Abstract
Steep roads with potholes, irregular slopes, and other barriers affect vehicle safety and accident prevention in mountainous areas. The paper proposes a computationally efficient computer vision and machine learning-based approach to detect these roads. The dataset includes damaged, steep, and narrow mountainous roadways. The Field of View (FoV) creation step in preprocessing increased the algorithm’s accuracy. The five statistical texture parameters—Entropy, Correlation, Homogeneity, Contrast, and dissimilarity—are extracted using the Gray-Level Co-Occurrence Matrix (GLCM) technique. The accuracy of various combinations of features, orientations, and distances varied. Haralick’s five horizontal, diagonal, and vertical GLCM-based features provided 90.95% accuracy. Experimentally, the Light Gradient Boosted Machine (LGBM) classifier predicted mountain roads most accurately.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Maeda H, Sekimoto Y, Seto T, Kashiyama T, Omata H (2018) Road damage detection and classification using deep neural networks with smartphone images. Comput-Aided Civ Infrastruct Eng 33(12):1127–1141
Cheng Y-T, Lin Y-C, Ravi R, Habib A Detection and visualization of narrow lane regions in work zones using LiDAR-based mobile mapping systems
Hsu Y-W, Perng J-W, Wu Z-H Design and implementation of an intelligent road detection system with multisensor integration. In: 2016 international conference on machine learning and cybernetics, vol 1, pp 219–225
Gupta N, Ahmed Z, Vishnoi C, Agarwal AK, Ather D (2020) Smart road management system with rough road detection. TechRxiv. Preprint 12757979.v1
Du K, Xin J, Shi Y, Liu D, Zhang Y A high-precision vision-based mobile robot slope detection method in an unknown environment. In: 2018 Chinese automation congress, pp 3192–3197
Tareen SAK, Khan HM Novel slope detection and calculation techniques for mobile robots. In: 2016 2nd international conference on robotics and artificial intelligence, pp 158–163
Fauzi AA, Utaminingrum F, Ramdani F (2020) Road surface classification based on LBP and GLCM features using KNN classifier. Bull Electr Eng Inform 9(4):1446–1453
Zhang X, Cui J, Wang W, Lin C (2017) A study for texture feature extraction of high-resolution satellite images based on a direction measure and gray level co-occurrence matrix fusion algorithm. Sensors 17(7):1474
Triantafyllou D, Kotoulas N, Krinidis S, Ioannidis D, Tzovaras D (2017) Large vehicle recognition and classification for traffic management and flow optimization in narrow roads. In: IEEE smart world, ubiquitous intelligence & computing, advanced & trusted computed, scalable computing & communications, cloud & big data computing, Internet of people and smart city innovation 2017, pp 1–4
Goyal A, Singh M, Srivastava A (2019) Lane detection on roads using computer vision. Int J Eng Adv Technol
Zhou X, Chen X, Zhang Y (2018) Narrow road extraction from remote sensing images based on super-resolution convolutional neural network. In: IGARSS 2018—2018 IEEE international geoscience and remote sensing symposium, pp 685–688
Manoharan K, Daniel P (2019) Autonomous lane detection on hilly terrain for perception-based navigation applications. Imaging Sci J 67(8):453–463
Cai K, Chi W, Qing-Hu Meng M A vision-based road surface slope estimation algorithm for mobile service robots in indoor environments. In: 2018 IEEE international conference on information and automation (ICIA), pp 621–626
Guo Y, Chen G, Zhang J (2021) Measurement of road slope based on computer vision. J Phys: Conf Ser 1802(3):032063
Li Q, Min G, Chen P, Liu Y, Tian S, Zhang D, Zhang W (2020) Computer vision-based techniques and path planning strategy in a slope monitoring system using the unmanned aerial vehicle. Int J Adv Rob Syst 17(2):1729881420904303
Sivaraman S, Trivedi MM A review of recent developments in vision-based vehicle detection. In: 2013 IEEE intelligent vehicles symposium (IV), pp 310–315
Xu Z, Shen Z, Li Y, Xia L, Wang H, Li S, Jiao S, Lei Y (2020) Road extraction in mountainous regions from high-resolution images based on DSDNet and terrain optimization. Remote Sens 13(1):90
Song J, Song H, Wang S (2021) PTZ camera calibration based on improved DLT transformation model and vanishing point constraints. Optik 225:165875
Yin Z, Dai Q, Guo H, Chen H, Chao L (2018) Estimation road slope and longitudinal velocity for four-wheel drive vehicle. IFAC-Papers OnLine 51(31):572–577
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Madake, J., Vyas, A., Pawale, V., Chaudhary, V., Bhatlawande, S., Shilaskar, S. (2023). Vision-Based Driver Assistance System to Detect Mountainous Roads Using GLCM and Haralick Texture Features. In: Rao, U.P., Alazab, M., Gohil, B.N., Chelliah, P.R. (eds) Security, Privacy and Data Analytics. ISPDA 2022. Lecture Notes in Electrical Engineering, vol 1049. Springer, Singapore. https://doi.org/10.1007/978-981-99-3569-7_10
Download citation
DOI: https://doi.org/10.1007/978-981-99-3569-7_10
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-3568-0
Online ISBN: 978-981-99-3569-7
eBook Packages: Computer ScienceComputer Science (R0)