scholarly journals Bayesian Localization in Real-Time using Probabilistic Maps and Unscented-Kalman-Filters

2021 ◽  
Author(s):  
Wael Farag ◽  
Keyword(s):  
Particle Filter ◽  
Real Time ◽  
High Performance ◽  
Unscented Kalman Filter ◽  
Spatial Clustering ◽  
Computational Cost ◽  
Measurement Data ◽  
High Definition ◽  
Probabilistic Maps ◽  
Reference Map

In this paper, based on the fusion of Lidar and Radar measurement data, high-definition probabilistic maps, and a tailored particle filter, a Real-Time Monte Carlo Localization (RT_MCL) method for autonomous cars is proposed. The lidar and radar devices are installed on the ego car, and a customized Unscented Kalman Filter (UKF) is used for their data fusion. Lidars are accurate in determining objects' positions and have a much higher spatial resolution. On the other hand, Radars are more accurate in measuring objects velocities and perform well in extreme weather conditions. Therefore, the merits of both sensors are combined using the UKF to provide pole-like static-objects pose estimations that are well suited to serve as landmarks for vehicle localization in urban environments. These pose estimations are then clustered using the Grid-Based Density-Based Spatial Clustering of Applications with Noise (GB-DBSCAN) algorithm to represent each pole landmarks in the form of a source-point model to reduce computational cost and memory requirements. A reference map that includes pole landmarks is generated off-line and extracted from a 3-D lidar to be used by a carefully designed Particle Filter (PF) for accurate ego-car localization. The particle filter is initialized by the combined GPS+IMU reading and used an ego-car motion model to predict the states of the particles. The data association between the estimated landmarks by the UKF and that in the reference map is performed using Iterative Closest Point (ICP) algorithm. The proposed pipeline is implemented using the high-performance language C++ and utilizes highly optimized math and optimization libraries for best real-time performance. Extensive simulation studies have been carried out to evaluate the performance of the RT_MCL in both longitudinal and lateral localization.

Lidar and radar fusion for real-time road-objects detection and tracking

2021 ◽  
pp. 1-14
Author(s):  
Wael Farag
Keyword(s):  
Kalman Filter ◽  
Real Time ◽  
High Performance ◽  
Clustering Algorithm ◽  
Unscented Kalman Filter ◽  
Spatial Clustering ◽  
Measurement Data ◽  
Autonomous Driving ◽  
Geometrical Shape ◽  
Detection And Tracking

In this paper, based on the fusion of Lidar and Radar measurement data, a real-time road-Object Detection and Tracking (LR_ODT) method for autonomous driving is proposed. The lidar and radar devices are installed on the ego car, and a customized Unscented Kalman Filter (UKF) is used for their data fusion. Lidars are accurate in determining objects’ positions but significantly less accurate on measuring their velocities. However, Radars are more accurate on measuring objects velocities but less accurate on determining their positions as they have a lower spatial resolution. Therefore, the merits of both sensors are combined using the proposed fusion approach to provide both pose and velocity data for objects moving in roads precisely. The Grid-Based Density-Based Spatial Clustering of Applications with Noise (GB-DBSCAN) clustering algorithm is used to detect objects and estimate their centroids from the lidar and radar raw data. Then, the estimation of the object’s velocity as well as determining its corresponding geometrical shape is performed by the RANdom SAmple Consensus (RANSAC) algorithm. The proposed technique is implemented using the high-performance language C+⁣+ and utilizes highly optimized math and optimization libraries for best real-time performance. The performance of the UKF fusion is compared to that of the Extended Kalman Filter fusion (EKF) showing its superiority. Simulation studies have been carried out to evaluate the performance of the LR_ODT for tracking bicycles, cars, and pedestrians.

scholarly journals Road-objects tracking for autonomous driving using lidar and radar fusion

2020 ◽  
Vol 71 (3) ◽  
pp. 138-149
Author(s):  
Wael Farag
Keyword(s):  
Kalman Filter ◽  
Real Time ◽  
High Performance ◽  
Clustering Algorithm ◽  
Unscented Kalman Filter ◽  
Spatial Clustering ◽  
Measurement Data ◽  
Autonomous Driving ◽  
Geometrical Shape ◽  
Dbscan Clustering

AbstractIn this paper, based on the fusion of Lidar and Radar measurement data, a real-time road-Object Detection and Tracking (LR_ODT) method for autonomous driving is proposed. The lidar and radar devices are installed on the ego car, and a customized Unscented Kalman Filter (UKF) is used for their data fusion. Lidars are accurate in determining objects’ positions but significantly less accurate on measuring their velocities. However, Radars are more accurate on measuring objects velocities but less accurate on determining their positions as they have a lower spatial resolution. Therefore, the merits of both sensors are combined using the proposed fusion approach to provide both pose and velocity data for objects moving in roads precisely. The Grid-Based Density-Based Spatial Clustering of Applications with Noise (GB-DBSCAN) clustering algorithm is used to detect objects and estimate their centroids from the lidar and radar raw data. Then, the estimation of the object’s velocity as well as determining its corresponding geometrical shape is performed by the RANdom SAmple Consensus (RANSAC) algorithm. The proposed technique is implemented using the high-performance language C++ and utilizes highly optimized math and optimization libraries for best real-time performance. The performance of the UKF fusion is compared to that of the Extended Kalman Filter fusion (EKF) showing its superiority. Simulation studies have been carried out to evaluate the performance of the LR ODT for tracking bicycles, cars, and pedestrians.

scholarly journals Multiple Road-Objects Detection and Tracking for Autonomous Driving

2021 ◽  
Author(s):  
Wael Farag ◽  
Keyword(s):  
Kalman Filter ◽  
Real Time ◽  
High Performance ◽  
Unscented Kalman Filter ◽  
Measurement Data ◽  
Autonomous Driving ◽  
Estimation Accuracy ◽  
Time Performance ◽  
Detection And Tracking ◽  
Objects Detection

In this paper, a real-time road-Object Detection and Tracking (LR_ODT) method for autonomous driving is proposed. The method is based on the fusion of lidar and radar measurement data, where they are installed on the ego car, and a customized Unscented Kalman Filter (UKF) is employed for their data fusion. The merits of both devices are combined using the proposed fusion approach to precisely provide both pose and velocity information for objects moving in roads around the ego car. Unlike other detection and tracking approaches, the balanced treatment of both pose estimation accuracy and its real-time performance is the main contribution in this work. The proposed technique is implemented using the high-performance language C++ and utilizes highly optimized math and optimization libraries for best real-time performance. Simulation studies have been carried out to evaluate the performance of the LR_ODT for tracking bicycles, cars, and pedestrians. Moreover, the performance of the UKF fusion is compared to that of the Extended Kalman Filter fusion (EKF) showing its superiority. The UKF has outperformed the EKF on all test cases and all the state variable levels (-24% average RMSE). The employed fusion technique show how outstanding is the improvement in tracking performance compared to the use of a single device (-29% RMES with lidar and -38% RMSE with radar).

scholarly journals A Deep Learning Method for Near-Real-Time Cloud and Cloud Shadow Segmentation from Gaofen-1 Images

2020 ◽  
Vol 2020 ◽  
pp. 1-13
Author(s):  
Mehdi Khoshboresh-Masouleh ◽  
Reza Shah-Hosseini
Keyword(s):  
Deep Learning ◽  
Real Time ◽  
Computational Cost ◽  
High Definition ◽  
Satellite Mission ◽  
Real Time Processing ◽  
National Space ◽  
Spatial Features ◽  
Efficiency And Effectiveness ◽  
Earth Observation Satellite

In this study, an essential application of remote sensing using deep learning functionality is presented. Gaofen-1 satellite mission, developed by the China National Space Administration (CNSA) for the civilian high-definition Earth observation satellite program, provides near-real-time observations for geographical mapping, environment surveying, and climate change monitoring. Cloud and cloud shadow segmentation are a crucial element to enable automatic near-real-time processing of Gaofen-1 images, and therefore, their performances must be accurately validated. In this paper, a robust multiscale segmentation method based on deep learning is proposed to improve the efficiency and effectiveness of cloud and cloud shadow segmentation from Gaofen-1 images. The proposed method first implements feature map based on the spectral-spatial features from residual convolutional layers and the cloud/cloud shadow footprints extraction based on a novel loss function to generate the final footprints. The experimental results using Gaofen-1 images demonstrate the more reasonable accuracy and efficient computational cost achievement of the proposed method compared to the cloud and cloud shadow segmentation performance of two existing state-of-the-art methods.

scholarly journals Application of Kalman Filtering Methods to Online Real-Time Structural Identification: A Comparison Study

2016 ◽  
Vol 16 (06) ◽  
pp. 1550016 ◽  
Author(s):  
Mohsen Askari ◽  
Jianchun Li ◽  
Bijan Samali
Keyword(s):  
Kalman Filter ◽  
Real Time ◽  
Unscented Kalman Filter ◽  
Structural Parameters ◽  
Measurement Data ◽  
Linear Structure ◽  
Structural Identification ◽  
Input Output ◽  
Output Measurement ◽  
Highly Nonlinear

System identification refers to the process of building or improving mathematical models of dynamical systems from the observed experimental input–output data. In the area of civil engineering, the estimation of the integrity of a structure under dynamic loadings and during service condition has become a challenge for the engineering community. Therefore, there has been a great deal of attention paid to online and real-time structural identification, especially when input–output measurement data are contaminated by high-level noise. Among real-time identification methods, one of the most successful and widely used algorithms for estimation of system states and parameters is the Kalman filter and its various nonlinear extensions such as extended Kalman filter (EKF), Iterated EKF (IEKF), the recently developed unscented Kalman filter (UKF) and Iterated UKF (IUKF). In this paper, an investigation has been carried out on the aforementioned techniques for their effectiveness and efficiencies through a highly nonlinear single degree of freedom (SDOF) structure as well as a two-storey linear structure. Although IEKF is an improved version of EKF, results show that IUKF generally produces better results in terms of structural parameters and state estimation than UKF and IEKF. Also IUKF is more robust to noise levels compared to the other approaches.

Kalman-filter-based sensor fusion applied to road-objects detection and tracking for autonomous vehicles

2020 ◽  
pp. 095965182097552
Author(s):  
Wael Farag
Keyword(s):  
Kalman Filter ◽  
Real Time ◽  
Extended Kalman Filter ◽  
Mean Squared Error ◽  
Unscented Kalman Filter ◽  
Measurement Data ◽  
Root Mean Squared Error ◽  
Time Performance ◽  
Detection And Tracking ◽  
Squared Error

In this article, a real-time road-Object Detection and Tracking (LR_ODT) method for autonomous driving is proposed. This method is based on the fusion of lidar and radar measurement data, where they are installed on the ego car, and a customized Unscented Kalman Filter is employed for their data fusion. The merits of both devices are combined using the proposed fusion approach to precisely provide both pose and velocity information for objects moving in roads around the ego car. Unlike other detection and tracking approaches, the balanced treatment of both pose estimation accuracy and its real-time performance is the main contribution in this work. The proposed technique is implemented using the high-performance language C++ and utilizes highly optimized math and optimization libraries for best real-time performance. Simulation studies have been carried out to evaluate the performance of the LR_ODT for tracking bicycles, cars, and pedestrians. Moreover, the performance of the Unscented Kalman Filter fusion is compared to that of the Extended Kalman Filter fusion showing its superiority. The Unscented Kalman Filter has outperformed the Extended Kalman Filter on all test cases and all the state variable levels (−24% average Root Mean Squared Error). The employed fusion technique shows how outstanding is the improvement in tracking performance compared to the use of a single device (−29% Root Mean Squared Error with lidar and −38% Root Mean Squared Error with radar).

scholarly journals New Motion Estimation Algorithms and its VLSI architectures for Real Time High Definition Video Coding

2012 ◽  
Vol 7 (1) ◽  
pp. 37-46
Author(s):  
Gustavo Sanchez ◽  
Marcelo Porto ◽  
Diego Noble ◽  
Sergio Bampi ◽  
Luciano Agostini
Keyword(s):  
Motion Estimation ◽  
Real Time ◽  
High Performance ◽  
Local Minima ◽  
High Definition ◽  
Vlsi Architectures ◽  
Estimation Algorithms ◽  
Diamond Search ◽  
Good Trade ◽  
And Performance

This paper presents an efficient hardware design using the new Motion Estimation (ME) algorithms named: Multi-point Diamond Search (MPDS) and Dynamic Multi-Point Diamond Search (DMPDS). These algorithms are more efficient to avoid from local minima falls than traditional fast algorithms.This fact contributes to increase the quality of the motion vectors, especially in High Definition (HD) videos, were the number of local minima are considerable higher. Two versions of MPDS algorithm were proposed. The first one, focused on high performance, is capable to process videos QFHD at 30 frames per second when synthesized to Altera Stratix 4 and 90nm TSCM, with only 18mW. The second version is focused on quality enhancement and is capable to process HD 1080p videos in real time. The DMPDS architecture has been developed focusing on high performance and was synthesized to Altera stratix 4. This architecture is capable to process videos QFHD at 34 frames per second. In comparison to related works, our solutions obtained the highest processing rates, and a good trade-off among power consumption, area, memory bits and performance.

scholarly journals Whole-Body Joint Angle Estimation for Real-Time Humanoid Robot Imitation Based on Gaussian Process Dynamical Model and Particle Filter

2019 ◽  
Vol 10 (1) ◽  
pp. 5
Author(s):  
Jian Mi ◽  
Yasutake Takahashi
Keyword(s):  
Particle Filter ◽  
Real Time ◽  
Humanoid Robot ◽  
Joint Angle ◽  
Computational Cost ◽  
High Dimensional ◽  
Motion Model ◽  
Joint Angles ◽  
Compact State ◽  
Low Computational Cost

Real-time imitation enables a humanoid robot to mirror the behavior of humans, being important for applications of human–robot interaction. For imitation, the corresponding joint angles of the humanoid robot should be estimated. Generally, a humanoid robot comprises dozens of joints that construct a high-dimensional exploration space for estimating the joint angles. Although a particle filter can estimate the robot state and provides a solution for estimating joint angles, the computational cost becomes prohibitive given the high dimension of the exploration space. Furthermore, a particle filter can only estimate the joint angles accurately using a motion model. To realize accurate joint angle estimation at low computational cost, Gaussian process dynamical models (GPDMs) can be adopted. Specifically, a compact state space can be constructed through the GPDM learning of high-dimensional time-series motion data to obtain a suitable motion model. We propose a GPDM-based particle filter using a compact state space from the learned motion models to realize efficient estimation of joint angles for robot imitation. Simulations and real experiments demonstrate that the proposed method efficiently estimates humanoid robot joint angles at low computational cost, enabling real-time imitation.

scholarly journals A High-Throughput Hardware Architecture for the H.264/AVC Half-Pixel Motion Estimation Targeting High-Definition Videos

2011 ◽  
Vol 2011 ◽  
pp. 1-9 ◽  
Author(s):  
Marcel M. Corrêa ◽  
Mateus T. Schoenknecht ◽  
Robson S. Dornelles ◽  
Luciano V. Agostini
Keyword(s):  
Motion Estimation ◽  
Real Time ◽  
High Throughput ◽  
High Performance ◽  
Hardware Architecture ◽  
Interpolation Process ◽  
High Definition ◽  
Efficient Search ◽  
Xilinx Fpga ◽  
Very High

This paper presents a high-performance hardware architecture for the H.264/AVC Half-Pixel Motion Estimation that targets high-definition videos. This design can process very high-definition videos like QHDTV () in real time (30 frames per second). It also presents an optimized arrangement of interpolated samples, which is the main key to achieve an efficient search. The interpolation process is interleaved with the SAD calculation and comparison, allowing the high throughput. The architecture was fully described in VHDL, synthesized for two different Xilinx FPGA devices, and it achieved very good results when compared to related works.

scholarly journals Using bacterial interaction and stereoscopic images for the location of obstacles on autonomous robots

2020 ◽  
Vol 9 (3) ◽  
pp. 906-913
Author(s):  
Fredy Martinez ◽  
Edwar Jacinto ◽  
Fernando Martínez
Keyword(s):  
Real Time ◽  
High Performance ◽  
Computational Cost ◽  
Cost Effective ◽  
Service Robots ◽  
Depth Information ◽  
Human Beings ◽  
Distance Information ◽  
Time Operation ◽  
Bacterial Interaction

Service robots are characterized by autonomously performing indoor tasks in unstructured environments, this condition of the environment prevents the prior programming of the map, which requires reactive behavior. These robots require real-time and cost-effective identification of obstacles in the environment, which includes not only distance information, but also depth information. This paper shows a strategy to estimate the position of obstacles in unknown environments. This strategy is characterized by low computational cost and real-time operation. The environments are selected because they are those usual to human beings, and this also influences our design, since we look for functional and morphological equivalence with human beings. This equivalence corresponds to the installation of two cameras in our robotic platform to form a stereoscopic system equivalent to the human. The images captured simultaneously are analyzed by a bacterial interaction scheme to define points on the obstacles. Our strategy showed a high performance in controlled environments. The scheme was able to establish distances to different points of the obstacle with 95% accuracy for distances between 0.8 and 2 m.

Sign in / Sign up

Export Citation Format

Share Document