DroneDAR: Long-Range Drone Distance Estimation Using Monocular Vision and Bounding-Box Features

David Han; Knut Peterson; Zaid Mayers

arxiv: 2606.07756 · v1 · pith:PAT3GFLCnew · submitted 2026-06-05 · 💻 cs.CV · cs.RO

DroneDAR: Long-Range Drone Distance Estimation Using Monocular Vision and Bounding-Box Features

Knut Peterson , Zaid Mayers , David Han This is my paper

Pith reviewed 2026-06-27 22:04 UTC · model grok-4.3

classification 💻 cs.CV cs.RO

keywords drone distance estimationmonocular visionbounding-box featuresgating mechanismlong-range detectionconvolutional backbonerange regression

0 comments

The pith

DroneDAR estimates long-range drone distances by gating convolutional features with bounding-box geometry.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper introduces DroneDAR for monocular distance estimation of small drones in long-range imagery where a detector first supplies a crop. It combines a convolutional backbone with explicit bounding-box cues through a lightweight gating mechanism to improve range prediction under scale variation and clutter. The study evaluates this model against a Droneranger-style baseline while measuring effects of backbone capacity, crop resolution, and regression losses across distance regimes. Experiments also catalog failure modes at long range such as sensitivity to bounding-box noise and loss of texture detail in tiny crops. This matters for building trackers and awareness systems that must operate when drones occupy only a few pixels.

Core claim

DroneDAR integrates a convolutional backbone with explicit bounding-box cues through a lightweight gating mechanism to predict range from detector-supplied image crops. Experiments show how backbone capacity, crop resolution, and regression loss functions affect performance across distance regimes and identify common long-range failure modes including bounding-box noise sensitivity and reduced texture detail.

What carries the argument

The lightweight gating mechanism that fuses convolutional appearance features extracted from the crop with explicit bounding-box geometry cues.

If this is right

Backbone capacity, crop resolution, and choice of regression loss affect estimation accuracy differently across short, medium, and long distance regimes.
Bounding-box noise and loss of texture detail in the crop are primary sources of error at long distances.
The results supply concrete design guidance for training range estimators that remain functional under real-world long-range conditions.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

The gating approach could be tested on other small-object ranging tasks that also receive detector crops, such as distant vehicles or birds.
Performance under varying detector qualities would quantify how much the method depends on box accuracy.
Pairing the single-frame estimator with multi-frame temporal filtering might mitigate cases where texture detail is minimal.

Load-bearing premise

A detector will supply bounding boxes accurate enough for the gating mechanism to help, and the cropped image still contains usable appearance information even when the drone occupies only a few pixels.

What would settle it

Compare DroneDAR performance against the ungated baseline on the same long-range test set after deliberately adding increasing levels of noise to the supplied bounding boxes; if the gating advantage vanishes, the central claim does not hold.

Figures

Figures reproduced from arXiv: 2606.07756 by David Han, Knut Peterson, Zaid Mayers.

**Figure 1.** Figure 1: Proposed model architecture for predicting the distance of a drone from the camera. We build on the DroneRanger [1] architecture by swapping [PITH_FULL_IMAGE:figures/full_fig_p002_1.png] view at source ↗

**Figure 2.** Figure 2: The bounding box feature gate takes the bounding box features [PITH_FULL_IMAGE:figures/full_fig_p003_2.png] view at source ↗

**Figure 3.** Figure 3: Plot of the error metrics for our final model compared to the original DroneRanger model for distances up to 200 ft. Longer distances are not [PITH_FULL_IMAGE:figures/full_fig_p005_3.png] view at source ↗

**Figure 4.** Figure 4: Examples of success cases where the model very accurately predicted the drone distance. These covered a wide variety of camera angles, lighting [PITH_FULL_IMAGE:figures/full_fig_p006_4.png] view at source ↗

**Figure 5.** Figure 5: Examples of failure cases where the model predicted inaccurate distances. Some of the failures were the result of inaccurate or noisy bounding [PITH_FULL_IMAGE:figures/full_fig_p006_5.png] view at source ↗

read the original abstract

Accurate distance estimation for small drones in long-range imagery is important for tracking and situational awareness, yet remains challenging due to extreme target scale variation, background clutter, and noisy visual cues. This paper studies monocular drone distance estimation using image crops together with bounding-box geometry, a practical setting in which a detector provides a candidate drone region and the model predicts range from appearance and box-derived features. We evaluate a Droneranger-style baseline, and introduce a new DroneDAR (Drone Detection And Ranging) model that combines a convolutional backbone with explicit bounding-box cues through a lightweight gating mechanism. Experiments analyze how backbone capacity, crop resolution, and regression loss functions affect performance across distance regimes. We further examine common failure modes at long distances, including sensitivity to bounding-box noise and reduced texture detail in the crop. The results provide guidance for designing and training range estimators that remain robust under real-world long-range conditions and highlight directions for improving reliability when drones occupy only a few pixels.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Desk Editor's Note private letter to a colleague

DroneDAR's gating fusion of box geometry with CNN features is a small practical tweak for drone ranging, but the abstract shows no numbers or ablations to confirm it beats the baseline under the failure cases it flags.

read the letter

The main thing to know is that this paper introduces DroneDAR, which adds a lightweight gating step to feed explicit bounding-box size and position into a conv backbone for monocular range regression on small drones. That specific combination for long-range drone work is the incremental novelty.

It does a reasonable job describing the setting: a detector supplies the crop and box, then the model predicts distance while dealing with scale changes, clutter, and low texture. The discussion of failure modes at long range, including box noise and sub-10-pixel targets, is useful practical context. Experiments on backbone capacity, crop resolution, and loss choices are mentioned and could give guidance to people tuning similar systems.

The soft spot is exactly what the stress-test note flags. The gating claim only matters if the upstream boxes stay reliable and the crop still carries signal when the drone is tiny. The abstract lists those as common problems yet gives no quantitative results, error bars, dataset details, or controlled ablations that isolate the gating contribution from box quality. Without that, the performance delta cannot be attributed to the architecture.

This is for applied CV or robotics groups working on drone tracking and situational awareness. A reader who needs monocular ranging under real long-range conditions might pick up some implementation hints, but the lack of numbers limits how far the claims can travel.

It deserves a serious referee if the full paper actually contains the promised experiments and ablations; the problem is real and the method is simple enough to evaluate quickly. Otherwise the evidence gap makes it hard to judge.

Referee Report

2 major / 0 minor

Summary. The paper introduces DroneDAR, a model that fuses a convolutional backbone with explicit bounding-box geometry via a lightweight gating mechanism for monocular distance estimation of small drones. It compares this to a Droneranger-style baseline, analyzes effects of backbone capacity, crop resolution, and regression losses across distance regimes, and examines failure modes including bounding-box noise sensitivity and loss of texture detail when targets occupy few pixels.

Significance. If the gating mechanism can be shown to deliver measurable gains under controlled conditions for long-range cases, the work would supply useful empirical guidance for practical monocular drone ranging systems. The current text, however, supplies no quantitative metrics, error bars, or dataset specifications, so the practical significance cannot yet be evaluated.

major comments (2)

Abstract: the description of experiments states that performance is analyzed across distance regimes and that failure modes are examined, yet no quantitative results, error bars, dataset details, or numerical metrics are reported, rendering the central performance claims unverifiable from the provided text.
Experiments section (implied by abstract): the manuscript flags sensitivity to bounding-box noise and reduced texture detail as common long-range failure modes, but provides no indication that experiments isolate the gating mechanism's contribution under controlled box noise or in sub-10-pixel regimes; without such isolation the reported deltas cannot be attributed to the proposed architecture.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive feedback highlighting the need for verifiable quantitative details and clearer experimental isolation. We address each major comment below and will revise the manuscript to incorporate the suggested improvements.

read point-by-point responses

Referee: Abstract: the description of experiments states that performance is analyzed across distance regimes and that failure modes are examined, yet no quantitative results, error bars, dataset details, or numerical metrics are reported, rendering the central performance claims unverifiable from the provided text.

Authors: We agree that the abstract would benefit from explicit numerical support. In the revised version we will expand the abstract to include key metrics such as mean absolute error and standard deviation across distance regimes, along with dataset specifications (image count, distance distribution) and error bars, ensuring the central claims are directly verifiable. revision: yes
Referee: Experiments section (implied by abstract): the manuscript flags sensitivity to bounding-box noise and reduced texture detail as common long-range failure modes, but provides no indication that experiments isolate the gating mechanism's contribution under controlled box noise or in sub-10-pixel regimes; without such isolation the reported deltas cannot be attributed to the proposed architecture.

Authors: The current experiments compare DroneDAR (with gating) against the baseline and analyze performance across regimes while noting bounding-box noise sensitivity as a failure mode. To strengthen attribution, we will add controlled ablation experiments that systematically inject calibrated bounding-box noise and restrict evaluation to sub-10-pixel targets, directly quantifying the gating mechanism's contribution relative to the baseline. revision: yes

Circularity Check

0 steps flagged

No circularity: empirical model with no derivations or self-referential steps

full rationale

The paper is an empirical computer-vision contribution that introduces an architecture (convolutional backbone plus lightweight gating on bounding-box features) and reports experimental results on distance regression. No equations, first-principles derivations, fitted parameters presented as predictions, or self-citation chains to uniqueness theorems appear in the abstract or description. The central claim is an architectural fusion whose benefit is evaluated experimentally rather than derived by construction from its own inputs. Therefore no load-bearing step reduces to a self-definition or renaming of known results.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

No mathematical derivations, free parameters, or invented entities are described in the abstract; the work appears entirely empirical.

pith-pipeline@v0.9.1-grok · 5702 in / 1065 out tokens · 18023 ms · 2026-06-27T22:04:58.044836+00:00 · methodology

discussion (0)

Reference graph

Works this paper leans on

23 extracted references · 1 canonical work pages

[1]

Droneranger: Vision- driven deep learning for drone distance estimation,

H. Azad, V . Mehta, I. Mantegh, and M. Bolic, “Droneranger: Vision- driven deep learning for drone distance estimation,” in2024 Interna- tional Conference on Unmanned Aircraft Systems (ICUAS), 2024

2024
[2]

The drone-vs-bird detection grand challenge at icassp 2023: A review of methods and results,

A. Coluccia, A. Fascista, L. Sommer, A. Schumann, A. Dimou, and D. Zarpalas, “The drone-vs-bird detection grand challenge at icassp 2023: A review of methods and results,”IEEE Open Journal of Signal Processing, vol. 5, pp. 766–779, 2024

2023
[3]

Air-to-air visual detection of micro-uavs: An experimental evaluation of deep learning,

Y . Zheng, Z. Chen, D. Lv, Z. Li, Z. Lan, and S. Zhao, “Air-to-air visual detection of micro-uavs: An experimental evaluation of deep learning,”IEEE Robotics and Automation Letters, vol. 6, no. 2, pp. 1020–1027, 2021

2021
[4]

Lrddv3: High- resolution long-range drone detection dataset with range information and thermal data,

K. Peterson, Z. Mayers, A. Yousuf, P. Chowdhury, A. Zaczepinski, S. Arezoomandan, R. Maarefdoust, and D. Han, “Lrddv3: High- resolution long-range drone detection dataset with range information and thermal data,” in2026 IEEE International Conference on Robotics and Automation (ICRA), 2026

2026
[5]

Reconstruction of 3d flight trajectories from ad-hoc camera networks,

J. Li, J. Murray, D. Ismaili, K. Schindler, and C. Albl, “Reconstruction of 3d flight trajectories from ad-hoc camera networks,” in2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2020, pp. 1621–1628

2020
[6]

uav detect dataset,

GET, “uav detect dataset,” https://universe.roboflow.com/get/uav- detect-pfiqs , jan 2023, visited on 2025-09-15. [Online]. Available: https://universe.roboflow.com/get/uav-detect-pfiqs

2023
[7]

A vision- based approach to uav detection and tracking in cooperative applications,

R. Opromolla, G. Fasano, and D. Accardo, “A vision- based approach to uav detection and tracking in cooperative applications,”Sensors, vol. 18, no. 10, 2018. [Online]. Available: https://www.mdpi.com/1424-8220/18/10/3391

2018
[8]

Vision-based detection and distance estimation of micro unmanned aerial vehicles,

F. G ¨okc ¸e, G. ¨Uc ¸oluk, E. S ¸ahin, and S. Kalkan, “Vision-based detection and distance estimation of micro unmanned aerial vehicles,” Sensors, vol. 15, no. 9, pp. 23 805–23 846, 2015. [Online]. Available: https://www.mdpi.com/1424-8220/15/9/23805

2015
[9]

How far can a drone be detected? a drone-to-drone detection system using sensor fusion,

J. Kim, Y . Kim, H. Shin, M. Wang, and E. Matson, “How far can a drone be detected? a drone-to-drone detection system using sensor fusion,” in15th International Conference on Agents and Artificial Intelligence (ICAART 2023), 01 2023, pp. 877–884

2023
[10]

You only look once: Unified, real-time object detection,

J. Redmon, S. K. Divvala, R. B. Girshick, and A. Farhadi, “You only look once: Unified, real-time object detection,”CoRR, vol. abs/1506.02640, 2015. [Online]. Available: http://arxiv.org/abs/1506.02640

Pith/arXiv arXiv 2015
[11]

Deformable detr: Deformable transformers for end-to-end object detection,

X. Zhu, W. Su, L. Lu, B. Li, X. Wang, and J. Dai, “Deformable detr: Deformable transformers for end-to-end object detection,”arXiv preprint arXiv:2010.04159, 2020

Pith/arXiv arXiv 2010
[12]

Slicing Aided Hyper Inference and Fine-Tuning for Small Object Detection,

F. C. Akyon, S. Onur Altinuc, and A. Temizel, “Slicing aided hyper inference and fine-tuning for small object detection,” in2022 IEEE International Conference on Image Processing (ICIP). IEEE, 2022. [Online]. Available: http://dx.doi.org/10.1109/ICIP46576.2022.9897990

work page doi:10.1109/icip46576.2022.9897990 2022
[13]

Depth anything v2,

L. Yang, B. Kang, Z. Huang, Z. Zhao, X. Xu, J. Feng, and H. Zhao, “Depth anything v2,”arXiv:2406.09414, 2024

Pith/arXiv arXiv 2024
[14]

Metric3d v2: A versatile monocular geometric foundation model for zero-shot metric depth and surface normal estimation,

M. Hu, W. Yin, C. Zhang, Z. Cai, X. Long, H. Chen, K. Wang, G. Yu, C. Shen, and S. Shen, “Metric3d v2: A versatile monocular geometric foundation model for zero-shot metric depth and surface normal estimation,”IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024

2024
[15]

Depth pro: Sharp monocular metric depth in less than a second,

A. Bochkovskii, A. Delaunoy, H. Germain, M. Santos, Y . Zhou, S. R. Richter, and V . Koltun, “Depth pro: Sharp monocular metric depth in less than a second,” inInternational Conference on Learning Representations, 2025. [Online]. Available: https://arxiv.org/abs/2410.02073

Pith/arXiv arXiv 2025
[16]

Vision-based detection and pose estimation for formation of micro aerial vehicles,

M. Zhang, F. Lin, and B. M. Chen, “Vision-based detection and pose estimation for formation of micro aerial vehicles,” in2014 13th International Conference on Control Automation Robotics & Vision (ICARCV), 2014, pp. 1473–1478

2014
[17]

Vision-based formation for uavs,

F. Lin, K. Peng, X. Dong, S. Zhao, and B. M. Chen, “Vision-based formation for uavs,” in11th IEEE International Conference on Control & Automation (ICCA), 2014, pp. 1375–1380

2014
[18]

Gated multimodal units for information fusion,

J. Arevalo, T. Solorio, M. M. y G ´omez, and F. A. Gonz ´alez, “Gated multimodal units for information fusion,” 2017. [Online]. Available: https://arxiv.org/abs/1702.01992

Pith/arXiv arXiv 2017
[19]

Feature fusion module based on gate mechanism for object detection,

Z. Sun, D. Jin, J. Deng, M. Zhang, and Z. Shao, “Feature fusion module based on gate mechanism for object detection,” inIEEE International Conference on Robotics and Biomimetics, 2023

2023
[20]

Gated-attention feature-fusion based framework for poverty prediction,

M. U. Ramzan, W. Khaddim, M. E. Rana, U. Ali, M. Ali, F. ul Hassan, and F. Mehmood, “Gated-attention feature-fusion based framework for poverty prediction,” inInnovations in Communication Networks: Sustainability for Societal and Industrial Impact, V . Bhateja, V . Ab- dul Hameed, S. K. Udgata, and A. T. Azar, Eds. Singapore: Springer Nature Singapore, 20...

2025
[21]

A dataset for multi-sensor drone detection,

F. Svanstr ¨om, F. Alonso-Fernandez, and C. Englund, “A dataset for multi-sensor drone detection,”Data in Brief, vol. 39, p. 107521, 2021. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S2352340921007976

2021
[22]

Long-range drone detection dataset,

A. Rouhi, H. Umare, S. Patal, R. Kapoor, N. Deshpande, S. Are- zoomandan, P. Shah, and D. Han, “Long-range drone detection dataset,” in2024 IEEE International Conference on Consumer Elec- tronics (ICCE), 2024

2024
[23]

Lrddv2: Enhanced long-range drone detection dataset with range information and comprehensive real-world challenges,

A. Rouhi, S. Patel, N. McCarthy, S. Khan, H. Khorsand, K. Lefkowitz, and D. Han, “Lrddv2: Enhanced long-range drone detection dataset with range information and comprehensive real-world challenges,” in 2024 International Symposium of Robotics Research (ISRR), 2024

2024

[1] [1]

Droneranger: Vision- driven deep learning for drone distance estimation,

H. Azad, V . Mehta, I. Mantegh, and M. Bolic, “Droneranger: Vision- driven deep learning for drone distance estimation,” in2024 Interna- tional Conference on Unmanned Aircraft Systems (ICUAS), 2024

2024

[2] [2]

The drone-vs-bird detection grand challenge at icassp 2023: A review of methods and results,

A. Coluccia, A. Fascista, L. Sommer, A. Schumann, A. Dimou, and D. Zarpalas, “The drone-vs-bird detection grand challenge at icassp 2023: A review of methods and results,”IEEE Open Journal of Signal Processing, vol. 5, pp. 766–779, 2024

2023

[3] [3]

Air-to-air visual detection of micro-uavs: An experimental evaluation of deep learning,

Y . Zheng, Z. Chen, D. Lv, Z. Li, Z. Lan, and S. Zhao, “Air-to-air visual detection of micro-uavs: An experimental evaluation of deep learning,”IEEE Robotics and Automation Letters, vol. 6, no. 2, pp. 1020–1027, 2021

2021

[4] [4]

Lrddv3: High- resolution long-range drone detection dataset with range information and thermal data,

K. Peterson, Z. Mayers, A. Yousuf, P. Chowdhury, A. Zaczepinski, S. Arezoomandan, R. Maarefdoust, and D. Han, “Lrddv3: High- resolution long-range drone detection dataset with range information and thermal data,” in2026 IEEE International Conference on Robotics and Automation (ICRA), 2026

2026

[5] [5]

Reconstruction of 3d flight trajectories from ad-hoc camera networks,

J. Li, J. Murray, D. Ismaili, K. Schindler, and C. Albl, “Reconstruction of 3d flight trajectories from ad-hoc camera networks,” in2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2020, pp. 1621–1628

2020

[6] [6]

uav detect dataset,

GET, “uav detect dataset,” https://universe.roboflow.com/get/uav- detect-pfiqs , jan 2023, visited on 2025-09-15. [Online]. Available: https://universe.roboflow.com/get/uav-detect-pfiqs

2023

[7] [7]

A vision- based approach to uav detection and tracking in cooperative applications,

R. Opromolla, G. Fasano, and D. Accardo, “A vision- based approach to uav detection and tracking in cooperative applications,”Sensors, vol. 18, no. 10, 2018. [Online]. Available: https://www.mdpi.com/1424-8220/18/10/3391

2018

[8] [8]

Vision-based detection and distance estimation of micro unmanned aerial vehicles,

F. G ¨okc ¸e, G. ¨Uc ¸oluk, E. S ¸ahin, and S. Kalkan, “Vision-based detection and distance estimation of micro unmanned aerial vehicles,” Sensors, vol. 15, no. 9, pp. 23 805–23 846, 2015. [Online]. Available: https://www.mdpi.com/1424-8220/15/9/23805

2015

[9] [9]

How far can a drone be detected? a drone-to-drone detection system using sensor fusion,

J. Kim, Y . Kim, H. Shin, M. Wang, and E. Matson, “How far can a drone be detected? a drone-to-drone detection system using sensor fusion,” in15th International Conference on Agents and Artificial Intelligence (ICAART 2023), 01 2023, pp. 877–884

2023

[10] [10]

You only look once: Unified, real-time object detection,

J. Redmon, S. K. Divvala, R. B. Girshick, and A. Farhadi, “You only look once: Unified, real-time object detection,”CoRR, vol. abs/1506.02640, 2015. [Online]. Available: http://arxiv.org/abs/1506.02640

Pith/arXiv arXiv 2015

[11] [11]

Deformable detr: Deformable transformers for end-to-end object detection,

X. Zhu, W. Su, L. Lu, B. Li, X. Wang, and J. Dai, “Deformable detr: Deformable transformers for end-to-end object detection,”arXiv preprint arXiv:2010.04159, 2020

Pith/arXiv arXiv 2010

[12] [12]

Slicing Aided Hyper Inference and Fine-Tuning for Small Object Detection,

F. C. Akyon, S. Onur Altinuc, and A. Temizel, “Slicing aided hyper inference and fine-tuning for small object detection,” in2022 IEEE International Conference on Image Processing (ICIP). IEEE, 2022. [Online]. Available: http://dx.doi.org/10.1109/ICIP46576.2022.9897990

work page doi:10.1109/icip46576.2022.9897990 2022

[13] [13]

Depth anything v2,

L. Yang, B. Kang, Z. Huang, Z. Zhao, X. Xu, J. Feng, and H. Zhao, “Depth anything v2,”arXiv:2406.09414, 2024

Pith/arXiv arXiv 2024

[14] [14]

Metric3d v2: A versatile monocular geometric foundation model for zero-shot metric depth and surface normal estimation,

M. Hu, W. Yin, C. Zhang, Z. Cai, X. Long, H. Chen, K. Wang, G. Yu, C. Shen, and S. Shen, “Metric3d v2: A versatile monocular geometric foundation model for zero-shot metric depth and surface normal estimation,”IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024

2024

[15] [15]

Depth pro: Sharp monocular metric depth in less than a second,

A. Bochkovskii, A. Delaunoy, H. Germain, M. Santos, Y . Zhou, S. R. Richter, and V . Koltun, “Depth pro: Sharp monocular metric depth in less than a second,” inInternational Conference on Learning Representations, 2025. [Online]. Available: https://arxiv.org/abs/2410.02073

Pith/arXiv arXiv 2025

[16] [16]

Vision-based detection and pose estimation for formation of micro aerial vehicles,

M. Zhang, F. Lin, and B. M. Chen, “Vision-based detection and pose estimation for formation of micro aerial vehicles,” in2014 13th International Conference on Control Automation Robotics & Vision (ICARCV), 2014, pp. 1473–1478

2014

[17] [17]

Vision-based formation for uavs,

F. Lin, K. Peng, X. Dong, S. Zhao, and B. M. Chen, “Vision-based formation for uavs,” in11th IEEE International Conference on Control & Automation (ICCA), 2014, pp. 1375–1380

2014

[18] [18]

Gated multimodal units for information fusion,

J. Arevalo, T. Solorio, M. M. y G ´omez, and F. A. Gonz ´alez, “Gated multimodal units for information fusion,” 2017. [Online]. Available: https://arxiv.org/abs/1702.01992

Pith/arXiv arXiv 2017

[19] [19]

Feature fusion module based on gate mechanism for object detection,

Z. Sun, D. Jin, J. Deng, M. Zhang, and Z. Shao, “Feature fusion module based on gate mechanism for object detection,” inIEEE International Conference on Robotics and Biomimetics, 2023

2023

[20] [20]

Gated-attention feature-fusion based framework for poverty prediction,

M. U. Ramzan, W. Khaddim, M. E. Rana, U. Ali, M. Ali, F. ul Hassan, and F. Mehmood, “Gated-attention feature-fusion based framework for poverty prediction,” inInnovations in Communication Networks: Sustainability for Societal and Industrial Impact, V . Bhateja, V . Ab- dul Hameed, S. K. Udgata, and A. T. Azar, Eds. Singapore: Springer Nature Singapore, 20...

2025

[21] [21]

A dataset for multi-sensor drone detection,

F. Svanstr ¨om, F. Alonso-Fernandez, and C. Englund, “A dataset for multi-sensor drone detection,”Data in Brief, vol. 39, p. 107521, 2021. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S2352340921007976

2021

[22] [22]

Long-range drone detection dataset,

A. Rouhi, H. Umare, S. Patal, R. Kapoor, N. Deshpande, S. Are- zoomandan, P. Shah, and D. Han, “Long-range drone detection dataset,” in2024 IEEE International Conference on Consumer Elec- tronics (ICCE), 2024

2024

[23] [23]

Lrddv2: Enhanced long-range drone detection dataset with range information and comprehensive real-world challenges,

A. Rouhi, S. Patel, N. McCarthy, S. Khan, H. Khorsand, K. Lefkowitz, and D. Han, “Lrddv2: Enhanced long-range drone detection dataset with range information and comprehensive real-world challenges,” in 2024 International Symposium of Robotics Research (ISRR), 2024

2024