STATIONARY ON-ROAD OBSTACLES AVOIDANCE BASED ON COMPUTER VISION PRINCIPLES
Апстракт
In this paper, the classification of the on-road obstacles based on the processing of a sequence of images obtained by a monocular camera embedded on a vehicle as well as the appropriate automatic guidance principle for obstacles avoidance are presented. The typical road scenarios have been used as a testing environment for the overall algorithm. Existing obstacles (vehicles) are classified into three classes: stationary, incoming, and outgoing. The first task in the algorithm consists of obstacles detection over the road background. This is followed by their tracking from one frame to another based on the appropriate selection of features using the SURF method. After that, the obstacles are recognized in a new frame, where it is possible to determine their position from the camera and the relative velocity using projection geometry principles. Then, the polynomial method is used in order to find the path that avoids the obstacles. Synthetic and realistic video sequences are used durin...g the tests.
Кључне речи:
obstacles avoidance / obstacles classification / polynomial method / SURF / SVMИзвор:
7th International Scientific Conference on Defensive Technologies, Belgrade, 6-7, October 2016, 2016Издавач:
- Belgrade : Military Technical Institute
Финансирање / пројекти:
- Рентабилни избор нових технологија и концепција одбране кроз друштвене промене и стратешке оријентације Србије у 21. веку (RS-47029)
Колекције
Институција/група
Mašinski fakultetTY - CONF AU - BENDJABALLAH, MOURAD AU - GRAOVAC, STEVICA AU - BOULAHLIB, MOHAMMED AMINE AU - Marković, Miloš PY - 2016 UR - https://machinery.mas.bg.ac.rs/handle/123456789/6183 AB - In this paper, the classification of the on-road obstacles based on the processing of a sequence of images obtained by a monocular camera embedded on a vehicle as well as the appropriate automatic guidance principle for obstacles avoidance are presented. The typical road scenarios have been used as a testing environment for the overall algorithm. Existing obstacles (vehicles) are classified into three classes: stationary, incoming, and outgoing. The first task in the algorithm consists of obstacles detection over the road background. This is followed by their tracking from one frame to another based on the appropriate selection of features using the SURF method. After that, the obstacles are recognized in a new frame, where it is possible to determine their position from the camera and the relative velocity using projection geometry principles. Then, the polynomial method is used in order to find the path that avoids the obstacles. Synthetic and realistic video sequences are used during the tests. PB - Belgrade : Military Technical Institute C3 - 7th International Scientific Conference on Defensive Technologies, Belgrade, 6-7, October 2016 T1 - STATIONARY ON-ROAD OBSTACLES AVOIDANCE BASED ON COMPUTER VISION PRINCIPLES UR - https://hdl.handle.net/21.15107/rcub_machinery_6183 ER -
@conference{ author = "BENDJABALLAH, MOURAD and GRAOVAC, STEVICA and BOULAHLIB, MOHAMMED AMINE and Marković, Miloš", year = "2016", abstract = "In this paper, the classification of the on-road obstacles based on the processing of a sequence of images obtained by a monocular camera embedded on a vehicle as well as the appropriate automatic guidance principle for obstacles avoidance are presented. The typical road scenarios have been used as a testing environment for the overall algorithm. Existing obstacles (vehicles) are classified into three classes: stationary, incoming, and outgoing. The first task in the algorithm consists of obstacles detection over the road background. This is followed by their tracking from one frame to another based on the appropriate selection of features using the SURF method. After that, the obstacles are recognized in a new frame, where it is possible to determine their position from the camera and the relative velocity using projection geometry principles. Then, the polynomial method is used in order to find the path that avoids the obstacles. Synthetic and realistic video sequences are used during the tests.", publisher = "Belgrade : Military Technical Institute", journal = "7th International Scientific Conference on Defensive Technologies, Belgrade, 6-7, October 2016", title = "STATIONARY ON-ROAD OBSTACLES AVOIDANCE BASED ON COMPUTER VISION PRINCIPLES", url = "https://hdl.handle.net/21.15107/rcub_machinery_6183" }
BENDJABALLAH, M., GRAOVAC, S., BOULAHLIB, M. A.,& Marković, M.. (2016). STATIONARY ON-ROAD OBSTACLES AVOIDANCE BASED ON COMPUTER VISION PRINCIPLES. in 7th International Scientific Conference on Defensive Technologies, Belgrade, 6-7, October 2016 Belgrade : Military Technical Institute.. https://hdl.handle.net/21.15107/rcub_machinery_6183
BENDJABALLAH M, GRAOVAC S, BOULAHLIB MA, Marković M. STATIONARY ON-ROAD OBSTACLES AVOIDANCE BASED ON COMPUTER VISION PRINCIPLES. in 7th International Scientific Conference on Defensive Technologies, Belgrade, 6-7, October 2016. 2016;. https://hdl.handle.net/21.15107/rcub_machinery_6183 .
BENDJABALLAH, MOURAD, GRAOVAC, STEVICA, BOULAHLIB, MOHAMMED AMINE, Marković, Miloš, "STATIONARY ON-ROAD OBSTACLES AVOIDANCE BASED ON COMPUTER VISION PRINCIPLES" in 7th International Scientific Conference on Defensive Technologies, Belgrade, 6-7, October 2016 (2016), https://hdl.handle.net/21.15107/rcub_machinery_6183 .