The paper proposes a novel instance segmentation method for traffic videos devised for deployment on real-time embedded devices. A novel neural network architecture is proposed using a multi-resolution feature extraction backbone and improved network designs for the object detection and instance segmentation branches. A novel post-processing method is introduced to ensure a reduced rate of false detection by evaluating the quality of the output masks. An improved network training procedure is proposed based on a novel label assignment algorithm. An ablation study on speed-vs.-performance trade-off further modifies the two branches and replaces the conventional ResNet-based performance-oriented backbone with a lightweight speed-oriented design. The proposed architectural variations achieve real-time performance when deployed on embedded devices. The experimental results demonstrate that the proposed instance segmentation method for traffic videos outperforms the you only look at coefficients algorithm, the state-of-the-art real-time instance segmentation method. The proposed architecture achieves qualitative results with 31.57 average precision on the COCO dataset, while its speed-oriented variations achieve speeds of up to 66.25 frames per second on the Jetson AGX Xavier module.
Panero Martinez, R, Schiopu, I, Cornelis, B & Munteanu, A 2021, 'Real-Time Instance Segmentation of Traffic Videos for Embedded Devices', Sensors, vol. 21, no. 1, 275. https://doi.org/10.3390/s21010275
Panero Martinez, R., Schiopu, I., Cornelis, B., & Munteanu, A. (2021). Real-Time Instance Segmentation of Traffic Videos for Embedded Devices. Sensors, 21(1), Article 275. https://doi.org/10.3390/s21010275
@article{f55404cb6fe84b1b9a85a260d1bcb7b4,
title = "Real-Time Instance Segmentation of Traffic Videos for Embedded Devices",
abstract = "The paper proposes a novel instance segmentation method for traffic videos devised for deployment on real-time embedded devices. A novel neural network architecture is proposed using a multi-resolution feature extraction backbone and improved network designs for the object detection and instance segmentation branches. A novel post-processing method is introduced to ensure a reduced rate of false detection by evaluating the quality of the output masks. An improved network training procedure is proposed based on a novel label assignment algorithm. An ablation study on speed-vs.-performance trade-off further modifies the two branches and replaces the conventional ResNet-based performance-oriented backbone with a lightweight speed-oriented design. The proposed architectural variations achieve real-time performance when deployed on embedded devices. The experimental results demonstrate that the proposed instance segmentation method for traffic videos outperforms the you only look at coefficients algorithm, the state-of-the-art real-time instance segmentation method. The proposed architecture achieves qualitative results with 31.57 average precision on the COCO dataset, while its speed-oriented variations achieve speeds of up to 66.25 frames per second on the Jetson AGX Xavier module.",
keywords = "instance segmentation, real-time, deep neural networks, embedded devices",
author = "{Panero Martinez}, Ruben and Ionut Schiopu and Bruno Cornelis and Adrian Munteanu",
note = "Copyright: This record is sourced from MEDLINE/PubMed, a database of the U.S. National Library of Medicine",
year = "2021",
month = jan,
day = "3",
doi = "10.3390/s21010275",
language = "English",
volume = "21",
journal = "Sensors",
issn = "1424-8220",
publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",
number = "1",
}