Abstract
In the intelligent traffic system, real-time and accurate detections of vehicles in images and video data are very important and challenging work. Especially in situations with complex scenes, different models, and high density, it is difficult to accurately locate and classify these vehicles during traffic flows. Therefore, we propose a single-stage deep neural network YOLOv3-DL, which is based on the Tensorflow framework to improve this problem. The network structure is optimized by introducing the idea of spatial pyramid pooling, then the loss function is redefined, and a weight regularization method is introduced, for that, the real-time detections and statistics of traffic flows can be implemented effectively. The optimization algorithm we use is the DL-CAR data set for end-to-end network training and experiments with data sets under different scenarios and weathers. The analyses of experimental data show that the optimized algorithm can improve the vehicles’ detection accuracy on the test set by 3.86%. Experiments on test sets in different environments have improved the detection accuracy rate by 4.53%, indicating that the algorithm has high robustness. At the same time, the detection accuracy and speed of the investigated algorithm are higher than other algorithms, indicating that the algorithm has higher detection performance.
Highlights
With the dramatic improvement of people’s standards of living, the rapid expansion of cities, and the growing number of private cars, traffic congestion has become an important issue that restricts urban development and affects the quality of life
By using the YOLOv3-Dl algorithm and optimized by DIOU, the traffic flow statistics with a high accuracy rate can be generated, and the results obtained after adjusting the threshold parameters are very close to the actual number of vehicles
The experimental results show that the YOLOv3 model needs to be further improved in real-time and accuracy rate of traffic monitoring
Summary
With the dramatic improvement of people’s standards of living, the rapid expansion of cities, and the growing number of private cars, traffic congestion has become an important issue that restricts urban development and affects the quality of life. The traditional target detection methods are as follows: Xu et al proposed a featured operator, which can extract features from the region of interest selected on the images and implement target detection by training a classifier [2]. Felzenszwalb et al had proposed a sliding window classification method, which first extracts the features of the region of interest through sliding windows and performs classification by a support vector machine (SVM) classifier to achieve target detection [4]. This method has a large amount of calculation, which leads to a slower detection speed [5].
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
