Back to Search
Start Over
Multi-vehicle detection with identity awareness using cascade Adaboost and Adaptive Kalman filter for driver assistant system
- Source :
- PLoS ONE, Vol 12, Iss 3, p e0173424 (2017), PLoS ONE
- Publication Year :
- 2017
- Publisher :
- Public Library of Science (PLoS), 2017.
-
Abstract
- Vision-based vehicle detection is an important issue for advanced driver assistance systems. In this paper, we presented an improved multi-vehicle detection and tracking method using cascade Adaboost and Adaptive Kalman filter(AKF) with target identity awareness. A cascade Adaboost classifier using Haar-like features was built for vehicle detection, followed by a more comprehensive verification process which could refine the vehicle hypothesis in terms of both location and dimension. In vehicle tracking, each vehicle was tracked with independent identity by an Adaptive Kalman filter in collaboration with a data association approach. The AKF adaptively adjusted the measurement and process noise covariance through on-line stochastic modelling to compensate the dynamics changes. The data association correctly assigned different detections with tracks using global nearest neighbour(GNN) algorithm while considering the local validation. During tracking, a temporal context based track management was proposed to decide whether to initiate, maintain or terminate the tracks of different objects, thus suppressing the sparse false alarms and compensating the temporary detection failures. Finally, the proposed method was tested on various challenging real roads, and the experimental results showed that the vehicle detection performance was greatly improved with higher accuracy and robustness.
- Subjects :
- 0209 industrial biotechnology
Statistical Noise
Stochastic modelling
Computer science
Vision
Computer Vision
Social Sciences
lcsh:Medicine
Advanced driver assistance systems
Transportation
02 engineering and technology
Monocular Vision
020901 industrial engineering & automation
0202 electrical engineering, electronic engineering, information engineering
Psychology
Computer vision
AdaBoost
lcsh:Science
Data Management
Multidisciplinary
Covariance
Applied Mathematics
Simulation and Modeling
Transportation Infrastructure
Gaussian Noise
Motor Vehicles
Cascade
Physical Sciences
symbols
Engineering and Technology
020201 artificial intelligence & image processing
Sensory Perception
Kalman Filter
Algorithms
Statistics (Mathematics)
Research Article
Computer and Information Sciences
Automobile Driving
Imaging Techniques
Research and Analysis Methods
Civil Engineering
symbols.namesake
Robustness (computer science)
Artificial Intelligence
Humans
business.industry
lcsh:R
Biology and Life Sciences
Random Variables
Kalman filter
Probability Theory
Roads
Target Detection
Gaussian noise
lcsh:Q
Artificial intelligence
business
Monocular vision
Mathematics
Neuroscience
Subjects
Details
- Language :
- English
- ISSN :
- 19326203
- Volume :
- 12
- Issue :
- 3
- Database :
- OpenAIRE
- Journal :
- PLoS ONE
- Accession number :
- edsair.doi.dedup.....3cf41b719a34e14329bcd83913ed4e34