring speed. The improved YOLOv3 improves AP by 6.4% and speed by 11.3 FPS over the original algorithm. The MDY algorithm achieves better performance on the KITTI dataset. To further verify the feasibility of the MDY algorithm, an actual test was conducted on an unmanned vehicle with Jetson TX2 embedded device as the on-board computer within the campus scenario, and the results showed that the MDY algorithm achieves 90.8% accuracy under real-time operation and can achieve adequate detection accuracy and real-time performance on the embedded device.

Real-time Telugu Sign Language Translator with Computer Vision

Abstract: Sign language is the basic communication method among hearing disabled and speech disabled people. To express themselves, they require an interpreter or motion sensing devices who/which converts sign language in a few of the standard languages. However, there is no system for those who speak in the Telugu language and hence they are forced to speak in the national language over the regional language of their culture along with the same issues of cumbersome hardware or need for an interpreter. This paper proposes a system that detects hand gestures and signs from a real-time video stream that is processed with the help of computer vision and classified with object detection YOLOv3 algorithm. Additionally, the labels are mapped to corresponding Telugu text. The style of learning is transfer learning, unlike conventional CNNs, RNNs or traditional Machine Learning models. It involves applying a pre-trained model onto a completely new problem to solve the related problem statement and adapts to the new problem’s requirements efficiently. This requires lesser training effort in terms of dataset size and greater accuracy. It is the first system developed as a sign language translator for Telugu script. It has given the best results as compared to the existing systems. The system is trained on 52 Telugu letters, 10 numbers and 8 frequently used Telugu words.

Real-time social distance measurement and face mask detection in public transportation systems during the COVID-19 pandemic and post-pandemic Era: Theoretical approach and case study in Italy

Due to its remarkable learning ability and benefits in several areas of real-life, deep learning-based applications have recovered to be a research topic of great importance in the last few years. This article presents a method devoted to guaranteeing safety conditions in public transportation systems (PTS) during the COVID-19 pandemic and post-pandemic era. The paper describes a viable real-time model based on deep learning for monitoring social distance between users and detecting face masks in stop areas and inside vehicles of public transportation systems. Detections are made using the deep learning approach and YOLOv3 algorithm. The safety rule violations are represented by red bounding boxes and red circles in a bird’s eye view as output of the video surveillance analysis. The datasets used to train the neural network are the “Caltech Pedestrian Dataset” and the “COVID-19 Medical Face Mask Detection Dataset”. Metrics, such Loss Accuracy, and Precision, obtained in the testing process of the neural network were used to evaluate the performance of the model in detecting users and face masks. The proposed method was recently tested in the Public Transportation System of the Municipality of Piazza Armerina (Italy). The results show a significant reliability of the method in detecting real-time interactions between users of the PTS in terms of over-time variations in their mutual distancing, as well as in recognising cases of violation of the imposed social distancing and FFP2 face mask use.

A digital implantation system for Z-direction yarn of three-dimensional preform based on flexible oriented woven process

The implantation of Z-direction yarn is crucial in the process of forming flexible oriented 3D woven preforms, but manual implantation of Z-direction yarn is both time-consuming and inefficient. In this study, the digital Z-direction yarn implantation process and device are developed. Firstly, in view of many targets, small diameter, and serious interference in the identification process of the guide sleeve, a modified YOLOv3 algorithm is proposed to improve the accuracy and speed of detection, completing the coarse identification of guide sleeve. Then, an algorithm with modified Hough transform is proposed to improve the accuracy and speed of circle detection of coarse identification guide sleeve. Finally, based on the 1.2 mm diameter guide sleeve, a digital yarn replacement device was built to precisely replace the guide sleeve with replacement needles and implant the Z-direction yarn into the preform. The identification error of the guide sleeve is within 0.31% and the error between the reconstructed coordinates and the actual coordinates is within 3.08%. This study is crucial to the identification and positioning of small targets under complex working conditions and the development of digital forming of preform.

Yolov5-based fall detection algorithm for homebound people

According to the statistics from the official website of the National Bureau of Statistics, the population over 60 years old in China is close to 260 million, accounting for about 18.7% of the total population. As society moves towards aging, the safety problem of the elder people alone is gradually highlighted, and the accidental fall of the elderly at home has become a problem that cannot be ignored, and developing fall detection technology to mitigate the danger of falls of the elderly is imperative. So, this paper proposes a fall detection method which is based on deep learning. Specifically, the method is based on the Yolov3 method, and to enhance the accuracy and speed, the Yolov3 algorithm is updated to Yolov5s. The final experimental results also confirm that the above method has achieved the purpose.

Insulator and Burst Fault Detection Using an Improved Yolov3 Algorithm

Insulators play an important role in the operation of outdoor high-voltage transmission lines. However, insulators are installed in outdoor environments for long periods and thus failures are inevitable. It is necessary to conduct timely insulator inspection and maintenance. In this paper, an improved Yolov3 target detection network (Yolov3-CK) is proposed in order to achieve higher detection accuracy and speed. First, Yolov3-CK uses the CIOU loss function instead of the mean square error loss function from Yolov3. Second, the Yolov3-CK model uses cluster analysis of the priori box via the k -means++ algorithm to obtain a priori box size that is more suitable for the detection of insulators and their burst faults. Finally, we use a dataset obtained by performing data enhancement on the China power line insulator dataset to train and test the data-enhanced Yolov3-CK model. The mean precision of Yolov3-CK reaches 91.67% with 47.9 frames processed per second. Yolov3-CK provides better detection accuracy and a higher processing rate than Faster RCNN, SSD, and Yolov3. Therefore, the Yolov3-CK model is more suitable for the detection of insulators and their burst faults.

A novel optimized tiny YOLOv3 algorithm for the identification of objects in the lawn environment

Based on the problem of insufficient accuracy of the original tiny YOLOv3 algorithm for object detection in a lawn environment, an Optimized tiny YOLOv3 algorithm with less computation and higher accuracy is proposed. Three reasons affect the accuracy of the original tiny YOLOv3 algorithm for detecting objects in a lawn environment. First, the backbone of the original algorithm is composed of a stack of a single convolutional layer and a max-pooling layer, which results in insufficient ability to extract feature information of objects. An enhancement module is proposed to enhance the feature extraction capability of the shallow layers of the network. Second, the information of the shallow convolutional layers of the backbone is not fully used, which results in insufficient detection capability for small objects. Third, the deep part of the backbone uses a convolutional layer with an excessive number of channels, which results in a large amount of computation. A multi-resolution fusion module is proposed to enhance the information interaction capability of the deep and shallow layers of the network, and reduce the computation. To verify the accuracy of this Optimized tiny YOLOv3 algorithm, the algorithm was tested on the dataset containing trunk, spherical tree and person, and compared with the current research. The results show that the algorithm proposed in this paper improves the detection accuracy while reducing the calculation.

Smart Tramway Systems for Smart Cities: A Deep Learning Application in ADAS Systems

Artificial intelligence and deep learning-based techniques undoubtedly are the future of Advanced Driver-Assistance Systems (ADAS) technologies. In this article is presented a technique for detecting, recognizing and tracking pedestrians, vehicles and cyclists along a tramway infrastructure in a complex urban environment by Computer Vision, Deep Learning approaches and YOLOv3 algorithm. Experiments have been conducted in the tramway Line 2 “Borgonuovo –Notarbartolo” (Palermo, Italy) in correspondence of the tramway segments crossing a roundabout having an external diameter of 24 m. A survey vehicle equipped with a video camera was used in the study. The results of the research show that the proposed method is able to search and detect the position and the speed of road users near and over the rails in front of the tram in a very precise way as demonstrate by the estimated values of the Accuracy, Loss and Precision obtained during the neural networks training process. The implementation of this advanced detection method in ADAS systems may increase the safety of novel autonomous trams and autonomous rapid trams (ARTs).

Automatic tracking of objects using improvised Yolov3 algorithm and alarm human activities in case of anomalies

Automatic tracking of objects using improvised Yolov3 algorithm and alarm human activities in case of anomalies

YOLO-Submarine Cable: An Improved YOLO-V3 Network for Object Detection on Submarine Cable Images

Due to the strain on land resources, marine energy development is expanding, in which the submarine cable occupies an important position. Therefore, periodic inspections of submarine cables are required. Submarine cable inspection is typically performed using underwater vehicles equipped with cameras. However, the motion of the underwater vehicle body, the dim light underwater, and the property of light propagation in water lead to problems such as the blurring of submarine cable images, the lack of information on the position and characteristics of the submarine cable, and the blue–green color of the images. Furthermore, the submarine cable occupies a significant portion of the image as a linear entity. In this paper, we propose an improved YOLO-SC (YOLO-Submarine Cable) detection method based on the YOLO-V3 algorithm, build a testing environment for submarine cables, and create a submarine cable image dataset. The YOLO-SC network adds skip connections to feature extraction to make the position information of submarine cables more accurate, a top-down downsampling structure in multi-scale special fusion to reduce the network computation and broaden the network perceptual field, and lightweight processing in the prediction network to accelerate the network detection. Under laboratory conditions, we illustrate the effectiveness of these modifications through ablation studies. Compared to other algorithms, the average detection accuracy of the YOLO-SC model is increased by up to 4.2%, and the average detection speed is decreased by up to 1.616 s. The experiments demonstrate that the YOLO-SC model proposed in this paper has a positive impact on the detection of submarine cables.