ISDNet: AI-enabled Instance Segmentation of Aerial Scenes for Smart Cities
The DOI matches its Crossref record; 61 of the 61 references it cites were found in a registry or an index.
Abstract
Aerial scenes captured by UAVs have immense potential in IoT applications related to urban surveillance, road and building segmentation, land cover classification, and so on, which are necessary for the evolution of smart cities. The advancements in deep learning have greatly enhanced visual understanding, but the domain of aerial vision remains largely unexplored. Aerial images pose many unique challenges for performing proper scene parsing such as high-resolution data, small-scaled objects, a large number of objects in the camera view, dense clustering of objects, background clutter, and so on, which greatly hinder the performance of the existing deep learning methods. In this work, we propose ISDNet (Instance Segmentation and Detection Network), a novel network to perform instance segmentation and object detection on visual data captured by UAVs. This work enables aerial image analytics for various needs in a smart city. In particular, we use dilated convolutions to generate improved spatial context, leading to better discrimination between foreground and background features. The proposed network efficiently reuses the segment-mask features by propagating them from early stages using residual connections. Furthermore, ISDNet makes use of effective anchors to accommodate varying object scales and sizes. The proposed method obtains state-of-the-art results in the aerial context.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 73,472
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.81 · Cited by 32,684
Feature Pyramid Networks for Object Detection
Lin, T.-Y., Dollar, P., Girshick, R., He, K., Hariharan, B., & Belongie, S. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.106 · Cited by 30,939
He, K., Gkioxari, G., Dollar, P., & Girshick, R. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.322 · Cited by 29,137
Girshick, R. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.169 · Cited by 28,105
Chen, L.-C., Papandreou, G., Kokkinos, I., Murphy, K., & Yuille, A. L. (2018) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2017.2699184 · Cited by 22,392
YOLO9000: Better, Faster, Stronger
Redmon, J., & Farhadi, A. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.690 · Cited by 19,892
Aggregated Residual Transformations for Deep Neural Networks
Xie, S., Girshick, R., Dollar, P., Tu, Z., & He, K. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.634 · Cited by 12,465
Path Aggregation Network for Instance Segmentation
Liu, S., Qi, L., Qin, H., Shi, J., & Jia, J. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00913 · Cited by 10,011
Research works printed but not linked: 8
- Jian Ding , Nan Xue , Yang Long , Gui-Song Xia , and Qikai Lu. 2018. Learning ROI transformer for detecting oriented objects in aerial images. arXiv preprint arXiv:1812.00155 ( 2018 ). Jian Ding, Nan Xue, Yang Long, Gui-Song Xia, and Qikai Lu. 2018. Learning ROI transformer for detecting oriented objects in aerial images. arXiv preprint arXiv:1812.00155 (2018). · arXiv
- Spyros Gidaris and Nikos Komodakis . 2016. Attend refine repeat: Active box proposal generation via in-out localization. arXiv preprint arXiv:1606.04446 ( 2016 ). Spyros Gidaris and Nikos Komodakis. 2016. Attend refine repeat: Active box proposal generation via in-out localization. arXiv preprint arXiv:1606.04446 (2016). · arXiv
- Kaiming He , Georgia Gkioxari , Piotr Dollár , and Ross Girshick . 2017 . Mask R-CNN. In Proceedings of the IEEE International Conference on Computer Vision. 2961–2969 . Kaiming He, Georgia Gkioxari, Piotr Dollár, and Ross Girshick. 2017. Mask R-CNN. In Proceedings of the IEEE International Conference on Computer Vision. 2961–2969.
- K. He , X. Zhang , S. Ren , and J. Sun . 2016. Deep residual learning for image recognition . In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’16) . 770–778. K. He, X. Zhang, S. Ren, and J. Sun. 2016. Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’16). 770–778.
- Tsung-Yi Lin , Michael Maire , Serge Belongie , James Hays , Pietro Perona , Deva Ramanan , Piotr Dollár , and C. Lawrence Zitnick . 2014. Microsoft COCO: Common objects in context . In Proceedings of the European Conference on Computer Vision. Springer, 740–755 . Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollár, and C. Lawrence Zitnick. 2014. Microsoft COCO: Common objects in context. In Proceedings of the European Conference on Computer Vision. Springer, 740–755.
- Wei Liu , Dragomir Anguelov , Dumitru Erhan , Christian Szegedy , Scott Reed , Cheng-Yang Fu , and Alexander C . Berg . 2016 . SSD : Single shot multibox detector. In Proceedings of the European Conference on Computer Vision. Springer , 21–37. Wei Liu, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy, Scott Reed, Cheng-Yang Fu, and Alexander C. Berg. 2016. SSD: Single shot multibox detector. In Proceedings of the European Conference on Computer Vision. Springer, 21–37.
- 10.5555/2969442.2969462 · doi:10.5555/2969442.2969462
- 10.5555/2969239.2969250 · doi:10.5555/2969239.2969250
Cited by
Interpreting Black-Box Models: A Review on Explainable Artificial Intelligence
Hassija, V., Chamola, V., Mahapatra, A., Singal, A., Goel, D., Huang, K., Scardapane, S., Spinelli, I., Mahmud, M., & Hussain, A. (2024) · Cognitive Computation · doi:10.1007/s12559-023-10179-8 · Cited by 2,495
“These models make predictions based on input data, but the decision-making process and reasoning behind the predictions are not transparent to the user [31].”
BackgroundSelf-citationA Review on the Role of Machine Learning in Enabling IoT Based Healthcare Applications
Bharadwaj, H. K., Agarwal, A., Chamola, V., Lakkaniga, N. R., Hassija, V., Guizani, M., & Sikdar, B. (2021) · IEEE Access · doi:10.1109/access.2021.3059858 · Cited by 208
“The resources of a smart city can never be fully exploited without intelligent, i.e., cognitive machinery [137].”
BackgroundSelf-citationAgriSegNet: Deep Aerial Semantic Segmentation Framework for IoT-Assisted Precision Agriculture
Anand, T., Sinha, S., Mandal, M., Chamola, V., & Yu, F. R. (2021) · IEEE Sensors Journal · doi:10.1109/jsen.2021.3071290 · Cited by 160
“Recent advancements in multi-modal sensing techniques, wireless communication, Internet of Things (IoT), artificial intelligence (AI) techniques and cloud computation has spurred rapid advancements in the proliferation of remote sensing based data analytics for automated decision making [12], [13].”
BackgroundSelf-citationLearning to Aggregate Multi-Scale Context for Instance Segmentation in Remote Sensing Images
Liu, Y., Li, H., Hu, C., Luo, S., Luo, Y., & Chen, C. W. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3336563 · Cited by 195
“Following previous works [20], [49], [51], we split them into 800 × 800 patches with a stride of 200 for fair benchmarking with existing methods.”
MethodChougule, A., Chamola, V., Sam, A., Yu, F. R., & Sikdar, B. (2023) · IEEE Open Journal of Vehicular Technology · doi:10.1109/ojvt.2023.3335180 · Cited by 184
“Fog, sleet, snow, and rain all reduce the vision and perception of self-driving cars [57], [58].”
BackgroundSelf-citationLuo, J., Zhao, T., Cao, L., & Biljecki, F. (2022) · Landscape and Urban Planning · doi:10.1016/j.landurbplan.2022.104569 · Cited by 89
“Thanks to the fast development of CV, such as semantic segmentation and object detection, studies on visual quality evaluation based on such trending techniques are proliferating (Wu et al., 2021; Garg et al., 2021; Wilkins et al., 2022; Wu and Biljecki, 2021; Ito and Biljecki, 2021).”
MethodKhan, F. S., Mazhar, S. S., Mazhar, K., AlSaleh, D., & Mazhar, A. (2025) · Artificial Intelligence Review · doi:10.1007/s10462-025-11215-9 · Cited by 150
Domain-Aware Unsupervised Hyperspectral Reconstruction for Aerial Image Dehazing
Mehta, A., Sinha, H., Mandal, M., & Narang, P. (2021) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv48630.2021.00046 · Cited by 79
“The aerial images and video data facilitate numerous applications such as aerial surveillance [28, 29, 30], search and rescue, event recognition [34], urban and rural scene understanding [45, 12].”
BackgroundSelf-citationIntegrating machine learning with agroecosystem modelling: Current state and future challenges
Aderele, M. O., Srivastava, A. K., Butterbach‐Bahl, K., & Rahimi, J. (2025) · European Journal of Agronomy · doi:10.1016/j.eja.2025.127610 · Cited by 74
“To address the limitations inherent in both PBMs and ML, the integration of the two into hybrid models has gained popularity in agroecosystem modelling (Garg et al., 2021).”
DroneSegNet: Robust Aerial Semantic Segmentation for UAV-Based IoT Applications
Chakravarthy, A. S., Sinha, S., Narang, P., Mandal, M., Chamola, V., & Yu, F. R. (2022) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2022.3144358 · Cited by 59
“Garg et al. [65] utilized Hybrid Task Cascade for joint detection and segmentation, with addition of residual connections and dilated convolutions for improved spatial context.”
MethodSelf-citationA Lightweight Adaptive RoI Extraction Network for Precise Aerial Image Instance Segmentation
Zeng, X., Wei, S., Shi, J., & Zhang, X. (2021) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2021.3121485 · Cited by 45
Ye, W., Zhang, W., Lei, W., Zhang, W., Chen, X., & Wang, Y. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.121007 · Cited by 42
A real-time efficient object segmentation system based on U-Net using aerial drone images
Ahmed, I., Ahmad, M., & Jeon, G. (2021) · Journal of Real-Time Image Processing · doi:10.1007/s11554-021-01166-z · Cited by 35
“[56], presented artificial intelligence based instance segmentation model for aerial scenes.”
BackgroundIoT Enabled Deep Learning Based Framework for Multiple Object Detection in Remote Sensing Images
Ahmed, I., Ahmad, M., Chehri, A., Hassan, M. M., & Jeon, G. (2022) · Remote Sensing · doi:10.3390/rs14164107 · Cited by 33
Liu, Y., Sun, T., Wu, K., Xiang, W., Zhang, J., Zhang, H., & Feng, M. (2025) · Natural Resources Research · doi:10.1007/s11053-025-10462-5 · Cited by 29
“…lack of deep model interpretability is primarily due to the black-box nature of AI modeling; that is, the model/algorithm can perform perfectly, but it is unable to render any reasonable interpretations of its decision-making processes (Garg et al., 2021; Hassija et al., 2023; Somani et al., 2023).”
GLFRNet: Global-Local Feature Refusion Network for Remote Sensing Image Instance Segmentation
Zhao, J., Wang, Y., Zhou, Y. Z., Du, W.-L., Yao, R., & Saddik, A. E. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3530515 · Cited by 21
“These methods usually improve FPN to enhance the ability of multiscale perception and modify regression and segmentation heads to augment the ability of detailed perceptual [8], [9], [19], [20], [21], [22], [23], [24], [25].”
InfluentialUnsupervised Haze Removal for Aerial Imagery Based on Asymmetric Contrastive CycleGAN
He, X., Ji, W., & Xie, J. (2022) · IEEE Access · doi:10.1109/access.2022.3186004 · Cited by 12
“In addition, aerial images can also facilitate numerous subsequent high-level vision applications, such as target detection [12], aerial surveillance [13], scene understanding [14], land cover classification [15].”
BackgroundThe Role of IoT in Shaping the Future of Geospatial AI
Rana, R., & Bhambri, P. (2024) · Advances in geospatial technologies book series · doi:10.4018/979-8-3693-8054-3.ch007 · Cited by 6
A transformer-based UAV instance segmentation model TF-YOLOv7
Tan, L., Liu, Z., Huang, X., Li, D., & Wang, F. (2024) · Signal Image and Video Processing · doi:10.1007/s11760-023-02992-3 · Cited by 6
Sliding mode based backstepping control for UAV-UAV interception strategy with K-mean clustering
Abubakar, A. N., Nasir, A., & Saif, A.-W. A. (2025) · International Journal of Intelligent Robotics and Applications · doi:10.1007/s41315-025-00495-7 · Cited by 5
Adaptive Pruning of Channel Spatial Dependability in Convolutional Neural Networks
Xie, W., Yuan, M., Ma, J., & Li, Y. (2024) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3664647.3681419 · Cited by 8
“Convolutional Neural Networks (CNNs) have been widely applied in various computer vision tasks, including image classification [38, 47–49], semantic segmentation [4, 12, 20], object detection [3, 13, 15], and many more challenging tasks.”
Deceptive Waypoint Sequencing Based UAV–UAV Interception Control Using DBSCAN Learning Strategy
Abubakar, A. N., Nasir, A., & Saif, A. A. (2026) · Machine Learning and Knowledge Extraction · doi:10.3390/make8030054 · Cited by 1
AUTOMATIC OBJECT SEGMENTATION TO SUPPORT CRISIS MANAGEMENT OF LARGE-SCALE EVENTS
Azimi, S. M., Kiefl, R., Gstaiger, V., Bahmanyar, R., Merkle, N., Henry, C., Rosenbaum, D., & Kurz, F. (2021) · The international archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprs-archives-xliii-b2-2021-433-2021 · Cited by 2
“In addition, ISDNet (Garg et al., 2020) has been developed which applies atrous spatial pyramid pooling (ASPP) module from the DeepLabv3+ (Chen et al., 2018) algorithm in the Mask-RCNN and CascadedRCNN manner.”
MethodA survey on state-of-the-art computing for cyber-physical systems
Dashora, R., & Babu, M. R. (2023) · AIP conference proceedings · doi:10.1063/5.0150080
Impact of Artificial Intelligence in Urban Tourism
Baby, J., Sindhu, K. P., & Biju John, M. (2024) · doi:10.46632/rmc/5/2/15
Modeling and Analysis of Kamikaze UAV Design with 3 Different Wing Configurations
Demirel, A. R., YAVUZ, M. M., & Tokgöz, N. (2024) · Journal of Mathematical Sciences and Modelling · doi:10.33187/jmsm.1505481
Evaluating the Effectiveness of Panoptic Segmentation Through Comparative Analysis
Sara, C., Daşdemir, İ., & Güven, S. A. (2024) · Bitlis Eren Üniversitesi Fen Bilimleri Dergisi · doi:10.17798/bitlisfen.1473041
“These segmentation techniques are applied in various fields such as earth sciences [2],[3], smart cities [4]-[6], and healthcare services [7]-[9], and their applications are becoming increasingly widespread.”
BackgroundHusain (2025) · Journal of Education Technology · doi:10.23887/jet.v9i1.92673
Socially Responsible and Explainable Automated Fact-Checking and Hate Speech Detection
Vargas, F., Pardo, T. A. S., & Benevenuto, F. (2025) · doi:10.5753/ctd.2025.8511
Fundamental Overview of Medical Scientific Data Sharing
Guan, J. (2025) · Springer eBooks · doi:10.1007/978-981-95-2806-6_1 · Cited by 1
Leveraging artificial intelligence in eosinophilic esophagitis
Liberto, J. D., Snyder, D. L., & Codipilly, D. C. (2026) · npj gut and liver. · doi:10.1038/s44355-025-00046-8
Jin, Q., Zhang, Y., Peng, C., Hu, J., & Li, L. (2026) · Geo-spatial Information Science · doi:10.1080/10095020.2026.2707066
Metadata
- Authors
- Garg, P., Chakravarthy, A. S., Mandal, M., Narang, P., Chamola, V., & Guizani, M.
- Affiliations
- Birla Institute of Technology and Science, Pilani (IN)
- Malaviya National Institute of Technology Jaipur (IN)
- Qatar University (QA)
- ORCID
- Venue
- ACM Transactions on Internet Technology
- Published
- 2021-08-10
- Volume
- 21
- Issue
- 3
- Pages
- 1-18
- ISSN
- 1533-5399 (ISSN-L)
- 1557-6051
- OpenAlex
- W3193164413
- Cited by
- 32
- References
- 60
- Citations by year
- 2026: 3 · 2025: 8 · 2024: 7 · 2023: 4 · 2022: 4 · 2021: 6
- FWCI
- 1.89
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- ACM Transactions on Internet Technology (publishedVersion)
- Qatar University QSpace (Qatar University) (submittedVersion)
- Funders
- BITS Additional Competitive Research (PLN/AD/2018-19/5)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Remote-Sensing Image Classification
- Physical Sciences › Engineering › Civil and Structural Engineering › Infrastructure Maintenance and Monitoring
- Keywords
- instance segmentation, object detection, aerial images, UAV imagery, smart cities, urban surveillance, dilated convolution, skip connections, anchor-based detection, foreground-background discrimination, land cover classification
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.