scholarly journals Detection and Tracking of Pedestrians Using Doppler LiDAR

2021 ◽  
Vol 13 (15) ◽  
pp. 2952
Author(s):  
Xiaoyi Peng ◽  
Jie Shan
Keyword(s):  
Kalman Filter ◽  
San Francisco ◽  
Autonomous Vehicles ◽  
Traffic Management ◽  
Pedestrian Detection ◽  
Supervised Machine Learning ◽  
Data Sets ◽  
Doppler Lidar ◽  
Tracking Accuracy ◽  
Detection And Tracking

Pedestrian detection and tracking is necessary for autonomous vehicles and traffic management. This paper presents a novel solution to pedestrian detection and tracking for urban scenarios based on Doppler LiDAR that records both the position and velocity of the targets. The workflow consists of two stages. In the detection stage, the input point cloud is first segmented to form clusters, frame by frame. A subsequent multiple pedestrian separation process is introduced to further segment pedestrians close to each other. While a simple speed classifier is capable of extracting most of the moving pedestrians, a supervised machine learning-based classifier is adopted to detect pedestrians with insignificant radial velocity. In the tracking stage, the pedestrian’s state is estimated by a Kalman filter, which uses the speed information to estimate the pedestrian’s dynamics. Based on the similarity between the predicted and detected states of pedestrians, a greedy algorithm is adopted to associate the trajectories with the detection results. The presented detection and tracking methods are tested on two data sets collected in San Francisco, California by a mobile Doppler LiDAR system. The results of the pedestrian detection demonstrate that the proposed two-step classifier can improve the detection performance, particularly for detecting pedestrians far from the sensor. For both data sets, the use of Doppler speed information improves the F1-score and the recall by 15% to 20%. The subsequent tracking from the Kalman filter can achieve 83.9–55.3% for the multiple object tracking accuracy (MOTA), where the contribution of the speed measurements is secondary and insignificant.

scholarly journals Convolutional Neural Network Using Kalman Filter for Human Detection and Tracking on RGB-D Video

2018 ◽  
Vol 12 (2) ◽  
pp. 105 ◽  
Author(s):  
Jovin Angelico ◽  
Ken Ratri Retno Wardani
Keyword(s):  
Neural Network ◽  
Kalman Filter ◽  
Convolutional Neural Network ◽  
Human Detection ◽  
Detection Accuracy ◽  
Tracking Accuracy ◽  
Lighting Condition ◽  
Detection And Tracking ◽  
Computation Efficiency ◽  
The Impact

The computer ability to detect human being by computer vision is still being improved both in accuracy or computation time. In low-lighting condition, the detection accuracy is usually low. This research uses additional information, besides RGB channels, namely a depth map that shows objects’ distance relative to the camera. This research integrates Cascade Classifier (CC) to localize the potential object, the Convolutional Neural Network (CNN) technique to identify the human and nonhuman image, and the Kalman filter technique to track human movement. For training and testing purposes, there are two kinds of RGB-D datasets used with different points of view and lighting conditions. Both datasets have been selected to remove images which contain a lot of noises and occlusions so that during the training process it will be more directed. Using these integrated techniques, detection and tracking accuracy reach 77.7%. The impact of using Kalman filter increases computation efficiency by 41%.

scholarly journals Review on Lane Detection and Tracking Algorithms of Advanced Driver Assistance System

2021 ◽  
Vol 13 (20) ◽  
pp. 11417
Author(s):  
Swapnil Waykole ◽  
Nirajan Shiwakoti ◽  
Peter Stasinopoulos
Keyword(s):  
Autonomous Vehicles ◽  
Driver Assistance System ◽  
Analysis Of Algorithms ◽  
Lane Detection ◽  
Assistance System ◽  
Advanced Driver Assistance System ◽  
Data Sets ◽  
Driver Assistance ◽  
Detection And Tracking ◽  
Tracking Algorithms

Autonomous vehicles and advanced driver assistance systems are predicted to provide higher safety and reduce fuel and energy consumption and road traffic emissions. Lane detection and tracking are the advanced key features of the advanced driver assistance system. Lane detection is the process of detecting white lines on the roads. Lane tracking is the process of assisting the vehicle to remain in the desired path, and it controls the motion model by using previously detected lane markers. There are limited studies in the literature that provide state-of-art findings in this area. This study reviews previous studies on lane detection and tracking algorithms by performing a comparative qualitative analysis of algorithms to identify gaps in knowledge. It also summarizes some of the key data sets used for testing algorithms and metrics used to evaluate the algorithms. It is found that complex road geometries such as clothoid roads are less investigated, with many studies focused on straight roads. The complexity of lane detection and tracking is compounded by the challenging weather conditions, vision (camera) quality, unclear line-markings and unpaved roads. Further, occlusion due to overtaking vehicles, high-speed and high illumination effects also pose a challenge. The majority of the studies have used custom based data sets for model testing. As this field continues to grow, especially with the development of fully autonomous vehicles in the near future, it is expected that in future, more reliable and robust lane detection and tracking algorithms will be developed and tested with real-time data sets.

scholarly journals Real-time vehicle detection and tracking using improved histogram of gradient features and Kalman filters

2018 ◽  
Vol 15 (1) ◽  
pp. 172988141774994 ◽  
Author(s):  
Xinyu Zhang ◽  
Hongbo Gao ◽  
Chong Xue ◽  
Jianhui Zhao ◽  
Yuchao Liu
Keyword(s):  
Kalman Filter ◽  
Intelligent Transportation Systems ◽  
Traffic Management ◽  
Vehicle Detection ◽  
Transportation Systems ◽  
Driver Assistance Systems ◽  
Filter Model ◽  
Detection And Tracking ◽  
Vehicle Detection And Tracking ◽  
Subsequent Motion

Intelligent transportation systems and safety driver-assistance systems are important research topics in the field of transportation and traffic management. This study investigates the key problems in front vehicle detection and tracking based on computer vision. A video of a driven vehicle on an urban structured road is used to predict the subsequent motion of the front vehicle. This study provides the following contributions. (1) A new adaptive threshold segmentation algorithm is presented in the image preprocessing phase. This algorithm is resistant to interference from complex environments. (2) Symmetric computation based on a traditional histogram of gradient (HOG) feature vector is added in the vehicle detection phase. Symmetric HOG feature with AdaBoost classification improves the detection rate of the target vehicle. (3) A motion model based on adaptive Kalman filter is established. Experiments show that the prediction of Kalman filter model provides a reliable region for eliminating the interference of shadows and sharply decreasing the missed rate.

scholarly journals Using Machine Learning Methods to Identify Particle Types from Doppler Lidar Measurements in Iceland

2021 ◽  
Vol 13 (13) ◽  
pp. 2433
Author(s):  
Shu Yang ◽  
Fengchao Peng ◽  
Sibylle von Löwis ◽  
Guðrún Nína Petersen ◽  
David Christian Finger
Keyword(s):  
Machine Learning ◽  
Weather Conditions ◽  
Dust Storms ◽  
Machine Learning Algorithms ◽  
Lidar Data ◽  
Data Sets ◽  
Doppler Lidar ◽  
Lidar Measurements ◽  
Using Data ◽  
Filter Noise

Doppler lidars are used worldwide for wind monitoring and recently also for the detection of aerosols. Automatic algorithms that classify the lidar signals retrieved from lidar measurements are very useful for the users. In this study, we explore the value of machine learning to classify backscattered signals from Doppler lidars using data from Iceland. We combined supervised and unsupervised machine learning algorithms with conventional lidar data processing methods and trained two models to filter noise signals and classify Doppler lidar observations into different classes, including clouds, aerosols and rain. The results reveal a high accuracy for noise identification and aerosols and clouds classification. However, precipitation detection is underestimated. The method was tested on data sets from two instruments during different weather conditions, including three dust storms during the summer of 2019. Our results reveal that this method can provide an efficient, accurate and real-time classification of lidar measurements. Accordingly, we conclude that machine learning can open new opportunities for lidar data end-users, such as aviation safety operators, to monitor dust in the vicinity of airports.

Cross-National Focus Group Response to Autonomous Vehicles

2021 ◽  
pp. 036119812199236
Author(s):  
Thomas A. Norton ◽  
Melissa Ruhl ◽  
Tim Armitage ◽  
Brian Matthews ◽  
John Miles
Keyword(s):  
Focus Group ◽  
San Francisco ◽  
Autonomous Vehicles ◽  
Public Investment ◽  
Public Attitudes ◽  
Total N ◽  
The Public ◽  
Form And Function ◽  
Positive Attitudes ◽  
Willingness To Use

The development of autonomous vehicles (AVs) is advancing quickly in some enclaves around the world. Consequently, AVs exist in the public consciousness, featuring regularly in mainstream media. As the form and function of AVs emerge, the attitudes of potential users become more important. The extent to which the public trusts AV technology and anticipates benefits, will drive consumer willingness to use AVs. Broadly, public attitudes will determine whether AVs can attract public investment in infrastructure and become a feature of the future transport mix or fail to realize the potential their developers assert. As part of UK Autodrive, a program trialing the introduction of AVs in the United Kingdom, researchers conducted focus groups in five UK cities, and a comparison focus group in San Francisco (December 2017 to September 2018) using representative samples (total n = 137). Focus group facilitators guided discussions in three areas considered central to usage decisions: trust in the technology, ownership models, and community benefit. This paper describes findings from a quasi-quantitative study supported with qualitative insights. This research provides three key takeaways centering on trust in the technology and in delivering benefit. First, some participants gain trust through experience and others through evidence. Second, participants had difficulty discriminating between AV developers, indicating a need for industry cooperation. Third, partnerships were found to demonstrate trust, highlighting the need for more and deeper partnerships moving forward. Generally, participants had positive attitudes toward AVs and expect AVs to provide benefits. However, these attitudes and expectations could change as AV development progresses.

Controlled Freezing of Nonideal Solutions With Application to Cryosurgical Processes

1991 ◽  
Vol 113 (4) ◽  
pp. 430-437 ◽  
Author(s):  
H. M. Budman ◽  
J. Dayan ◽  
A. Shitzer
Keyword(s):  
Cooling Rate ◽  
Freezing Process ◽  
Data Sets ◽  
Tracking Accuracy ◽  
Loop Control ◽  
Set Point ◽  
New Device ◽  
Loop Control System ◽  
The Stability ◽  
Controlled Freezing

Success of a cryosurgical procedure, i.e., maximal cell destruction, requires that the cooling rate be controlled during the freezing process. Standard cryosurgical devices are not usually designed to perform the required controlled process. In this study, a new cryosurgical device was developed which facilitates the achievement of a specified cooling rate during freezing by accurately controlling the probe temperature variation with time. The new device has been experimentally tested by applying it to an aqueous solution of mashed potatoes. The temperature field in the freezing medium, whose thermal properties are similar to those of biological tissue, was measured. The cryoprobe temperature was controlled according to a desired time varying profile which was assumed to maximize necrosis. The tracking accuracy and the stability of the closed loop control system were investigated. It was found that for most of the time the tracking accuracy was excellent and the error between the measured probe temperature and the desired set point is within ±0.4°C. However, noticeable deviations from the set point occurred due to the supercooling phenomenon or due to the instability of the liquid nitrogen boiling regime in the cryoprobe. The experimental results were compared to those obtained by a finite elements program and very good agreement was obtained. The deviation between the two data sets seems to be mainly due to errors in positioning of the thermocouple junctions in the medium.

Sign in / Sign up

Export Citation Format

Share Document