Three-Dimensional Object Co-Localization From Mobile LiDAR Point Clouds

2021 ◽  
Vol 22 (4) ◽  
pp. 1996-2007
Author(s):  
Wenzhong Guo ◽  
Jiawei Chen ◽  
Weipeng Wang ◽  
Huan Luo ◽  
Shiping Wang
Keyword(s):  
Three Dimensional ◽  
Point Clouds ◽  
Dimensional Object

Three-Dimensional Object Matching in Mobile Laser Scanning Point Clouds

2015 ◽  
Vol 12 (3) ◽  
pp. 492-496 ◽  
Author(s):  
Yongtao Yu ◽  
Jonathan Li ◽  
Haiyan Guan ◽  
Fukai Jia ◽  
Cheng Wang
Keyword(s):  
Laser Scanning ◽  
Three Dimensional ◽  
Point Clouds ◽  
Object Matching ◽  
Dimensional Object

scholarly journals Learning Deformable Network for 3D Object Detection on Point Clouds

2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Wanyi Zhang ◽  
Xiuhua Fu ◽  
Wei Li
Keyword(s):  
Object Detection ◽  
Point Cloud ◽  
Three Dimensional ◽  
Ground Truth ◽  
Point Clouds ◽  
Detection Accuracy ◽  
3D Object ◽  
Cloud Data ◽  
Dimensional Object ◽  
3D Object Detection

3D object detection based on point cloud data in the unmanned driving scene has always been a research hotspot in unmanned driving sensing technology. With the development and maturity of deep neural networks technology, the method of using neural network to detect three-dimensional object target begins to show great advantages. The experimental results show that the mismatch between anchor and training samples would affect the detection accuracy, but it has not been well solved. The contributions of this paper are as follows. For the first time, deformable convolution is introduced into the point cloud object detection network, which enhances the adaptability of the network to vehicles with different directions and shapes. Secondly, a new generation method of anchor in RPN is proposed, which can effectively prevent the mismatching between the anchor and ground truth and remove the angle classification loss in the loss function. Compared with the state-of-the-art method, the AP and AOS of the detection results are improved.

Reconstruction of Objects from their Projections Using Orthogonal Functions

1973 ◽  
Vol 31 ◽  
pp. 268-269
Author(s):  
Elrnar Zeitler
Keyword(s):  
Unit Area ◽  
Three Dimensional ◽  
One Dimension ◽  
Spatial Density ◽  
Dimensional Representation ◽  
Orthogonal Functions ◽  
Object A ◽  
Plane Normal ◽  
Dimensional Object ◽  
Spatial Density Distribution

Considering any finite three-dimensional object, a “projection” is here defined as a two-dimensional representation of the object's mass per unit area on a plane normal to a given projection axis, here taken as they-axis. Since the object can be seen as being built from parallel, thin slices, the relation between object structure and its projection can be reduced by one dimension. It is assumed that an electron microscope equipped with a tilting stage records the projectionWhere the object has a spatial density distribution p(r,ϕ) within a limiting radius taken to be unity, and the stage is tilted by an angle 9 with respect to the x-axis of the recording plane.

scholarly journals Multi-Dimensional Underwater Point Cloud Detection Based on Deep Learning

Sensors ◽  
2021 ◽  
Vol 21 (3) ◽  
pp. 884
Author(s):  
Chia-Ming Tsai ◽  
Yi-Horng Lai ◽  
Yung-Da Sun ◽  
Yu-Jen Chung ◽  
Jau-Woei Perng
Keyword(s):  
Deep Learning ◽  
Point Cloud ◽  
Three Dimensional ◽  
Point Clouds ◽  
Training Data ◽  
Network Architectures ◽  
Point Cloud Data ◽  
Data Types ◽  
Raw Data ◽  
Cloud Data

Numerous sensors can obtain images or point cloud data on land, however, the rapid attenuation of electromagnetic signals and the lack of light in water have been observed to restrict sensing functions. This study expands the utilization of two- and three-dimensional detection technologies in underwater applications to detect abandoned tires. A three-dimensional acoustic sensor, the BV5000, is used in this study to collect underwater point cloud data. Some pre-processing steps are proposed to remove noise and the seabed from raw data. Point clouds are then processed to obtain two data types: a 2D image and a 3D point cloud. Deep learning methods with different dimensions are used to train the models. In the two-dimensional method, the point cloud is transferred into a bird’s eye view image. The Faster R-CNN and YOLOv3 network architectures are used to detect tires. Meanwhile, in the three-dimensional method, the point cloud associated with a tire is cut out from the raw data and is used as training data. The PointNet and PointConv network architectures are then used for tire classification. The results show that both approaches provide good accuracy.

Robotic motion compensation for bone movement, using ultrasound images

2015 ◽  
Vol 42 (5) ◽  
pp. 466-474 ◽  
Author(s):  
P.M.B. Torres ◽  
P. J. S. Gonçalves ◽  
J.M.M. Martins
Keyword(s):  
Motion Compensation ◽  
Optical Measurement ◽  
Three Dimensional ◽  
Point Clouds ◽  
Robotic System ◽  
Ultrasound Images ◽  
Bone Drilling ◽  
Content Type ◽  
3D Point Clouds ◽  
Robotic Motion

Purpose – The purpose of this paper is to present a robotic motion compensation system, using ultrasound images, to assist orthopedic surgery. The robotic system can compensate for femur movements during bone drilling procedures. Although it may have other applications, the system was thought to be used in hip resurfacing (HR) prosthesis surgery to implant the initial guide tool. The system requires no fiducial markers implanted in the patient, by using only non-invasive ultrasound images. Design/methodology/approach – The femur location in the operating room is obtained by processing ultrasound (USA) and computer tomography (CT) images, obtained, respectively, in the intra-operative and pre-operative scenarios. During surgery, the bone position and orientation is obtained by registration of USA and CT three-dimensional (3D) point clouds, using an optical measurement system and also passive markers attached to the USA probe and to the drill. The system description, image processing, calibration procedures and results with simulated and real experiments are presented and described to illustrate the system in operation. Findings – The robotic system can compensate for femur movements, during bone drilling procedures. In most experiments, the update was always validated, with errors of 2 mm/4°. Originality/value – The navigation system is based entirely on the information extracted from images obtained from CT pre-operatively and USA intra-operatively. Contrary to current surgical systems, it does not use any type of implant in the bone to track the femur movements.

Sign in / Sign up

Export Citation Format

Share Document