Unmanned vehicle-mounted intelligent camera in-loop test method and device

Abstract

The invention discloses an unmanned vehicle-mounted intelligent camera in-loop test method and device. The device comprises a box body and a box cover; an LED display screen is arranged on the box body; a fan accommodating device and an LED illuminating lamp accommodating device are arranged on each of the two sides; a water storage box is arranged below the rear end; a guide rail, a graduated scale and a water collecting tank are longitudinally arranged on the bottom surface, a sliding block is arranged on the guide rail, a threaded rod is fixedly connected to the central position of the sliding block, and the upper end of the threaded rod is inserted into a camera fixing disc through a height adjusting disc. The test method tests the performance of the intelligent camera under differentweather conditions by simulating the weather environment in a real scene. The test method and device provided by the invention can realize indoor test of the performance of the intelligent camera, andthe test method is simple, the test device is convenient to install, the cost is relatively low, the work is safe and reliable, and the generalizability is relatively high.

Description

technical field [0001] The invention belongs to the technical field of unmanned driving, and in particular relates to a method and device for in-loop testing of an unmanned vehicle-mounted intelligent camera. Background technique [0002] With the development of automotive intelligent network technology, all countries in the world have regarded the development of driverless vehicles as an important strategic reserve. Especially in recent years, the rapid development of machine learning and deep learning technology has greatly promoted the process of unmanned vehicles. 3D map reconstruction is one of the most important technologies in the field of unmanned driving. Mainstream unmanned vehicles generally use multi-line radar as a 3D sensor to realize this technology. However, radar equipment is expensive, and can only recognize depth information, cannot obtain texture and color, and has insufficient perception of surroundings. [0003] Using cameras for stereo matching and o...

AI Technical Summary

Problems solved by technology

[0006] 1. The test of the camera manufacturer is to test the parameters of the camera. It is difficult to guarantee that it can meet the performance requirements of the driverless car.

[0007] 2. Car manufacturers spend a lot of manpower, material and financial resources on the actual vehicle test of the camera, which takes a long time and is dangerous

[0008] 3. When the camera is used on location, due to the limitations of external light, weather conditions and test sites, the actual vehicle test is difficult to meet various test scenarios and working conditions, and the operation is complicated

Images