Object Recognition Based Interpolation With 3D LIDAR and Vision for Autonomous Driving of an Intelligent Vehicle

Abstract

An algorithm has been developed for fusing 3D LIDAR (Light Detection and Ranging) systems that receive objects detected in deep learning-based image sensors and object data in the form of 3D point clouds. 3D LIDAR represents 3D point data in a planar rectangular coordinate system with a 360 • representation of the detected object surface, including the front face. However, only the direction and distance data of the object can be obtained, and point cloud data cannot be used to create a specific definition of the object. Therefore, only the movement of the point cloud data can be tracked using probability and classification algorithms based on image processing. To overcome this limitation, the study matches 3D LIDAR data with 2D image data through the fusion of hybrid level multi-sensors. First, because 3D LIDAR data represents all objects in the sensor's detection range as dots, all unnecessary data, including ground data, is filtered out. The 3D Random Sample Consensus (RANSAC) algorithm enables the extraction of ground data perpendicular to the reference estimation 3D plane and data at both ends through ground estimation. Classified environmental data facilitates the labeling of all objects within the viewing angle of 3D LIDAR based on the presence or absence of movement. The path of motion of the platform can be established by detecting whether objects within the region of interest are movable or static. Because LIDAR is based on 8-and 16-channel rotation mechanisms, real-time data cannot be used to define objects. Instead, point clouds can be used to detect obstacles in the image through deep learning in the preliminary processing phase of the classification algorithm. By matching the labeling information of defined objects with the classified object cloud data obtained using 3D LIDAR, the exact dynamic trajectory and position of the defined objects can be calculated. Consequently, to process the acquired object data efficiently, we devised an active-region-ofinterest technique to ensure a fast processing speed while maintaining a high detection rate.

YOLOv4Tiny: Bearing Angle Based Pose Estimation and Semantic Segmentation For 3D Object Detection From LiDAR Point Cloud & RGB-D Data

“…The random sample consensus algorithm (RANSAC) was proposed in [39] for performing segmentation for both 3D LiDAR and 2D images. Noise removal and feature fusion were performed in this work in which YOLO was used to perform classification.…”

3D Recognition Based on Sensor Modalities for Robotic Systems: A Survey

“…With the recent monumental innovations in sensor technology, a wide variety of DL-based 3D object [25][26][27][28] and place recognition approaches [29][30][31] have been developed for different types of sensors. LiDAR and camera are two frequently used and increasingly popular sensors [32] that have been employed for object and place recognition in robotic systems.…”

Spherically Stratified Point Projection: Feature Image Generation for Object Classification Using 3D LiDAR Data

“…The safety of the path traveled by an autonomous vehicle and its ability to avoid obstacles depend on the accurate classification of objects surrounding the vehicle [ 3 ]. Apart from autonomous driving, object classification is necessary for various applications and represents the basis for object recognition [ 4 , 5 ].…”