Public transport vehicle passenger flow statistical method and system

Abstract

The invention discloses a public transport vehicle passenger flow statistical method and system. Concretely, two cameras are respectively installed at the front and rear doors of a bus. The release lines of the front and rear doors of the bus and a fitting function of the camera height and the head size are determined before processing images acquired by the cameras. After a door opening signal is received, preprocessing, head detection, head tracking and head movement track analysis are performed on the images acquired by the cameras in turn, and finally passenger behaviors are analyzed according to head movement tracks, the number of bidirectional passenger flow of the corresponding doors is acquired and the number of bidirectional passenger flow of the whole bus is acquired through statistics of the number of bidirectional passenger flow of the front and rear doors of the bus. After a door closing signal is received, processing of the images acquired by the cameras is stopped, and the problem of influence on the statistical result caused by abrupt change of illumination generated by movement of the bus can be reduced. The method has advantages of high statistical accuracy so that reliable supporting can be provided for intelligent scheduling of the bus.

Description

technical field [0001] The invention relates to a passenger flow statistics method, in particular to a bus passenger flow statistics method and system. Background technique [0002] With the rapid development of the economy, the continuous expansion of the city, the increase in the number of urban motor vehicles, and the increase in road traffic flow, with the advent of the "Internet +" era, people are more willing to choose convenient travel methods, among which buses are one of the commonly used methods, but The bus is full, empty, and passengers are stranded at the station. Therefore, how to reasonably dispatch buses is the primary issue of current public bus services. Real-time statistical analysis of bus passenger flow data can provide good data support for bus operation and scheduling, which is conducive to the development of public transport. [0003] At present, there are several methods for bus passenger flow statistics: manual statistics, pressure detection techno...

AI Technical Summary

Problems solved by technology

The feature point tracking calculation generally clusters and analyzes the trajectory of the feature points to obtain passenger flow information, but the feature points themselves are difficult to track stably, and the calculation accuracy is poor; human body segmentation and tracking is to extract moving target blocks first, and then segment them to obtain Single target, tracking the trajectory of each target, so as to realize passenger flow statistics, but it cannot deal with the situation of occlusion, which affects the accuracy; the tracking of head or head shoulder detection generally chooses an appropriate angle to reduce occlusion, and selects the classifier to perform head detection Detection, but it is not easy to identify false targets, resulting in inaccurate headcount

At present, the existing system is in its infancy, and its configuration environment is cumbersome, which brings difficulties to the engineering installation personnel. In addition, the algorithm itself is not ideal for the actual application effect, and has not achieved intelligence.

Images