Abstract
In order to enhance the real-time and retrieval performance of road traffic data filling, a real-time data filling and automatic retrieval algorithm based on the deep-learning method is proposed. In image detection, the depth representation is extracted according to the detection target area of a general object. The local invariant feature is extracted to describe local attributes in the region, and it is fused with depth representation to complete the real-time data filling of road traffic. According to the results of the database enhancement, the retrieval results of the deep representation level are reordered. In the index stage, unsupervised feature updating is realized by neighborhood information to improve the performance of a feature retrieval. The experimental results show that the proposed method has high recall and precision, a short retrieval time and a low running cost.
Highlights
On the basis of traditional methods, this paper designs and proposes a real-time data filling and automatic retrieval algorithm based on the deep-learning method
This paper proposes a road extraction model based on a deep-learning network that greatly improves the accuracy of image road extraction but, greatly enhances the fitness of the same model for road extraction in different terrain environments
Aiming at the problems of the traditional retrieval methods, such as the long retrieval time, high operation cost, and unsatisfactory retrieval effect, this paper designs and proposes a real-time data filling and automatic retrieval algorithm based on the deep-learning method and obtains the following conclusions: (1) The automatic extraction of road information from images has been proposed by many methods, but at present, the accuracy of these methods for image road extraction and the adaptability of road extraction in different terrain environments are not very high, which cannot meet the needs of practical application
Summary
In order to reduce traffic pressure, the most important thing is to accurately count the traffic flow to achieve a reasonable diversion To achieve this goal, real-time data filling and the automatic retrieval of road traffic has become a crucial step [1,2]. It is of great practical significance to study the technology of the real-time automatic detection of vehicles by surveillance video and improve its retrieval accuracy. On the basis of traditional methods, this paper designs and proposes a real-time data filling and automatic retrieval algorithm based on the deep-learning method. Because the experimental data assumes that the detector is normal, the factor of the detector failure is not considered This part of the data can be eliminated by Formula (3)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have