Abstract
Signals, such as point clouds captured by light detection and ranging sensors, are often affected by highly reflective objects, including specular opaque and transparent materials, such as glass, mirrors, and polished metal, which produce reflection artifacts, thereby degrading the performance of associated computer vision techniques. In traditional noise filtering methods for point clouds, noise is detected by considering the distribution of the neighboring points. However, noise generated by reflected areas is quite dense and cannot be removed by considering the point distribution. Therefore, this paper proposes a noise removal method to detect dense noise points caused by reflected objects using multi-position sensing data comparison. The proposed method is divided into three steps. First, the point cloud data are converted to range images of depth and reflective intensity. Second, the reflected area is detected using a sliding window on two converted range images. Finally, noise is filtered by comparing it with the neighbor sensor data between the detected reflected areas. Experiment results demonstrate that, unlike conventional methods, the proposed method can better filter dense and large-scale noise caused by reflective objects. In future work, we will attempt to add the RGB image to improve the accuracy of noise detection.
Highlights
Light detection and ranging (LiDAR) sensors are high-precision sensors, which involve transmitting laser light to targets and measuring the reflected light to determine the difference in the wavelength and time of arrival of the reflected light [1]
LiDAR measures the position and the shape of objects and forms high-quality 3-D point clouds; it has been widely adopted in 3-D reconstruction, self-driving cars, robotics, and various fields [2,3,4,5,6,7,8,9]
When capturing large-scale 3-D point clouds using LiDAR sensors, laser pulses emitted from the scanner result in the formation of undesired reflection artifacts and virtual points in the 3-D space
Summary
Light detection and ranging (LiDAR) sensors are high-precision sensors, which involve transmitting laser light to targets and measuring the reflected light to determine the difference in the wavelength and time of arrival of the reflected light [1]. When capturing large-scale 3-D point clouds using LiDAR sensors, laser pulses emitted from the scanner result in the formation of undesired reflection artifacts and virtual points in the 3-D space. The LiDAR sensor measures the distance from the scanner to the target object by emitting laser pulses and receiving their return pulses based on the propagation time of light. In this case, the laser is reflected to other objects because of the reflective nature of the glass when the sensor emits the laser light onto the glass
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have