2019 International Conference on Artificial Intelligence: Applications and Innovations (IC-AIAI)

Detection of Big Animals on Images with Road Scenes using Deep Learning

Yudin D. 1
Sotnikov Anton 1
Krishtopik Andrey 2
1
 
Laboratory of Intelligent Transport, Moscow Institute of Physics and Technology (National Research University), Dolgoprudny, Russia
2
 
Laboratory of Cognitive Dynamic Systems, Moscow Institute of Physics and Technology (National Research University), Dolgoprudny, Russia
Publication typeProceedings Article
Publication date2019-09-01
Quartile SCImago
Quartile WOS
Impact factor
ISSN
Abstract
The recognition of big animals on the images with road scenes has received little attention in modern research. There are very few specialized data sets for this task. Popular open data sets contain many images of big animals, but the most part of them is not correspond to road scenes that is necessary for on-board vision systems of unmanned vehicles. The paper describes the preparation of such a specialized data set based on Google Open Images and COCO datasets. The resulting data set contains about 20000 images of big animals of 10 classes: "Bear", "Fox", "Dog", "Horse", "Goat", "Sheep", "Cow", "Zebra", "Elephant", "Giraffe". Deep learning approaches to detect these objects are researched in the paper. Authors trained and tested modern neural network architectures YOLOv3, RetinaNet R-50-FPN, Faster R-CNN R-50-FPN, Cascade R-CNN R-50-FPN. To compare the approaches the mean average precision (mAP) was determined at IoU≥50%, also their speed was calculated for input tensor sizes 640x384x3. The highest quality metrics are demonstrated by architecture YOLOv3 as for ten classes (0.78 mAP) and one joint class (0.92 mAP) detection with speed more 35 fps on NVidia Tesla V-100 32GB video card. At the same hardware, the RetinaNet R-50-FPN architecture provided recognition speed of more than 44 fps and a 13% lower mAP. The software implementation was done using the Keras and PyTorch deep learning libraries and NVidia CUDA technology. The proposed data set and neural network approach to recognizing big animals on images have shown their effectiveness and can be used in the on-board vision systems of driverless cars or in driver assistant systems.

Citations by journals

1
Lecture Notes in Networks and Systems
Lecture Notes in Networks and Systems, 1, 20%
Lecture Notes in Networks and Systems
1 publication, 20%
1

Citations by publishers

1
Springer Nature
Springer Nature, 1, 20%
Springer Nature
1 publication, 20%
1
  • We do not take into account publications that without a DOI.
  • Statistics recalculated only for publications connected to researchers, organizations and labs registered on the platform.
  • Statistics recalculated weekly.
Metrics
Share
Cite this
GOST |
Cite this
GOST Copy
Yudin D., Sotnikov A., Krishtopik A. Detection of Big Animals on Images with Road Scenes using Deep Learning // 2019 International Conference on Artificial Intelligence: Applications and Innovations (IC-AIAI). 2019.
GOST all authors (up to 50) Copy
Yudin D., Sotnikov A., Krishtopik A. Detection of Big Animals on Images with Road Scenes using Deep Learning // 2019 International Conference on Artificial Intelligence: Applications and Innovations (IC-AIAI). 2019.
RIS |
Cite this
RIS Copy
TY - CPAPER
DO - 10.1109/IC-AIAI48757.2019.00028
UR - https://doi.org/10.1109%2FIC-AIAI48757.2019.00028
TI - Detection of Big Animals on Images with Road Scenes using Deep Learning
T2 - 2019 International Conference on Artificial Intelligence: Applications and Innovations (IC-AIAI)
AU - Yudin, D.
AU - Sotnikov, Anton
AU - Krishtopik, Andrey
PY - 2019
DA - 2019/09/01 00:00:00
PB - IEEE
ER -
BibTex
Cite this
BibTex Copy
@inproceedings{2019_Yudin
author = {D. Yudin and Anton Sotnikov and Andrey Krishtopik},
title = {Detection of Big Animals on Images with Road Scenes using Deep Learning},
year = {2019},
month = {sep},
publisher = {IEEE}
}
Found error?