Scholarlink

This paper focuses on optimizing sensor data for enhanced obstacle detection, leveraging insights from two key sensors: the RGB-D depth camera and the 2D-Lidar sensor. Depth data is acquired using an enhanced obstacle detection algorithm, as previously introduced in our cited work. The algorithm employs a steering-based Region of Interest to effectively identify obstacles. Additionally, the Lidar range is constrained to \(30^{\circ}\) . To refine the acquired data, we employ a Kalman filter, optimizing it based on variance values. This process enhances the accuracy and reliability of the sensor data. Our contribution lies in presenting the optimized data obtained through the Kalman filter, showcasing its effectiveness in improving the overall performance of obstacle detection systems. This research underscores the significance of sensor data optimization and contributes to the broader field of autonomous systems by addressing challenges in obstacle detection, a critical aspect of autonomous navigation.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Dynamic Obstacle Detection and Depth Estimation for Autonomous Car

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Shobith Bankapur,
  • Sharatkumar Kondikoppa,
  • D. Shreyas,
  • Rohit Kalyani,
  • N. Praveen,
  • Nalini C. Iyer

摘要

This paper focuses on optimizing sensor data for enhanced obstacle detection, leveraging insights from two key sensors: the RGB-D depth camera and the 2D-Lidar sensor. Depth data is acquired using an enhanced obstacle detection algorithm, as previously introduced in our cited work. The algorithm employs a steering-based Region of Interest to effectively identify obstacles. Additionally, the Lidar range is constrained to \(30^{\circ}\) . To refine the acquired data, we employ a Kalman filter, optimizing it based on variance values. This process enhances the accuracy and reliability of the sensor data. Our contribution lies in presenting the optimized data obtained through the Kalman filter, showcasing its effectiveness in improving the overall performance of obstacle detection systems. This research underscores the significance of sensor data optimization and contributes to the broader field of autonomous systems by addressing challenges in obstacle detection, a critical aspect of autonomous navigation.