Enhanced Yolov5 Deep Learning Technique for Multi-Object Detection in Autonomous Vehicle in Extreme Weather Condition
Keywords:
CNN, R-CNN, YOLOV5, Single shot object detection, Multi object detectionAbstract
Autonomous vehicle requires more accurate object detection and object classification for the real-world environment. Detection and classification of objects in the stable environment using deep learning framework yields the very efficient result. But in real situation due to rapid changes in the real environment object detection in harsh condition fails due to the various challenges in it. In the proposed work considered two types of dataset image [KITTI] and video [BDD] with nine various environment condition -normal, night, rain, rain with night, low light, high illumination, cluttered environment, FOG, high speed. Applied enhanced robust deep learning algorithm YOLOV5 to all the above conditions and results are compared with the accuracy with the previous work. From the enhanced Yolov5 resulted in 98.7%, 76%, 76%,75%, 71% in normal, rainy, haze, high illumination, night weather condition respective. Proposed model is giving significant improvement in accuracy, precision, recall than the previous work in the extreme weather condition.
Downloads
References
Joel Janai, Fatma Guney, Aseem Behl, Andreas Geiger,” Computer Vision for Autonomous Vehicles: Problems, Datasets and State of the Art”, arXiv: 1704.05519v2 [cs.CV. 2019].
Shanshan Zhang, Rodrigo Benenson, Mohamed Omran, Jan Hosang and Bernt Schiele,” How Far are We from Solving Pedestrian Detection?”, arXiv:1602.01237v2 [cs.CV] .2016.
Joel Janai, Fatma G uney, Anurag Ranjan, Michael Black, and Andreas Geiger. Unsupervised Learning of Multi-Frame Optical Flow with Occlusions". In: Proc. of the European Conf. on Computer Vision (ECCV). 2018.
Siyu Tang, Bjoern Andres, Mykhaylo Andriluka, and Bernt Schiele.Multi-person Tracking by Multicut and Deep Matching". In: Proc. Of the European Conf. on Computer Vision (ECCV) Workshops. 2016.
Qasem Abu Al-Haija , Manaf Gharaibeh ,Ammar Odeh, “Detection in Adverse Weather Conditions for Autonomous Vehicles via Deep Learning”, MDPI, 2022..
Mazin Hnewa and Hayder Radha,” Object Detection Under Rainy Conditions for Autonomous Vehicles: A Review of State-of-the-Art and Emerging Techniques”, arXiv:2006.16471v4 [cs.CV] 12 Feb 2021.
Kim, Y., Hwang, H., Shin, J.:Robust object detection under harsh autonomous-driving environments. IET Image Process.16, 958–971 (2022).
Abhishek Balasubramaniam, Sudeep Pasricha, “Object Detection in Autonomous Vehicles: Status and Open Challenges, 2021.
Top 10 Popular Datasets for Autonomous Driving Projects (analyticsindiamag.com)
Gene Lewis, “Object Detection for Autonomous Vehicles”, 2015.
https://blog.roboflow.com/yolov5-improvements-and-evaluation/.
https://www.exxactcorp.com/blog/DeepLearning/YOLOv5-PyTorch-Tutorial
Shanshan Zhang, Rodrigo Benenson, Mohamed Omran, Jan Hosang and Bernt Schiele,” How Far are We from Solving Pedestrian Detection?”, arXiv:1602.01237v2 [cs.CV] .2016.
Joel Janai, Fatma G uney, Anurag Ranjan, Michael Black, and Andreas Geiger. Unsupervised Learning of Multi-Frame Optical Flow with Occlusions". In: Proc. of the European Conf. on Computer Vision (ECCV). 2018.
Markus Braun, Sebastian Krebs, Fabian Flohr, and Dariu M. Gavrila. The EuroCity Persons Dataset: A Novel Benchmark for Object Detection". In: IEEE Trans. on Pattern Analysis and Machine Intelligence (PAMI) (2019).
Marius Cordts, Mohamed Omran, Sebastian Ramos, Timo Rehfeld, Markus Enzweiler, Rodrigo Benenson, Uwe Franke, Stefan Roth, and Bernt Schiele. The Cityscapes Dataset for Semantic Urban Scene Understanding". In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR). 2016.
Laura Leal-Taix_e, Cristian Canton-Ferrer, and Konrad Schindler. Learning by Tracking: Siamese CNN for Robust Target Association". In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR) Workshops. 2016.
Siyu Tang, Bjoern Andres, Mykhaylo Andriluka, and Bernt Schiele.Multi-person Tracking by Multicut and Deep Matching". In: Proc. Of the European Conf. on Computer Vision (ECCV) Workshops. 2016.
Ahmed I, Ahmad M, Ahmad A, Jeon G (2021) IoT-based crowd monitoring system: Using SSD with transfer learning. Comput Electr Eng 93:107226.
Wang Q et al (2023) Deep convolutional cross-connected kernel mapping support vector machine based on SelectDropout. Inf Sci 626:694–709.
Ding L, Xu X, Cao Y, Zhai G, Yang F, Qian L (2021) Detection and tracking of infrared small target by jointly using SSD and pipeline flter. Digit Signal Process 110:102949.
Yundong LI et al (2020) Multi-block SSD based on small object detection for UAV railway scene surveillance. Chin J Aeronaut 33(6):1747–1755
Li X, Li Y, Shen C, Dick A, Hengel AVD (2013) Contextual hypergraph modeling for salient object detection. In: 2013 IEEE International Conference on Computer Vision, Sydney, pp. 3328–3335.
Jiang H, Wang J, Yuan Z, Wu Y, Zheng N, Li S (2013) Salient object detection: a discriminative regional feature integration approach. In: 2013 IEEE Conference on Computer Vision and Pattern Recognition, Portland, pp 2083–209
Emmanuel Maggiori, Yuliya Tarabalka, Guillaume Charpiat and Pierre Alliez. “Can Semantic Labeling Methods Generalize to Any City? The Inria Aerial Image Labeling Benchmark”. IEEE International Geoscience and Remote Sensing Symposium (IGARSS). 2017.
Wei Liu, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy, Scott E. Reed, Cheng-Yang Fu, and Alexander C. Berg. SSD: Single Shot MultiBox Detector". In: Proc. of the European Conf. on Computer Vision (ECCV). 2016.
Mohana, S.D., Bharathi, R.K. (2021). Face Template Security: LBP-Based LSB Watermarking Technique for Multi-class SVM Classification Using HoG. In: Komanapalli, V.L.N., Sivakumaran, N., Hampannavar, S. (eds) Advances in Automation, Signal Processing, Instrumentation, and Control. i-CASIC 2020. Lecture Notes in Electrical Engineering, vol 700. Springer, Singapore. https://doi.org/10.1007/978-981-15-8221-9_148
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
