Anti-shake ranging method, device and electronic equipment for monocular adas

Abstract

The present application relates to an anti-shake ranging method, device and electronic equipment for monocular ADAS. According to one embodiment, there is provided a method for determining the shake amount of a vehicle, comprising: using a vehicle-mounted camera to obtain multiple frames of images of the surrounding environment of the vehicle; determining the first shake of the vehicle based on the multiple frames of images; using an inertial measurement unit ( an IMU) to determine a second shake of the vehicle; and fusing the first shake and the second shake to determine the shake of the vehicle. By determining the amount of shaking of the vehicle, errors due to shaking can be compensated during monocular vision ranging, resulting in more accurate ranging.

Description

technical field [0001] The present application generally relates to the field of driver assistance (ADAS), and more particularly, relates to a method, device and electronic device for monocular ADAS visual ranging and anti-shake based on an inertial measurement unit (IMU). Background technique [0002] In recent years, autonomous driving, or Advanced Driver Assistance Systems (ADAS), has received extensive attention and intense research. The ADAS system needs to use various on-board sensors to perceive the various states of the vehicle itself and the surrounding environment, so as to make driving strategy decisions, and finally realize the automatic driving function. Examples of such on-vehicle sensors include cameras, lidar, ultrasonic radar, etc., where cameras, also called on-vehicle cameras, are widely used due to their low price and ability to perform multiple functions. For example, the camera can be used for visual distance measurement for collision avoidance, lane t...

AI Technical Summary

Problems solved by technology

However, these methods have certain drawbacks

Due to the different types of vehicles and the large difference in vehicle width, the vehicle distance calculated based on the width of the vehicle in the image may have poor accuracy

In addition, this method is also easily affected by the internal parameters of the camera, the actual distance, etc., so the error is large

For the second type of method, the relative position can be used to measure the distance of vehicles of different models. However, the relative position of the front vehicle in the image will be affected by the ups and downs of the vehicle, especially for the relative position of the farther vehicle. Big

Images