Statistical method, system, computing device and storage medium for bus operation data
A technology for data statistics and public transportation, applied in the computer field, can solve the problems of high cost and low data accuracy, and achieve the effect of ensuring accuracy, reducing equipment deployment, and low deployment requirements
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0047] figure 1 The implementation process of the bus operation data statistical method provided by the first embodiment of the present invention is shown. For the convenience of explanation, only the parts related to the embodiment of the present invention are shown, and the details are as follows:
[0048] In step S101, a number of video images to be processed are obtained. The video images to be processed are obtained by processing the bus environment video, and there is a time sequence relationship between different video images to be processed.
[0049] In this embodiment, when bus operation data such as passenger flow data and passenger congestion data need to be counted for a certain bus environment, a video shooting system can be built in the bus environment or an existing video shooting system for monitoring can be used. The shooting system can use ordinary vertical hanging cameras to shoot corresponding bus scenes. The real-time video stream or offline video files ob...
Embodiment 2
[0058] On the basis of Embodiment 1, this embodiment further provides the following content:
[0059] Such as figure 2 As shown, before step S101, it also includes:
[0060] In step S201, a frame cutting process is performed on the bus environment video to obtain an original video image.
[0061] In this embodiment, during the frame cutting process, there is an appropriate time interval between the cut out original video images (frames), which should not be too short to avoid repeated images.
[0062] In step S202, the original video image is preprocessed to obtain a video image to be processed.
[0063] In this embodiment, in order to enable the subsequent deep learning network to input the required video images to be processed, it is necessary to perform corresponding preprocessing on the original video images, and the preprocessing may include one or more of the following processing methods: First, the denoising process can use three-dimensional block matching (Block Ma...
Embodiment 3
[0065] This embodiment further provides the following content on the basis of other embodiments:
[0066] The deep learning network used in step S102 is preferably an SSD deep learning network.
[0067] In this embodiment, the SSD deep learning network can be obtained through more than 200,000 rounds of sample training based on the tensorflow framework of the python language. The learning rate can be set to 0.0005 for the first 50,000 rounds of training. During the 10,000th round and the 150,000th round of training, the learning rate is multiplied by 0.5, 0.1, and 0.05 to further reduce the learning rate, and the visual geometry group (Visual Geometry Group, VGG)-16 is used to train the model based on the ImageNet dataset. Migration learning is carried out to finally obtain the SSD deep learning network referred to in this embodiment.
[0068] The SSD deep learning network architecture can be as follows image 3 As shown, it includes: a pre-convolutional network 301 and a po...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com