Image-identification-based system for detecting contour dimension of motor vehicle

Abstract

The invention relates to a system for detecting the contour dimension of a motor vehicle, in particular to an image-identification-based system for detecting the contour dimension of a motor vehicle. The system comprises a digital camera set, a front-end controller, a switcher and a computer, wherein the digital camera set is connected with the front-end controller, and the front-end controller is connected with the computer through the switcher. The system is characterized by also comprising a black and white barcode grade rod, a double portal frame, single portal frames and a double-face frame with two rectangular portal frames The black and white barcode grade rod is arranged on the outer side of the rectangular double-face frame, the single portable frames are respectively arranged at the position 2-5 meters in right ahead of each portal frame face at the outer side of the rectangular double-face frame, wherein each single portable frame is a plan-shaped single-face frame, the digital camera set is arranged right above the plan-shaped single-face frames, and the photographing direction of the digital camera set is symmetrical with the direction of the black and white barcode grade rod arranged on the double-face frame with two portal frames. By the system, contour dimension and other parameters of various motor vehicles can be measured quickly and efficiently.

Description

1. Technical field [0001] The invention relates to a detection system for the exterior dimensions of a motor vehicle, in particular to a detection system for the exterior dimensions of a motor vehicle based on image recognition. 2. Background technology [0002] With the development of the automobile industry, the detection technology of motor vehicles is also constantly improving. However, at present, my country's vehicle management department mainly relies on manual inspection for the detection of the external dimensions of motor vehicles, that is, through manual visual inspection or measurement with measuring tools. This measurement method has the following disadvantages: ①The error of the detection result is large, and the accuracy cannot be guaranteed; ②The detection time is long, the work efficiency is low, and it takes up more manpower and material resources; ③The degree of automation is low, and it cannot meet the requirements of the motor vehicle management departme...

AI Technical Summary

Problems solved by technology

This measurement method has the following disadvantages: ①The error of the detection result is large, and the accuracy cannot be guaranteed; ②The detection time is long, the work efficiency is low, and it takes up more manpower and material resources; ③The degree of automation is low, and it cannot meet the requirements of the motor vehicle management department. Development needs of information management for motor vehicles

Although this technical solution can obtain the external dimensions of the motor vehicle, it also has shortcomings: ① Due to the limitation of the best viewing angle and shooting range of the camera, there is an error in the captured image of the external shape of the motor vehicle; ② In this technical solution, due to the lack of clear reference objects Parameters are corrected by the image, which causes errors in the detection results; ③ It is impossible to measure the important shape parameter of the wheelbase of the motor vehicle

[0004] Chengdu Zhicheng Automobile Insurance Testing Equipment Co., Ltd.’s patent application 200920079045.7 proposed “a fully automatic measuring device for measuring vehicle outline dimensions by acquiring images of moving vehicles” and patent application 200820140878.5 proposed “measurement of vehicle outline dimensions based on images acquired by moving vehicles Although these two technical solutions can realize the measurement of the external dimensions of the motor vehicle, the obvious shortcomings are: ① When the obtained vehicle cross-sectional images are deformed or distorted, the seamlessness between the images cannot be realized splicing, so that the vehicle outline size cannot be accurately calculated; ②Because the ground marks and facade marks are not clear, the process of processing and analyzing the obtained vehicle section images is complicated, which increases the difficulty of detection; ③The ground marks and facade marks are closely related to the The section of the tested vehicle is not in the same plane. When calculating the vehicle outline size, it is necessary to solve the problem of depth of field, which enlarges the error of the detection data result

Although this technical solution has progress compared with the above-mentioned technical solutions, there are still obvious deficiencies: ① There is an obvious mechanical motion error when using the mobile slide rail to drive the industrial digital camera to collect images, and this error is inevitable. To reduce the error, it must be increased The equipment cost is the premise, so it is difficult to realize; ②Due to the repeated movement of the industrial digital camera and the moving slide rail, the stability of the acquired image is not high, so there are errors when splicing the images frame by frame, which directly affects the accuracy of the detection results ③The maintenance work of mobile slide rails and industrial digital cameras is more complicated, and the requirements for equipment operators are very high; The high cost of digital cameras, and repeated movement shortens the life of the device, etc.

Images