Identification and Recognition of Vehicle Environment Using Artificial Neural Networks
Само за регистроване кориснике
2019
Конференцијски прилог (Објављена верзија)
Метаподаци
Приказ свих података о документуАпстракт
Object detection using deep learning over the years became one of the most popular methods for implementation in autonomous systems. Autonomous vehicle requires very reliable and accurate identification and recognition of surrounding objects in real traffic environments to achieve decent detection results. In this paper, special type of Artificial Neural Network (ANN) named Convolutional Neural Network (CNN) was used for identification and recognition of surrounding objects in real traffic. The new model based on CNN was trained and developed to be able to identify and recognize 4 different classes of objects: cars, traffic lights, persons and bicycles. The developed model has shown 94.6% accuracy of object identification and recognizing on the test set.
Кључне речи:
Vehicles environment / Object detection / Convolutional Neural Network / Artificial Neural NetworksИзвор:
Experimental and Numerical Investigations in Materials Science and Engineering, 2019, 54, 208-219Издавач:
- Springer International Publishing Ag, Cham
DOI: 10.1007/978-3-319-99620-2_16
ISSN: 2367-3370
WoS: 000495600600016
Scopus: 2-s2.0-85063236159
Колекције
Институција/група
Mašinski fakultetTY - CONF AU - Jocić, Darko AU - Ćirović, Velimir AU - Aleksendrić, Dragan PY - 2019 UR - https://machinery.mas.bg.ac.rs/handle/123456789/3094 AB - Object detection using deep learning over the years became one of the most popular methods for implementation in autonomous systems. Autonomous vehicle requires very reliable and accurate identification and recognition of surrounding objects in real traffic environments to achieve decent detection results. In this paper, special type of Artificial Neural Network (ANN) named Convolutional Neural Network (CNN) was used for identification and recognition of surrounding objects in real traffic. The new model based on CNN was trained and developed to be able to identify and recognize 4 different classes of objects: cars, traffic lights, persons and bicycles. The developed model has shown 94.6% accuracy of object identification and recognizing on the test set. PB - Springer International Publishing Ag, Cham C3 - Experimental and Numerical Investigations in Materials Science and Engineering T1 - Identification and Recognition of Vehicle Environment Using Artificial Neural Networks EP - 219 SP - 208 VL - 54 DO - 10.1007/978-3-319-99620-2_16 ER -
@conference{ author = "Jocić, Darko and Ćirović, Velimir and Aleksendrić, Dragan", year = "2019", abstract = "Object detection using deep learning over the years became one of the most popular methods for implementation in autonomous systems. Autonomous vehicle requires very reliable and accurate identification and recognition of surrounding objects in real traffic environments to achieve decent detection results. In this paper, special type of Artificial Neural Network (ANN) named Convolutional Neural Network (CNN) was used for identification and recognition of surrounding objects in real traffic. The new model based on CNN was trained and developed to be able to identify and recognize 4 different classes of objects: cars, traffic lights, persons and bicycles. The developed model has shown 94.6% accuracy of object identification and recognizing on the test set.", publisher = "Springer International Publishing Ag, Cham", journal = "Experimental and Numerical Investigations in Materials Science and Engineering", title = "Identification and Recognition of Vehicle Environment Using Artificial Neural Networks", pages = "219-208", volume = "54", doi = "10.1007/978-3-319-99620-2_16" }
Jocić, D., Ćirović, V.,& Aleksendrić, D.. (2019). Identification and Recognition of Vehicle Environment Using Artificial Neural Networks. in Experimental and Numerical Investigations in Materials Science and Engineering Springer International Publishing Ag, Cham., 54, 208-219. https://doi.org/10.1007/978-3-319-99620-2_16
Jocić D, Ćirović V, Aleksendrić D. Identification and Recognition of Vehicle Environment Using Artificial Neural Networks. in Experimental and Numerical Investigations in Materials Science and Engineering. 2019;54:208-219. doi:10.1007/978-3-319-99620-2_16 .
Jocić, Darko, Ćirović, Velimir, Aleksendrić, Dragan, "Identification and Recognition of Vehicle Environment Using Artificial Neural Networks" in Experimental and Numerical Investigations in Materials Science and Engineering, 54 (2019):208-219, https://doi.org/10.1007/978-3-319-99620-2_16 . .