Abstract
Autonomous vehicles face significant challenges in accurately identifying vehicles, objects, and traffic signals under adverse weather conditions and poor lighting. To address these issues, we introduce a novel detection system utilizing automatic white balance techniques, specifically the Adaptive Retinex algorithm, to restore visibility and enhance color. This system is integrated with a Faster R-CNN framework enhanced by non-maximum suppression to improve the accuracy of object detection. Employing a combination of three datasets—Dawn, MCWRD, and Indian Roads Dataset (IRD)—our method includes over 6000 augmented images representing diverse environmental conditions. We also implement an optimized version of Differentiable ARchiTecture Search (DARTS) to dynamically fine-tune the architectural parameters of our detection model. This approach has successfully achieved a detection accuracy of 97.43% with a minimal loss rate, demonstrating significant potential for enhancing navigation safety in autonomous vehicles across various challenging environments.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
Gautam S, Kumar A (2023) Image-based automatic traffic lights detection system for autonomous cars: a review. Multimed Tools Appl 82(17):26135–26182. https://doi.org/10.1007/s11042-023-14340-1
Kuang H, Chen L, Gu F, Chen J, Chan L, Yan H (2016) Combining Region-of-Interest Extraction and Image Enhancement for Nighttime Vehicle Detection. IEEE Intell Syst 31(3):57–65. https://doi.org/10.1109/MIS.2016.17
Shen Z, Zhu X, Cao X, Chen J (2019) Measurement of blooming effect of DMSP-OLS nighttime light data based on NPP-VIIRS data. Ann GIS 25(2):153–165. https://doi.org/10.1080/19475683.2019.1570336
Golcarenarenji G, Martinez-Alpiste I, Wang Q, Alcaraz-Calero JM (2023) Robust real-time traffic light detector on small-form platform for autonomous vehicles. J Intell Transp Syst Technol Plan Oper. https://doi.org/10.1080/15472450.2023.2205018
Saxena S, Dey S, Shah M, Gupta S (2024) Traffic sign detection in unconstrained environment using improved YOLOv4. Expert Syst. Appl. 238:121836. https://doi.org/10.1016/j.eswa.2023.121836
Shojaiee F, Baleghi Y (2023) EFASPP U-Net for semantic segmentation of night traffic scenes using fusion of visible and thermal images. Eng. Appl. Artif. Intell. 117:105627. https://doi.org/10.1016/j.engappai.2022.105627
Jiang Y, Wang Y, Zhao M, Zhang Y, Qi H (2024) Nighttime traffic object detection via adaptively integrating event and frame domains. Fundam Res. https://doi.org/10.1016/j.fmre.2023.08.004
Vieira de Mello JP et al (2021) Deep traffic light detection by overlaying synthetic context on arbitrary natural images. Comput Graph 94:76–86. https://doi.org/10.1016/j.cag.2020.09.012
Zhang J, Zhang H, Lang D, Xu Y, Li HA, Li X (2023) Research on rainy day traffic sign recognition algorithm based on PMRNet. Math Biosci Eng 20(7):12240–12262. https://doi.org/10.3934/mbe.2023545
Tang J, Feng G (2023) Background-detail restoration image deraining network based on convolutional dictionary network. Signal Process Image Commun 119:117057. https://doi.org/10.1016/j.image.2023.117057
Yu R, Li X, Bi T (2024) Modelling and validation of LiDAR noise distribution in fog and rain. Meas J Int Meas Confed 229:114472. https://doi.org/10.1016/j.measurement.2024.114472
Xiaojun B, Zheng C, Jianyu Y, Haibo W (2022) LRP-net: A lightweight recursive pyramid network for single image deraining. Neurocomputing 490:181–192. https://doi.org/10.1016/J.NEUCOM.2022.03.035
Hu M, Wu Y, Yang Y, Fan J, Jing B (2023) DAGL-Faster: Domain adaptive faster r-cnn for vehicle object detection in rainy and foggy weather conditions. Displays 79:102484. https://doi.org/10.1016/J.DISPLA.2023.102484
Singh A, Kumar DP, Shivaprasad K, Mohit M, Wadhawan A 2021 Vehicle Detection and Accident Prediction in Sand/Dust Storms. In: Proc. - 2021 Int. Conf. Comput. Sci. ICCS 2021, pp. 107–111,
Aloufi N, Alnori A, Thayananthan V, Basuhail A (2023) Object detection performance evaluation for autonomous vehicles in sandy weather environments. Appl Sci. https://doi.org/10.3390/app131810249
Meng X, Liu Y, Fan L, Fan J (2023) YOLOv5s-fog: an improved model based on YOLOv5s for object detection in foggy weather scenarios. Sensors 23(11):1–16. https://doi.org/10.3390/s23115321
Liu Z, Zhao S, Wang X (2023) Research on driving obstacle detection technology in foggy weather based on GCANet and feature fusion training. Sensors. https://doi.org/10.3390/s23052822
Iqbal J, Hafiz R, Ali M (2022) FogAdapt: Self-supervised domain adaptation for semantic segmentation of foggy images. Neurocomputing 501:844–856. https://doi.org/10.1016/j.neucom.2022.05.086
Zhao X, Xu W, Ma J, Li H, Chen Y, Rong J (2019) Effects of connected vehicle-based variable speed limit under different foggy conditions based on simulated driving. Accid Anal Prev 128(May):206–216. https://doi.org/10.1016/j.aap.2019.04.020
Wang Z, Zhan J, Li Y, Zhong Z, Cao Z (2021) A new scheme of vehicle detection for severe weather based on multi-sensor fusion. Meas J Int Meas Confed 191(December):2022. https://doi.org/10.1016/j.measurement.2022.110737
Park W, Jin M, Kim Y, Kim K, Lee S (2023) Investigating the effect of road lighting color temperature on road visibility in night foggy conditions. Appl Ergon 106:103899. https://doi.org/10.1016/j.apergo.2022.103899
Ooi JBH, Wong CJ, Edmund Loh WM (2023) A multiple scattering theory approach: numerical model for haze detection using horizontal scanning LIDAR. Opt Lasers Eng. https://doi.org/10.1016/j.optlaseng.2023.107713
Guan S, Wang J, Wang X, Zhang B, Liang H (2024) Improved RefineDNet algorithm for precise environmental perception of autonomous earthmoving machinery under haze and fugitive dust conditions. Adv Eng Inf 59:102326. https://doi.org/10.1016/j.aei.2023.102326
Mo Y, Li C, Zheng Y, Wu X (2022) DCA-CycleGAN: Unsupervised single image dehazing using Dark Channel Attention optimized CycleGAN. J Vis Commun Image Represent 82:103431. https://doi.org/10.1016/j.jvcir.2021.103431
Pal NS, Lal S, Shinghal K (2018) Visibility enhancement of images degraded by hazy weather conditions using modified non-local approach. Optik (Stuttg) 163:99–113. https://doi.org/10.1016/j.ijleo.2018.02.067
Dutta P, Saikia B, Banik AK (2024) Novel distance measure for q-rung orthopair fuzzy sets with application to transportation problem. Int J Inf Technol 1–18.
Sarathkumar K, Sudhakar P, Kanmani AC (2024) Enhancing intrusion detection using coati optimization algorithm with deep learning on vehicular Adhoc networks. Int J Inf Technol 16:3009–3018.
Babaei P, Riahinia N, Ebadati EOM, Azimi A (2024) Autonomous vehicles’ object detection architectures ranking based on multi-criteria decision-making techniques. Int J Inf Technol 16:2343–2352.
Ashwin SH, Naveen Raj R (2023) Deep reinforcement learning for autonomous vehicles: lane keep and overtaking scenarios with collision avoidance. Int J Inf Technol 15(7):3541–3553
Kaviarasan R, Arulmurgan A (2021) Salp swarm bio inspired algorithm for detecting non line of sight vehicles in VANETs. Int J Inf Technol 13(4):1601–1613
Luo JQ, Fang HS, Shao FM, Zhong Y, Hua X (2021) Multi-scale traffic vehicle detection based on faster R-CNN with NAS optimization and feature enrichment. Def Technol 17(4):1542–1554. https://doi.org/10.1016/j.dt.2020.10.006
Diaz-Cabrera M, Cerri P, Medici P (2015) Robust real-time traffic light detection and distance estimation using a single camera. Expert Syst Appl 42(8):3911–3923. https://doi.org/10.1016/j.eswa.2014.12.037
Dubey U, Chaurasiya RK (2021) Efficient traffic sign recognition using CLAHE-based image enhancement and ResNet CNN architectures. Int J Cogn Inf Nat Intell 15(4):1–19. https://doi.org/10.4018/IJCINI.295811
Yuming L, Shuqing G (2021) Traffic signal light detection and recognition based on canny operator. J Meas Eng 9(3):167–180. https://doi.org/10.21595/JME.2021.22024
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors affirm that there is no conflict of interest to disclose in the present matter. We maintain a commitment to transparency and ethical conduct in all our work.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Kumar, A., Gautam, S. A hybrid framework for heterogeneous object detection amidst diverse and adverse weather conditions employing Enhanced-DARTS. Int. j. inf. tecnol. (2024). https://doi.org/10.1007/s41870-024-02164-7
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s41870-024-02164-7