Multi-sensor-based vehicle-mounted environment recognition system and omni-directional vision module

Abstract

The invention discloses a multi-sensor-based vehicle-mounted environment recognition system. The system comprises an omni-directional vision module, an IMU module, a GPS module, a radar module and a data fusion module, wherein the omni-directional vision module is used for acquiring environment three-dimensional information in a 360-degree range around a vehicle, the IMU module is used for acquiring accelerated speed and angular speed information of the vehicle, the GPS module and the IMU module jointly work to acquire position and posture information of the vehicle, the radar module is used for acquiring front target position information of the vehicle and has the characteristics of all weather and all time, and the data fusion module is used for fusing environment information acquired by each sensor to more accurately recognize a vehicle driving environment. The invention further discloses an omni-directional vision module, which utilizes each stepping motor to control a corresponding binocular camera to perform a pitching motion in order to acquire omni-directional scene images of an observed environment; and an image processing module is used for in real time collecting and processing scene images acquired by each group of the binocular cameras.

Description

technical field [0001] The invention relates to a multi-camera mosaic omnidirectional vision device and a multi-sensor-based vehicle environment recognition system, belonging to the field of sensor technology. Background technique [0002] Monocular vision can perform simple target tracking and target recognition, but it cannot provide the depth information of the environment. Binocular vision realizes the acquisition of depth information on the basis of monocular vision, but it cannot obtain all-round information in real time. Compared with the shortcomings of traditional vision sensors in terms of limited field of view, omnidirectional vision devices can obtain all-round environmental information in real time, and play an active role in military applications, public safety, video conferencing, and location environment detection. Simultaneous shooting of multiple imaging devices at multiple angles is the most conceivable technology for all-round image acquisition. Compared...

AI Technical Summary

Problems solved by technology

[0004] The invention provides an omnidirectional visual module, which is an omnidirectional visual device spliced ​​by multiple cameras, which solves the problem that traditional visual sensors cannot acquire omnidirectional environmental information in real time

Images