ETRI-Knowledge Sharing Plaform

KOREAN
논문 검색
Type SCI
Year ~ Keyword

Detail

Conference Paper Real-time semantic segmentation on edge devices: A performance comparison of segmentation models
Cited 3 time in scopus Download 22 time Share share facebook twitter linkedin kakaostory
Authors
MyeongSeok Lee, Mooseop Kim, Chi Yoon Jeong
Issue Date
2022-10
Citation
International Conference on Information and Communication Technology Convergence (ICTC) 2022, pp.383-388
Language
English
Type
Conference Paper
DOI
https://dx.doi.org/10.1109/ICTC55196.2022.9952938
Project Code
22ZS1200, 인간중심의 자율지능시스템 원천기술연구, Jeong Dan Choi
Abstract
Recent advances in convolutional neural networks have led to considerably accurate semantic segmentation tasks. However, previous works use a pre-trained backbone borrowed from image classification tasks with considerable computational complexity, resulting in large latencies. Many methods have been proposed to reduce the latency of the segmentation network without loss of accuracy. These methods have reported varying experimental results with different computing devices, acceleration techniques, and input image sizes. Although most studies claim that their results are state-of-the-art, it is necessary to reconsider whether they are being compared under the same conditions. We propose a performance evaluation method of real-time semantic segmentation models to compare the performance under the same conditions fairly. In addition, we carry out an empirical study to evaluate the performance of recent real-time semantic segmentation networks and make a comparative analysis between them. We train the segmentation models using the same input data and data augmentation method. Then, the performance of the segmentation methods is analyzed regarding accuracy and speed. In contrast to most studies that exclude the time required for the pre-processing and post-processing steps, we measured the actual processing time needed to perform semantic segmentation with a real dataset. Further, we measured the processing speed and power consumption of the segmentation models in embedded devices in which real-time segmentation is applied, unlike previous studies that measured performance on a PC. Experimental results showed that the real-time semantic segmentation methods could not run in real-time on embedded devices when considering the pre-processing and post-processing steps. By comprehensively considering the inference speed, energy consumption, and processing time of semantic segmentation models, the experimental results show that FasterSeg-S is suited for embedded devices.
KSP Keywords
Augmentation method, Carry out, Comparative analysis, Computational complexity, Convolution neural network(CNN), Data Augmentation, Edge devices, Embedded Devices, Empirical study, Image classification, Performance comparison