3d detection method, device, medium and vehicle based on fisheye camera

By establishing a horizontal coordinate system in the fisheye camera and predicting only the yaw angle, the problems of high prediction complexity and large error in fisheye camera 3D detection are solved, and efficient and accurate 3D target detection is achieved.

CN115937166BActive Publication Date: 2026-06-12安徽蔚来智驾科技有限公司

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
安徽蔚来智驾科技有限公司
Filing Date
2022-12-20
Publication Date
2026-06-12

AI Technical Summary

Technical Problem

The mounting method of fisheye cameras results in the 3D bounding box of objects in their camera coordinate system containing pitch and roll angles. Existing methods that directly predict yaw angles will produce large deviations, and predicting three Euler angles at the same time increases the complexity of the model and makes it difficult to correlate with the appearance of the image.

Method used

Establish a horizontal coordinate system that coincides with the origin of the fisheye camera's coordinate system. Predict only the yaw angle. Transform the yaw angle in the radar coordinate system to the horizontal coordinate system using a rotation matrix. Train a 3D detection model to obtain the target's 3D bounding box.

🎯Benefits of technology

While ensuring prediction accuracy, it reduces model complexity and makes 3D detection results easy to correlate with image appearance, eliminating errors caused by ignoring pitch and roll angles.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
Patent Text Reader

Abstract

The present application relates to the technical field of auxiliary driving, and particularly provides a 3D detection method and device based on a fisheye camera, a medium and a vehicle, aiming to solve the problem of how to effectively reduce the complexity of a prediction model while ensuring the accuracy of a 3D detection process based on a fisheye camera. To this end, the present application pre-establishes a horizontal coordinate system, which coincides with the origin of the camera coordinate system of the fisheye camera and is parallel to the ground plane formed by the x-axis and the z-axis. When a 3D detection model is applied to 3D target detection of image data collected by the fisheye camera, only the yaw angle of the horizontal coordinate system needs to be predicted, without simultaneously predicting the yaw angle, the pitch angle and the roll angle, thereby effectively reducing the complexity of model prediction while ensuring the prediction accuracy, and the obtained 3D detection result is also easier to be associated with the appearance in the image.
Need to check novelty before this filing date? Find Prior Art