SegMatic: A Deep Neural Network Learning Model for Semantic Segmentation

International Journal of Electronics and Communication Engineering

© 2023 by SSRG - IJECE Journal

Volume 10 Issue 10

Year of Publication : 2023

Authors : K.G. Suma, Gurram Sunitha, J. Avanija

10.14445/23488549/IJECE-V10I10P104

How to Cite?

K.G. Suma, Gurram Sunitha, J. Avanija, "SegMatic: A Deep Neural Network Learning Model for Semantic Segmentation," SSRG International Journal of Electronics and Communication Engineering, vol. 10,  no. 10, pp. 40-48, 2023. Crossref, https://doi.org/10.14445/23488549/IJECE-V10I10P104

Abstract:

Semantic segmentation enables vehicles to accurately identify and categorize objects in their surroundings, such as pedestrians, other cars, road signs, and obstacles. Semantic segmentation, object detection, and deep learning have emerged as critical pillars, enabling machines to perceive and understand the visual world with unprecedented precision. This paper introduces SegMatic, a novel deep-learning model specifically tailored to address the unique demands of autonomous vehicles. SegMatic is a novel deep model for semantic segmentation and precise object detection. This model harnesses the power of deep learning to transform raw images into pixel-wise semantic maps, providing detailed insights into object boundaries and category-specific regions. SegMatic employs a two-stage approach. It uses a modified U-Net as the first stage to extract feature maps. Mask R-CNN is used as the second stage for post-processing. Experiments are conducted on the Pascal VOC 2012 dataset. SegMatic outperformed traditional models with remarkable precision and pixel accuracy scores. It achieved superior results in both semantic segmentation and object detection. This success is evidenced by achieving a mIoU of 94.6 and PA of 95.7 across various object categories. These results substantiate the significance of SegMatic’s contributions to computer vision and deep learning.

Keywords:

Deep learning, Image segmentation, Object detection, U-Net, Mask R-CNN.

References:

[1] Zhengxia Zou et al., “Object Detection in 20 Years: A Survey,” Proceedings of the IEEE, vol. 111, no. 3, pp. 257-276, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Esmaeil Mirmahdi, and Omid Ghorbani Shirazi, “Installation of Suitable Sensors for Object Detection and Height Control on Combine Harvester,” SSRG International Journal of Mechanical Engineering, vol. 8, no. 5, pp. 12-19, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Ashish Kumar Gupta et al., “Salient Object Detection Techniques in Computer Vision-A Survey,” Entropy, vol. 22, no. 10, pp. 1-49, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Hongshan Yu et al., “Methods and Datasets on Semantic Segmentation: A Review,” Neurocomputing, vol. 304, pp. 82-103, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Indrabayu et al., “Various Obstacles Detection Systems Using Single Shot Multi-Box Detector (SSD) for Autonomous-Driving Vehicles,” International Journal of Engineering Trends and Technology, vol. 71, no. 5, pp. 1-8, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[6] E. Parimalasundar et al., “Investigation of Efficient Multilevel Inverter for Photovoltaic Energy System and Electric Vehicle Applications,” Electrical Engineering & Electromechanics, no. 4, pp. 47-51, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[7] D. Raja, and M. Karthikeyan, “Plant Disease Detection and Classification Based on Rat Swarm Optimization Using Deep Learning Approach,” International Journal of Engineering Trends and Technology, vol. 71, no. 7, pp. 42-52, 2023.
[CrossRef] [Publisher Link]
[8] Yujian Mo et al., “Review the State-of-the-Art Technologies of Semantic Segmentation Based on Deep Learning,” Neurocomputing, vol. 493, pp. 626-646, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Shervin Minaee et al., “Image Segmentation Using Deep Learning: A Survey,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 44, no. 7, pp. 3523-3542, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Swarnendu Ghosh et al., “Understanding Deep Learning Techniques for Image Segmentation,” ACM Computing Surveys, vol. 52, no. 4, pp. 1-35, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Foivos I. Diakogiannis et al., “ResUNet-A: A Deep Learning Framework for Semantic Segmentation of Remotely Sensed Data,” ISPRS Journal of Photogrammetry and Remote Sensing, vol. 162, pp. 94-114, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Manasa R., K. Karibasappa, and Rajeshwari J., “Autonomous Path Finder and Object Detection Using an Intelligent Edge Detection Approach,” SSRG International Journal of Electrical and Electronics Engineering, vol. 9, no. 8, pp. 1-7, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Parimalasundar Ezhilvannan et al., “Analysis of the Effectiveness of a Two-Stage Three-Phase Grid Connected Inverter for Photovoltaic Applications,” Journal of Solar Energy Research, vol. 8, no. 2, pp. 1471-1483, 2023.
[Google Scholar] [Publisher Link]
[14] Jian-Hua Shu et al., “An Improved Mask R-CNN Model for Multiorgan Segmentation,” Mathematical Problems in Engineering, vol. 2020, pp. 1-11, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Kitsuchart Pasupa et al., “Evaluation of Deep Learning Algorithms for Semantic Segmentation of Car Parts,” Complex & Intelligent Systems, vol. 8, no. 5, pp. 3613-3625, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Xiangyang Xu et al., “Crack Detection and Comparison Study Based on Faster R-CNN and Mask R-CNN,” Sensors, vol. 22, no. 3, pp. 1-17, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Panqu Wang et al., “Understanding Convolution for Semantic Segmentation,” 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), Lake Tahoe, NV, USA, pp. 1451-1460, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Alex Dominguez-Sanchez et al., “A New Dataset and Performance Evaluation of a Region-Based CNN for Urban Object Detection,” 2018 International Joint Conference on Neural Networks (IJCNN), Rio de Janeiro, Brazil, pp. 1-8, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Kaiming He et al., “Mask R-CNN,” Proceedings of the IEEE International Conference on Computer Vision, pp. 2961-2969, 2017.
[Google Scholar] [Publisher Link]
[20] Nitigya Sambyal et al., “Modified U-Net Architecture for Semantic Segmentation of Diabetic Retinopathy Images,” Biocybernetics and Biomedical Engineering, vol. 40, no. 3, pp. 1094-1109, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Mohammad Hesam Hesamian et al., “Deep Learning Techniques for Medical Image Segmentation: Achievements and Challenges,” Journal of Digital Imaging, vol. 32, pp. 582-596, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[22] Fahad Lateef, and Yassine Ruichek, “Survey on Semantic Segmentation Using Deep Learning Techniques,” Neurocomputing, vol. 338, pp. 321-348, 2019.
[CrossRef] [Google Scholar] [Publisher Link]