scholarly journals Efficient 3D object tracking approach based on convolutional neural network and Monte Carlo algorithms used for a pick and place robot

2019 ◽  
Author(s):  
Yan Zhang ◽  
Chen Zhang ◽  
Rico Nestler ◽  
Maik Rosenberger ◽  
Gunther Notni
Keyword(s):  
Neural Network ◽  
Monte Carlo ◽  
Convolutional Neural Network ◽  
Object Tracking ◽  
3D Object ◽  
Monte Carlo Algorithms ◽  
Pick And Place

scholarly journals Multiple Pedestrians and Vehicles Tracking in Aerial Imagery Using a Convolutional Neural Network

2021 ◽  
Vol 13 (10) ◽  
pp. 1953
Author(s):  
Seyed Majid Azimi ◽  
Maximilian Kraus ◽  
Reza Bahmanyar ◽  
Peter Reinartz
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Object Tracking ◽  
Short Term Memory ◽  
Aerial Imagery ◽  
Future Research ◽  
Short Term ◽  
Term Memory ◽  
Long Short Term Memory

In this paper, we address various challenges in multi-pedestrian and vehicle tracking in high-resolution aerial imagery by intensive evaluation of a number of traditional and Deep Learning based Single- and Multi-Object Tracking methods. We also describe our proposed Deep Learning based Multi-Object Tracking method AerialMPTNet that fuses appearance, temporal, and graphical information using a Siamese Neural Network, a Long Short-Term Memory, and a Graph Convolutional Neural Network module for more accurate and stable tracking. Moreover, we investigate the influence of the Squeeze-and-Excitation layers and Online Hard Example Mining on the performance of AerialMPTNet. To the best of our knowledge, we are the first to use these two for regression-based Multi-Object Tracking. Additionally, we studied and compared the L1 and Huber loss functions. In our experiments, we extensively evaluate AerialMPTNet on three aerial Multi-Object Tracking datasets, namely AerialMPT and KIT AIS pedestrian and vehicle datasets. Qualitative and quantitative results show that AerialMPTNet outperforms all previous methods for the pedestrian datasets and achieves competitive results for the vehicle dataset. In addition, Long Short-Term Memory and Graph Convolutional Neural Network modules enhance the tracking performance. Moreover, using Squeeze-and-Excitation and Online Hard Example Mining significantly helps for some cases while degrades the results for other cases. In addition, according to the results, L1 yields better results with respect to Huber loss for most of the scenarios. The presented results provide a deep insight into challenges and opportunities of the aerial Multi-Object Tracking domain, paving the way for future research.

Real-Time 3D object detection using improved convolutional neural network based on image-driven point cloud

2021 ◽  
Vol 14 ◽  
Author(s):  
Zhiyong Gao ◽  
Jianhong Xiang
Keyword(s):  
Neural Network ◽  
Object Detection ◽  
Convolutional Neural Network ◽  
Real Time ◽  
Point Cloud ◽  
Point Clouds ◽  
3D Point Cloud ◽  
3D Object ◽  
3D Object Detection ◽  
Instance Segmentation

Background: While detecting the object directly from the 3D point cloud, the natural 3D patterns and invariance of 3D data are often obscure. Objective: In this work, we aimed at studying the 3D object detection from discrete, disordered and sparse 3D point clouds. Methods: The CNN is composed of the frustum sequence module, 3D instance segmentation module S-NET, 3D point cloud transformation module T-NET, and 3D boundary box estimation module E-NET. The search space of the object is determined by the frustum sequence module. The instance segmentation of the point cloud is performed by the 3D instance segmentation module. The 3D coordinates of the object are confirmed by the transformation module and the 3D bounding box estimation module. Results: Evaluated on KITTI benchmark dataset, our method outperforms the state of the art by remarkable margins while having real-time capability. Conclusion: We achieve real-time 3D object detection by proposing an improved convolutional neural network (CNN) based on image-driven point clouds.

scholarly journals 3D Object Detection Algorithm for Panoramic Images With Multi-Scale Convolutional Neural Network

IEEE Access ◽  
2019 ◽  
Vol 7 ◽  
pp. 171461-171470
Author(s):  
Dianwei Wang ◽  
Yanhui He ◽  
Ying Liu ◽  
Daxiang Li ◽  
Shiqian Wu ◽  
...  
Keyword(s):  
Neural Network ◽  
Object Detection ◽  
Convolutional Neural Network ◽  
Detection Algorithm ◽  
3D Object ◽  
Multi Scale ◽  
Panoramic Images ◽  
3D Object Detection

CNNTracker: Online discriminative object tracking via deep convolutional neural network

2016 ◽  
Vol 38 ◽  
pp. 1088-1098 ◽  
Author(s):  
Yan Chen ◽  
Xiangnan Yang ◽  
Bineng Zhong ◽  
Shengnan Pan ◽  
Duansheng Chen ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Object Tracking ◽  
Deep Convolutional Neural Network

scholarly journals Monte Carlo Dose Calculation Using MRI Based Synthetic CT Generated by Fully Convolutional Neural Network for Gamma Knife Radiosurgery

2021 ◽  
Vol 20 ◽  
pp. 153303382110464
Author(s):  
Jiankui Yuan ◽  
Elisha Fredman ◽  
Jian-Yue Jin ◽  
Serah Choi ◽  
David Mansur ◽  
...  
Keyword(s):  
Neural Network ◽  
Monte Carlo ◽  
Convolutional Neural Network ◽  
Gamma Knife ◽  
Learning Algorithm ◽  
Gamma Knife Radiosurgery ◽  
Dice Similarity Coefficient ◽  
Mr Images ◽  
The Difference ◽  
Synthetic Ct

The aim of this work is to study the dosimetric effect from generated synthetic computed tomography (sCT) from magnetic resonance (MR) images using a deep learning algorithm for Gamma Knife (GK) stereotactic radiosurgery (SRS). The Monte Carlo (MC) method is used for dose calculations. Thirty patients were retrospectively selected with our institution IRB’s approval. All patients were treated with GK SRS based on T1-weighted MR images and also underwent conventional external beam treatment with a CT scan. Image datasets were preprocessed with registration and were normalized to obtain similar intensity for the pairs of MR and CT images. A deep convolutional neural network arranged in an encoder–decoder fashion was used to learn the direct mapping from MR to the corresponding CT. A number of metrics including the voxel-wise mean error (ME) and mean absolute error (MAE) were used for evaluating the difference between generated sCT and the true CT. To study the dosimetric accuracy, MC simulations were performed based on the true CT and sCT using the same treatment parameters. The method produced an MAE of 86.6 ± 34.1 Hundsfield units (HU) and a mean squared error (MSE) of 160.9 ± 32.8. The mean Dice similarity coefficient was 0.82 ± 0.05 for HU > 200. The difference for dose-volume parameter D95 between the ground true dose and the dose calculated with sCT was 1.1% if a synthetic CT-to-density table was used, and 4.9% compared with the calculations based on the water-brain phantom.

scholarly journals A Monte Carlo Simulation Approach in Non-linear Structural Dynamics Using Convolutional Neural Networks

2021 ◽  
Vol 7 ◽  
Author(s):  
Franz Bamer ◽  
Denny Thaler ◽  
Marcus Stoffel ◽  
Bernd Markert
Keyword(s):  
Neural Network ◽  
Monte Carlo Simulation ◽  
Monte Carlo ◽  
Convolutional Neural Network ◽  
Ground Motion ◽  
Structural Response ◽  
Structural Failure ◽  
Non Linear ◽  
Time Histories ◽  
Sample Set

The evaluation of the structural response statistics constitutes one of the principal tasks in engineering. However, in the tail region near structural failure, engineering structures behave highly non-linear, making an analytic or closed form of the response statistics difficult or even impossible. Evaluating a series of computer experiments, the Monte Carlo method has been proven a useful tool to provide an unbiased estimate of the response statistics. Naturally, we want structural failure to happen very rarely. Unfortunately, this leads to a disproportionately high number of Monte Carlo samples to be evaluated to ensure an estimation with high confidence for small probabilities. Thus, in this paper, we present a new Monte Carlo simulation method enhanced by a convolutional neural network. The sample-set used for this Monte Carlo approach is provided by artificially generating site-dependent ground motion time histories using a non-linear Kanai-Tajimi filter. Compared to several state-of-the-art studies, the convolutional neural network learns to extract the relevant input features and the structural response behavior autonomously from the entire time histories instead of learning from a set of hand-chosen intensity inputs. Training the neural network based on a chosen input sample set develops a meta-model that is then used as a meta-model to predict the response of the total Monte Carlo sample set. This paper presents two convolutional neural network-enhanced strategies that allow for a practical design approach of ground motion excited structures. The first strategy enables for an accurate response prediction around the mean of the distribution. It is, therefore, useful regarding structural serviceability. The second strategy enables for an accurate prediction around the tail end of the distribution. It is, therefore, beneficial for the prediction of the probability of failure.

Sign in / Sign up

Export Citation Format

Share Document