Device and method for real-time three-dimensionally sensing safe driving of vehicle having mixed multi-visual information

Abstract

The invention discloses a device and a method for real-time three-dimensionally sensing safe driving of a vehicle having mixed multi-visual information. A video image collecting device is provided with six cameras; a main processor comprises a DSP subsystem and an APM subsystem; an SDRAM storage unit is connected with the main processor and an FPGA controller; the FPGA controller controls the collection of images around the vehicle, pre-treats the images and then stores in the SDRAM storage unit; the DSP subsystem reads images from the SDRAM storage unit, matches a frame image and rebuilds a three-dimensional scene; and the DSP subsystem synthesizes a predicted back track data and a rebuilt three-dimensional image and sends to a liquid crystal display in order to display. When a driver drives or backs a car, the phenomenon that a common backing device always has a blind area is completely avoided.

Description

technical field [0001] The invention relates to a real-time three-dimensional sensing device and method for safe driving of a vehicle with multi-visual information fusion, belonging to the field of intelligent image processing. Background technique [0002] With the development of the economy, there are more and more people with cars and more and more parking spaces. At the same time, the space for the car to turn is less and less, and the problem of the driver's difficulty in reversing is becoming more and more prominent. It is easy to touch other vehicles or buildings if you are not careful. Therefore, a variety of driving and reversing safety auxiliary devices have appeared on the market, such as reversing sensors, reversing visual system devices, etc., but these devices provide voice reminders and image display rear-view scenes, and some can only display the distance from the rear of the car. For the distance information of obstacles behind the vehicle, some only use th...

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to solve the problem that the existing vehicle-mounted visual monitoring device outputs the image and video information obtained by the 4-way camera around the vehicle body on the display in 2D without processing, low efficiency, insufficient accuracy, monitoring blind spots, and unintuitive etc., provide a multi-visual information fusion real-time three-dimensional perception device and method for vehicle safety driving, using intelligent image processing technology, real-time three-dimensional reconstruction of the acquired multi-channel vehicle body surrounding environment image video information, forming a real-time vehicle driving environment three-dimensional environment

Images