Second-hand commercial vehicle condition detection method based on improved Faster RCNN prediction model

A predictive model and vehicle condition detection technology, which is applied in neural learning methods, biological neural network models, image enhancement, etc., can solve problems such as unsatisfactory detection and recognition results, lack of discrimination ability for buyers, and no evaluation system

Inactive Publication Date: 2021-05-11
天津狮拓信息技术有限公司
View PDF17 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The evaluation and inspection system of commercial vehicles requires complex procedures and comprehensive inspections of cabs, chassis, engines, gearboxes, etc., and ordinary buyers do not have the ability to discriminate
At the same time, due to the actual use environment of the vehicle, the professional knowledge of the practitioners and the lack of professional third-party service agencies, the second-hand commercial vehicle market has never had a reasonable evaluation system or unified standards, which makes it often difficult for users to purchase second-hand commercial vehicles. Accurately

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Second-hand commercial vehicle condition detection method based on improved Faster RCNN prediction model
  • Second-hand commercial vehicle condition detection method based on improved Faster RCNN prediction model
  • Second-hand commercial vehicle condition detection method based on improved Faster RCNN prediction model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings. It should be understood that the specific embodiments described here are only used to explain the present invention, and are not intended to limit the present invention.

[0026] Such as figure 1 As shown, in this embodiment, a second-hand commercial vehicle condition detection method based on the improved Faster RCNN prediction model is provided, including the following steps,

[0027] S1. Collect images of parts to be detected in second-hand commercial vehicles, and divide the images of parts to be detected into a training set and a test set in proportion; use an image marking tool to mark the category and position coordinates of the accident points in the training set;

[0028] S2. Name the training set as an image file in a preset format, scale the image file i...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a second-hand commercial vehicle condition detection method based on an improved Faster RCNN prediction model, and the method comprises the steps: collecting an image of a to-be-detected part of a second-hand commercial vehicle, and dividing the image of the to-be-detected part into a training set and a test set according to a proportion; using an image marking tool to mark the category and the position coordinate of an accident point in the training set; and naming the training set as an image file in a preset format, scaling the image file in the preset format into a preset size suitable for network training through a bilinear interpolation method, and then performing data enhancement operation on the image file to obtain a preprocessed image. The method has the advantages that the deep learning technology and the image processing technology are combined, the accident point on the second-hand commercial vehicle in the complex scene is detected and recognized through the deep learning method, and the detection speed and precision are improved. The network structure and the training mode of the Faster RCNN prediction model are improved, the optimization algorithm and the data augmentation method are improved, and the detection effect is improved.

Description

technical field [0001] The invention relates to the technical field of used vehicle detection, in particular to a method for detecting the condition of a used commercial vehicle based on an improved Faster RCNN prediction model. Background technique [0002] The replacement of second-hand cars is the premise and key to promoting new car sales. Its transaction volume is increasing year by year, especially the proportion of second-hand commercial vehicles in the entire second-hand car transaction volume is constantly expanding. However, it is undeniable that there are still many pain points in the second-hand commercial vehicle transaction market. The most obvious of these is the evaluation and detection system. The evaluation and inspection system of commercial vehicles requires complex procedures and comprehensive inspections of the cab, chassis, engine, gearbox, etc., and ordinary buyers do not have the ability to discriminate. At the same time, due to the actual use envir...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06T7/00G06T3/40G06T3/60G06N3/08G06N3/04
CPCG06T7/0002G06T3/4007G06T3/60G06N3/08G06T2207/20104G06T2207/20081G06T2207/20084G06N3/045Y02T10/40
Inventor 唐明利杨林张道甜刘宁东
Owner 天津狮拓信息技术有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products