YOLO and K-Means Based 3D Object Detection Method on Image and Point Cloud

TL;DR

This paper presents a real-time 3D object detection method combining YOLO for 2D detection and k-means clustering for 3D point cloud segmentation, optimized for GPU processing in autonomous driving.

Contribution

It introduces a novel integration of YOLO-based 2D detection with k-means clustering for efficient 3D object recognition from Lidar and camera data.

Findings

Achieves high-speed 3D detection on GPU

Combines 2D YOLO detection with 3D point cloud segmentation

Enables real-time autonomous driving applications

Abstract

Lidar based 3D object detection and classification tasks are essential for automated driving(AD). A Lidar sensor can provide the 3D point coud data reconstruction of the surrounding environment. But the detection in 3D point cloud still needs a strong algorithmic challenge. This paper consists of three parts.(1)Lidar-camera calib. (2)YOLO, based detection and PointCloud extraction, (3) k-means based point cloud segmentation. In our research, Camera can capture the image to make the Real-time 2D Object Detection by using YOLO, I transfer the bounding box to node whose function is making 3d object detection on point cloud data from Lidar. By comparing whether 2D coordinate transferred from the 3D point is in the object bounding box or not, and doing a k-means clustering can achieve High-speed 3D object recognition function in GPU.