Abstract
Semantic segmentation of aerial images plays a pivotal role in extracting detailed information about land cover, infrastructure, and natural features. Traditional single-channel segmentation models struggle to harness the rich information present in multi-channel aerial images, such as multi-spectral or hyperspectral data. While the DeepLabV3 + architecture has shown remarkable success in semantic segmentation tasks by exploiting multi-scale context and atrous convolutions, its performance on aerial images remains suboptimal due to the unique challenges of this domain. With the motive of addressing the difficulties in the existing semantic segmentation techniques for aerial images, the adoption of deep learning techniques is utilized. A multi-objective derived Adaptive Multichannel deeplabv3 + (AMC-Deeplabv3 +) with a new meta-heuristic algorithm called Improved Beluga whale optimization (IBWO) algorithm is proposed in this paper. Here, the hyperparameters of Multichannel deeplabv3 + are optimized by the IBWO algorithm and this model intends to set new benchmarks in the accuracy and contextual understanding of aerial image segmentation by integrating multi-channel data processing techniques and preserving spatial context. The proposed model attains improved accuracies of 98.65% & 98.72% for dataset 1 and 2 respectively and also achieves the dice coefficient of 98.73% & 98.85% respectively, with a computation time of 113.0123 s. The evolutional outcomes of the proposed model show significantly better than the state-of-the-art techniques.
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-023-17247-z/MediaObjects/11042_2023_17247_Fig1_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-023-17247-z/MediaObjects/11042_2023_17247_Fig2_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-023-17247-z/MediaObjects/11042_2023_17247_Figa_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-023-17247-z/MediaObjects/11042_2023_17247_Fig3_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-023-17247-z/MediaObjects/11042_2023_17247_Fig4_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-023-17247-z/MediaObjects/11042_2023_17247_Fig5_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-023-17247-z/MediaObjects/11042_2023_17247_Fig6_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-023-17247-z/MediaObjects/11042_2023_17247_Fig7_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-023-17247-z/MediaObjects/11042_2023_17247_Fig8_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-023-17247-z/MediaObjects/11042_2023_17247_Fig9_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-023-17247-z/MediaObjects/11042_2023_17247_Fig10_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs11042-023-17247-z/MediaObjects/11042_2023_17247_Fig11_HTML.png)
Similar content being viewed by others
Data availability statement
The data underlying this article are available in Semantic segmentation of aerial imagery “https://www.kaggle.com/datasets/humansintheloop/semantic-segmentation-of-aerialimagery?select=Semantic+segmentation+dataset”.
Aerial image segmentation dataset http://jiangyeyuan.com/ASD/Aerial%20Image%20Segmentation%20Dataset.html.
Abbreviations
- CNN:
-
Convolutional Neural Networks
- DCNN:
-
Deep Convolutional Neural Network
- IBWO:
-
Improved Beluga whale optimization
- FCN:
-
Fully Convolutional Neural Network
- IRRG:
-
Infrared, Red, and Green
- DRN:
-
Deep Residual Networks
- DFCN:
-
Deep Fully Convolutional Network
- CAM-DFCN:
-
Channel Attention Mechanism-Deep Fully Convolutional Neural Network
- ASPP:
-
Atrous Spatial Pyramid Pooling
- UAV:
-
Unmanned Aerial Vehicle
- OSM:
-
Open Street Map
- GAN:
-
Generative Adversarial Network
- DSM:
-
Digital Surface Models
- DSMF:
-
Digital Surface Models Fusion
- FoV:
-
Field-of-View
- VHR:
-
Very High Resolution
- BWO:
-
Beluga Whale Optimization
- GSO:
-
Glow-worm Swarm Optimization
- BOA:
-
Butterfly Optimization Algorithm
- COA:
-
Coyote Optimization Algorithm
References
Chakravarthy AS, Sinha S, Narang P, Mandal M, Chamola V, Yu FR (2022) DroneSegNet: robust aerial semantic segmentation for UAV-Based IoT applications. IEEE Trans Veh Technol 71(4):4277–4286
Esmael Agnaldo Aparecido, Santos Jefersson Alex Dos, da Silva Ricardo, Torres, (2018) On the ensemble of multiscale object-based classifiers for aerial images: a comparative study. Multimedia Tools Appl 77:24565–24592
Khan SD, Alarabi L, Basalamah S (2023) Segmentation of farmlands in aerial images by deep learning framework with feature fusion and context aggregation modules. Multimed Tools Appl 1–20. https://doi.org/10.1007/s11042-023-14962-5
Liu C, Wu Y, Liu J, Sun Z (2021) Improved YOLOv3 network for insulator detection in aerial images with diverse background interference. Electronics 10(7):771
Hong Z et al (2022) Highway crack segmentation from unmanned aerial vehicle images using deep learning. IEEE Geosci Remote Sens Lett 19:1–5
Deng G, Wu Z, Wang C, Xu M, Zhong Y (2022) CCANet: class-constraint coarse-to-fine attentional deep network for subdecimeter aerial image semantic segmentation. IEEE Trans Geosci Remote Sens 60:1–20
Anand T, Sinha S, Mandal M, Chamola V, Yu FR (2021) AgriSegNet: deep aerial semantic segmentation framework for IoT-assisted precision agriculture. IEEE Sens J 21(16):17581–17590
Liu W, Zhang Y, Fan H, Zou Y, Cui Z (2020) A new multi-channel deep convolutional neural network for semantic segmentation of remote sensing image. IEEE Access 8:131814–131825
Lee K, Kim JH, Lee H, Park J, Choi JP, Hwang JY (2022) Boundary-oriented binary building segmentation model with two scheme learning for aerial images. IEEE Trans Geosci Remote Sens 60:1–17
Li J, Sun B, Li S, Kang X (2022) Semisupervised semantic segmentation of remote sensing images with consistency self-training. IEEE Trans Geosci Remote Sens 60:1–11
Sun Y, Fu Z, Sun C, Hu Y, Zhang S (2022) Deep multimodal fusion network for semantic segmentation using remote sensing image and LiDAR data. IEEE Trans Geosci Remote Sens 60:1–18
Zhang M, Xu G, Chen K, Yan M, Sun X (2019) Triplet-based semantic relation learning for aerial remote sensing image change detection. IEEE Geosci Remote Sens Lett 16(2):266–270
Kaiser P, Wegner JD, Lucchi A, Jaggi M, Hofmann T, Schindler K (2017) Learning aerial image segmentation from online maps. IEEE Trans Geosci Remote Sens 55(11):6054–6068
Manickam R, Kumar Rajan S, Subramanian C et al (2020) Person identification with aerial imaginary using SegNet based semantic segmentation. Earth Sci Inform 13:1293–1304
Anilkumar P, Venugopal P (2022) Research contribution and comprehensive review towards the semantic segmentation of aerial images using deep learning techniques. Security and Communication Networks 1–32. https://doi.org/10.1155/2022/6010912
Yadavendra, Chand S (2022) Semantic segmentation and detection of satellite objects using U-Net model of deep learning. Multimed Tools Appl 81(30):44291–44310
Mou L, Hua Y, Zhu XX (2020) Relation matters: relational context-aware fully convolutional network for semantic segmentation of high-resolution aerial images. IEEE Trans Geosci Remote Sens 58(11):7557–7569
Volpi M, Tuia D (2018) Deep multi-task learning for a geographically-regularized SSAI. ISPRS J Photogramm Remote Sens 144:48–60
Chen K, Fu K, Yan M, Gao X, Sun X, Wei X (2018) SSAI with shuffling convolutional neural networks. IEEE Geosci Remote Sens Lett 15(2):173–177
Luo H, Chen C, Fang L, Zhu X, Lu L (2019) High-resolution aerial images semantic segmentation using deep fully convolutional network with channel attention mechanism. IEEE J Select Topics Appl Earth Observ Remote Sens 12(9):3492–3507
Cao Z et al (2019) End-to-end DSM fusion networks for semantic segmentation in high-resolution aerial images. IEEE Geosci Remote Sens Lett 16(11):1766–1770
Girisha S, Verma U, ManoharaPai MM, Pai RM (2021) "UVid-Net: Enhanced Semantic segmentation of UAV aerial videos by embedding temporal information. IEEE J Selected Topics Appl Earth Observ Remote Sens 14:4115–4127
Gupta A, Watson S, Yin H (2021) Deep learning-based aerial image segmentation with open data for disaster impact assessment. Neurocomputing 439:22–33
Abdollahi A, Pradhan B, Sharma G, Maulud KNA, Alamri A (2021) Improving road semantic segmentation using generative adversarial network. IEEE Access 9:64381–64392
He P, Jiao L, Shang R, Shuang Wang Xu, Liu DQ, Yang K, Zhao D (2022) MANet: Multi-scale aware-relation network for semantic segmentation in aerial scenes. IEEE Trans Geosci Remote Sens 60:1–15
Huang Z, Zhang Q, Zhang G (2022) MLCRNet: Multi-level context refinement for semantic segmentation in aerial images. Remote Sensing 14(6):1498
Diao Qi, Dai Y, Zhang Ce, Yan Wu, Feng X, Pan F (2022) Superpixel-based attention graph neural network for semantic segmentation in aerial images. Remote Sensing 14(2):305
Akbari Y, Al-Maadeed S, Adam K (2020) Binarization of degraded document images using convolutional neural networks and wavelet-based multichannel images. IEEE Access 8:153517–153534
Sudo Y, Itoyama K, Nishida K, Nakadai K (2020) Multi-channel environmental sound segmentation. In 2020 IEEE/SICE International Symposium on System Integration (SII), pp. 820–825. IEEE
Yao X, Guo Q, Li A (2021) Light-weight cloud detection network for optical remote sensing images with attention-based deeplabv3+ architecture. Remote Sensing 13(18):3617
Abro GEM (2022) Hand gesture-based control of autonomous UAV for mobile disinfectant dispenser. in 2022 international conference on future trends in smart communities (ICFTSC) (pp. 218–222). IEEE
Israr Ambar, Mustafa Ghulam E, Abro M. Sadiq, Khan Ali, Farhan Muhammad, SaifulAzrin Bin MohdZulkifli, (2021) Internet of things (IoT)-Enabled unmanned aerial vehicles for the inspection of construction sites: a vision and future directions. Math Problems Eng 2021:1–15
Chakravarthy Anirudh S, Sinha Soumendu, Narang Pratik, Mandal Murari, Chamola Vinay, Yu F Richard (2022) DroneSegNet: robust aerial semantic segmentation for uav-based iot applications. IEEE Trans Vehicular Technol 71(4):4277–4286
Behera Tanmay Kumar, Bakshi Sambit, Sa Pankaj Kumar (2023) A lightweight deep learning architecture for vegetation segmentation using UAV-captured aerial images. Sustain Comput: Inform Syst 37:100841
Behera TK, Bakshi S, Nappi M, Sa PK (2023) Superpixel-based multiscale CNN approach toward multiclass object segmentation from UAV-captured aerial images. IEEE J Selected Topics Appl Earth Observ Remote Sens 16:1771–1784
Zhong C, Li G, Meng Z (2022) Beluga whale optimization: A novel nature-inspired metaheuristic algorithm. Knowledge-Based Syst 251
Zhou H, Cheng H-Y, Wei Z-L, Zhao X, Tang A-D, Xie L (2021) A hybrid butterfly optimization algorithm for numerical optimization problems. Comput Intell Neurosci 2021:14
Chang GW, Cong Chinh N (2020) Coyote optimization algorithm-based approach for strategic planning of photovoltaic distributed generation. IEEE Access 8:36180–36190
Zainal N, Zain AM, Radzi NH, Udin A (2013) Glowworm swarm optimization (GSO) algorithm for optimization problems: a state-of-the-art review. Appl Mech Mater 421:507–511
Ulmas P, Liiv I (2020) Segmentation of satellite imagery using u-net models for land cover classification. arXiv preprint arXiv:2003.02899
Akcay O, Kinaci AC, Avsar EO, Aydar U (2022) Semantic segmentation of high-resolution airborne images with dual-stream deeplabv3+. ISPRS Int J Geo Inf 11(1):23
Masayoshi K, Katada Y, Ozawa N, Ibuki M, Negishi K, Kurihara T (2022) Automatic segmentation of non-perfusion area from fluorescein angiography using deep learning with uncertainty estimation. Informatics in Medicine Unlocked 32:101060
Anilkumar P, Venugopal P (2023) An enhanced multi-objective-derived adaptive deeplabv3 using g-rda for semantic segmentation of aerial images. Arab J Sci Eng 1–25
Funding
This research work received no external funding.
Author information
Authors and Affiliations
Contributions
Conceptualization, V.P; methodology, V.P; software, A.P.; validation, A.P; investigation, A.P; resources, V.P and A.P; writing—original draft preparation, A.P; writing—review and editing, V.P; visualization, V.P; supervision, V.P;
Corresponding author
Ethics declarations
Conflicts of interest
The authors declare no conflict of interest.
Additional information
Publisher's note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
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
Anilkumar, P., Venugopal, P. An adaptive multichannel DeepLabv3 + for semantic segmentation of aerial images using improved Beluga Whale Optimization Algorithm. Multimed Tools Appl 83, 46439–46478 (2024). https://doi.org/10.1007/s11042-023-17247-z
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-023-17247-z