Optimized YOLOv3 Algorithm and Its Application in Traffic Flow Detections

Huang, Yiqi; Zheng, Jiachun; Sun, Shidan; Yang, Cheng-Fu; Liu, Jing

doi:10.3390/app10093079

Cited by 92 publications

(45 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…However, the MSE loss function fails to reflect the relationship between the information, but uses it as an independent variable. In order to improve it, IoU loss is proposed, which considers the area of the predicted bounding box (BBOX) and the ground truth bounding box [28,29]. YOLOv4 uses CIoU loss instead of MSE loss, which includes the shape and direction of the object and also considers the overlap area, the distance between the center points, and the aspect ratio, which are defined as follows.…”

Section: The Loss Of Yolov4mentioning

confidence: 99%

A Hybrid YOLOv4 and Particle Filter Based Robotic Arm Grabbing System in Nonlinear and Non-Gaussian Environment

et al. 2021

View full text Add to dashboard Cite

In this paper, we propose a robotic arm grasping system suitable for complex environments. For a robotic arm, in order to achieve its accurate grasp of the target object, not only the vision but also a certain tracking ability should be provided. To improve the grasp quality, we propose a robotic arm grasping system using YOLOv4 combined with a particle filter (PF) algorithm, which can be applied in a nonlinear and non-Gaussian environment. Firstly, the coordinates of the bounding box in the image can be obtained through the YOLOv4 object detection algorithm. Secondly, the coordinates in the world system can be obtained through the eye-to-hand calibration system. Thirdly, a PF model can be established based on the coordinate changes of the target object. Finally, according to the predicted output of the PF, the robotic arm and the target object can reach the specific position at the same time and complete the grab. As the target object, the bowl is applied to experiments for the sake of achieving a more convincing demonstration. The experimental results show that the robotic arm grasping system proposed in this paper can accomplish the successful grasp at a rate of nearly 88%, even at a higher movement speed, which is of great significance to robot applications in various fields.

show abstract

Section: The Loss Of Yolov4mentioning

confidence: 99%

A Hybrid YOLOv4 and Particle Filter Based Robotic Arm Grabbing System in Nonlinear and Non-Gaussian Environment

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Fifty videos were recorded. The length of each collected video was 40 s, a value chosen according to related studies [78]. The videos are 34.25 FPS and were captured with an EOS 550D camera at four different locations, under three occlusion statuses.…”

Section: Validation With Real-time Videosmentioning

confidence: 99%

Lightweight PVIDNet: A Priority Vehicles Detection Network Model Based on Deep Learning for Intelligent Traffic Lights

Barbosa

Ayub

Rosa

et al. 2020

Sensors

View full text Add to dashboard Cite

Minimizing human intervention in engines, such as traffic lights, through automatic applications and sensors has been the focus of many studies. Thus, Deep Learning (DL) algorithms have been studied for traffic signs and vehicle identification in an urban traffic context. However, there is a lack of priority vehicle classification algorithms with high accuracy, fast processing, and a lightweight solution. For filling those gaps, a vehicle detection system is proposed, which is integrated with an intelligent traffic light. Thus, this work proposes (1) a novel vehicle detection model named Priority Vehicle Image Detection Network (PVIDNet), based on YOLOV3, (2) a lightweight design strategy for the PVIDNet model using an activation function to decrease the execution time of the proposed model, (3) a traffic control algorithm based on the Brazilian Traffic Code, and (4) a database containing Brazilian vehicle images. The effectiveness of the proposed solutions were evaluated using the Simulation of Urban MObility (SUMO) tool. Results show that PVIDNet reached an accuracy higher than 0.95, and the waiting time of priority vehicles was reduced by up to 50%, demonstrating the effectiveness of the proposed solution.

show abstract

“…The pioneering work of region-based target detection began with the region-based convolutional neural network (R-CNN), including three modules: regional proposal, vector transformation, and classification [ 15 , 16 ]. Spatial pyramid pooling (SPP)-net optimized the R-CNN and improved detection performance [ 16 , 17 ]. Fast R-CNN combines the essence of SPP-net and R-CNN, and introduces a multi-task loss function, which is what makes the training and testing of the whole network so functional [ 16 , 18 ].…”

Section: Introductionmentioning

confidence: 99%

The Development of a Skin Cancer Classification System for Pigmented Skin Lesions Using Deep Learning

Jinnai¹,

Yamazaki²,

Hirano

et al. 2020

Biomolecules

176

View full text Add to dashboard Cite

Recent studies have demonstrated the usefulness of convolutional neural networks (CNNs) to classify images of melanoma, with accuracies comparable to those achieved by dermatologists. However, the performance of a CNN trained with only clinical images of a pigmented skin lesion in a clinical image classification task, in competition with dermatologists, has not been reported to date. In this study, we extracted 5846 clinical images of pigmented skin lesions from 3551 patients. Pigmented skin lesions included malignant tumors (malignant melanoma and basal cell carcinoma) and benign tumors (nevus, seborrhoeic keratosis, senile lentigo, and hematoma/hemangioma). We created the test dataset by randomly selecting 666 patients out of them and picking one image per patient, and created the training dataset by giving bounding-box annotations to the rest of the images (4732 images, 2885 patients). Subsequently, we trained a faster, region-based CNN (FRCNN) with the training dataset and checked the performance of the model on the test dataset. In addition, ten board-certified dermatologists (BCDs) and ten dermatologic trainees (TRNs) took the same tests, and we compared their diagnostic accuracy with FRCNN. For six-class classification, the accuracy of FRCNN was 86.2%, and that of the BCDs and TRNs was 79.5% (p = 0.0081) and 75.1% (p < 0.00001), respectively. For two-class classification (benign or malignant), the accuracy, sensitivity, and specificity were 91.5%, 83.3%, and 94.5% by FRCNN; 86.6%, 86.3%, and 86.6% by BCD; and 85.3%, 83.5%, and 85.9% by TRN, respectively. False positive rates and positive predictive values were 5.5% and 84.7% by FRCNN, 13.4% and 70.5% by BCD, and 14.1% and 68.5% by TRN, respectively. We compared the classification performance of FRCNN with 20 dermatologists. As a result, the classification accuracy of FRCNN was better than that of the dermatologists. In the future, we plan to implement this system in society and have it used by the general public, in order to improve the prognosis of skin cancer.

show abstract

Optimized YOLOv3 Algorithm and Its Application in Traffic Flow Detections

Cited by 92 publications

References 18 publications

A Hybrid YOLOv4 and Particle Filter Based Robotic Arm Grabbing System in Nonlinear and Non-Gaussian Environment

A Hybrid YOLOv4 and Particle Filter Based Robotic Arm Grabbing System in Nonlinear and Non-Gaussian Environment

Lightweight PVIDNet: A Priority Vehicles Detection Network Model Based on Deep Learning for Intelligent Traffic Lights

The Development of a Skin Cancer Classification System for Pigmented Skin Lesions Using Deep Learning

Contact Info

Product

Resources

About