Abstract
For autonomous vehicles, interpreting road scenes in the context of the driving environment is an important challenge. Real-time visual segmentation is crucial in self-driving applications. The processing overhead of semantic segmentation needs to be decreased in order to make it practical for embedded systems and autonomous vehicles. The modeluses image-level tag annotations to develop a dense pixel-level prediction model for semantic segmentation. These tags show whether certain classes are present in an image. Traffic signs, streets, people walking, trees, other cars, etc. are all depicted in the photographs. The initiative is based on autonomous or self-driving vehicles. In autonomous driving, self-driving cars must understand their surroundings. To extract regions with drivable roads, the suggested approach uses pixel-level segmentation. It then conducts a qualitative and quantitative study to show how well the proposed dataset and road detection work. The accuracy metric of the ResNet50 algorithm with different epoch sizesis compared. It aims to categorize each pixel in an image collected by a camera mounted on a moving vehicle into one of several possible images. Various stages of the procedure are applied to the collected photos to create a segmented image. It can distinguish between up to six classes. The above models offer real-time solutions as well as essential applications like road scene information, environmental awareness and understanding, and provide 85% accuracy.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Rasib M, Butt MA, Riaz F, Sulaiman A, Akram M (2021) Pixel level segmentation based drivable road region detection and steering angle estimation method for autonomous driving on unstructured roads. IEEE Access 9:167855–167867. https://doi.org/10.1109/ACCESS.2021.3134889
Dataset: https://www.kaggle.com/datasets/carlolepelaars/camvid
Gu Y, Si B, Liu B (2021) A novel hierarchical model in ensemble environment for road detection application. Remote Sens 13(6):1213
Rato D, Santos V (2021) LiDAR based detection of road boundaries using the density of accumulated point clouds and their gradients. Robot Auton Syst 138, Art. no. 103714
Butt MA, Khattak AM, Shafifique S, Hayat B, Abid S, Kim K-I, Ayub MW, Sajid A, Adnan A (2021) Convolutional neural network based vehicle classification in adverse illuminous conditions for intelligent transportation systems. Complexity 2021:1–11
Dahal A, Golab E, Garlapati R, Kumar VR, Yogamani S (2021) RoadEdgeNet: road edge detection system using surround view camera images
Sun Y, Zuo W, Liu M (2020) See the future: a semantic segmentation network predicting ego-vehicle trajectory with a single monocular camera. IEEE Robot Autom Lett 5(2):3066–3073
Goga SEC, Nedevschi S (2018) Fusing semantic labeled camera images and 3D LiDAR data for the detection of urban curbs. In: Proceedings of IEEE 14th international conference on intelligent computer communication and processing (ICCP), pp 301–308
Demir SO, Ertop TE, Koku AB, Konukseven EI (2017) An adaptive approach for road boundary detection using 2D LiDAR sensor. In: Proceedings IEEE international conference on multisensor fusion and integration for intelligent systems (MFI), pp 206–211
Yang F, Wang H, Jin Z (2020) A fusion network for road detection via spatial propagation and spatial transformation. Pattern Recognit 100, Art. no. 107141
Wulff F, Schäufele B, Sawade O, Becker D,Henke B, Radusch I (2018) Early Fusion of camera and lidar for robust road detection based on U-Net FCN. IEEE Xplore
Li K, Xiong H, Yu D, Liu J, Guo Y, Wang J (2021) An end-to-end multitask learning model for drivable road detection via edge refinement and geometric deformation. IEEE Trans Intell Trans Syst 23:8641–8651
Shi W, Alawieh MB, Li X, Yu H (2017) Algorithm and hardware implementation for visual perception system in autonomous vehicle: a survey. Integration 59:148–156
Raguraman SJ, Park J (2020) Intelligent drivable area detection system using camera and LiDAR sensor for autonomous vehicle. In: Proceedings IEEE international conference on electro information technology (EIT), pp 429–436
Yu X, Marinov M (2020) A study on recent developments and issues with obstacle detection systems for automated vehicles. https://www.mdpi.com/2071-1050/12/8/3281
Chan YC, Lin YC, Chen PC (2019) Lane mark and drivable area detection using a novel instance segmentation scheme. In: Proceedings IEEE/SICE international symposium on system integration (SII), pp 502–506. https://doi.org/10.1109/SII.2019.8700359
Vachmanus S, Ravankar AA, Emaru T, Kobayashi Y (2020) Semantic segmentation for road surface detection in snowy environment. In: Proceedings 59th annual conference of the society of instrument and control engineers of Japan (SICE), pp 1381–1386. https://doi.org/10.23919/sice48898.2020.9240402
Jianfei C, Changming Z (2020) Research on image recognition based on improved ResNet. In: 2020 IEEE 6th international conference on computer and communications (ICCC), Chengdu, China, 2020, pp 1422–1426. https://doi.org/10.1109/ICCC51575.2020.9345181
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Sandhya, S., Awadhiya, M., Nimmala, B., Pranathi, S., Soumya, K. (2024). Multi-class Pixel Level Segmentation for Drivable Road Detection. In: Kumar, A., Mozar, S. (eds) Proceedings of the 6th International Conference on Communications and Cyber Physical Engineering . ICCCE 2024. Lecture Notes in Electrical Engineering, vol 1096. Springer, Singapore. https://doi.org/10.1007/978-981-99-7137-4_81
Download citation
DOI: https://doi.org/10.1007/978-981-99-7137-4_81
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-7136-7
Online ISBN: 978-981-99-7137-4
eBook Packages: EngineeringEngineering (R0)