Multiple target localization with lidar-camera sensor fusion

The ability to detect and position multiple targets is a crucial aspect of numerous fields, including industry, defence, healthcare, and more. In many systems, it is essential to accurately identify and locate multiple targets with high precision, particularly in autonomous navigation and driving, robotics and computer vision, security systems, and industrial automation. This study aims to develop a method for detecting and simultaneously positioning multiple targets. An artificial neural network is employed to achieve simultaneous detection of multiple targets. The data from different sensors is used for the 2D and 3D positioning of the detected targets. In the 3D positioning process, a single sensor data was used, while in the 2D positioning process, positioning was performed by fusion of two sensors. The data obtained from the sensors used were processed with similar methods, and the results obtained were compared with each other and with real values. The sensors and the proposed methods have been studied in real time. The processing of sensor data using the proposed methods yielded results that were found to be in close proximity to the actual values when it came to the detection and positioning of multiple targets.