Aiming at the obtained 3D point cloud data, there are a large amount of noise and the loss of local details in the process of data processing, an improved deep learning network based on PCPNET was proposed for effectively denoising. In the encoder, the feature enhancement module is used to fully explore the potential local geometric features of the noisy point cloud, process the point clouds of different scales, and design the corresponding loss function to feed back the network, optimize the network performance, and achieve the purpose of point cloud denoising, which is conducive to improving the registration accuracy of 3D point cloud in the future. Experimental results show that compared with traditional methods, the proposed method has better denoising effect, has a certain robustness to different noises, and can effectively retain local edge information.
Using the satellite characterization information obtained by the space-based platform, the key parts of the satellite, such as solar panels, satellite payload, and propulsion systems, are segmented. The target object segmented from the point cloud data is significant to improve the accuracy of subsequent point cloud registration and attitude recognition. In this study, we introduced TSNet, which has the following characteristics. 1) The continuous recursive gate convolution module (gnConv) is introduced into the network, which can improve the accuracy of point cloud segmentation. 2) The weight channel for feature transfer is designed to avoid global information loss. The mIoU value of TSNet laser point cloud segmentation reached 88.12%, which was better than common point cloud segmentation algorithms, such as PointNet, PointNet++ and DGCNN. The proposed method can provide more accurate perception information for ground control personnel.
Range-gated technique is useful for improving the accuracy of 3D target attitude measurements. The 3D super-resolution range-gated imaging technique and 3D inversion algorithm are introduced. In this paper, the characteristics of high-speed moving targets are analyzed. Nanosecond sensor gate is selected to capture instantaneous images to eliminate the effect of target movement. Based on this design, a dual-camera range-gated imaging measurement system is analyzed. Through imaging experiments on different targets, the system is feasible and for a target 20m away, the root-mean-square error of the measurement is 0.69cm. At the same time, the possible errors caused by the introduction of dual camera system and a reasonable solution is analyzed. The results show that the proposed system can effectively measure the 3D attitude information of high-speed moving targets, improve the ranging accuracy, meet the requirements of real-time 3D imaging, and provide a basis for subsequent data processing and ranging performance improvement.
Aiming at the problem of moving targets by the laser active imaging system, a laser active imaging technology based on random coding is proposed. The laser pulse coding is used to replace the shuttle coding exposure, combining the random coding exposure imaging technique with the active range-gated laser imaging technique. In the coded exposure mode, when imaging a moving target, the pulsed laser and ICCD image intensifier are synchronously gated based on FPGA, to obtain the encoded exposure image. And the blurred images are recovered based on LO regularization, which improves the laser active imaging quality. According to the laser active imaging theory, the image signal-to-noise ratio in pulse code modulation mode is analyzed, which shows that the pulse random coding technology can effectively improve the brightness of the imaging image, improve the image signal-to-noise ratio, and have a certain inhibitory effect on motion blur. The blurred image restoration effect under the 31-bit coding length was simulated and analyzed, and the imaging effect and applicability conditions of the typical parameter laser imaging system on moving targets under the coding pulse system were analyzed. Compared with other deblurring methods, under the condition of pulse coding accuracy of 5ns, the 31-bit coding length can achieve better blurred image restoration for the target of relative speed of 10m/s.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.