Automatic Detection of Civilian and Military Personnel in Reconnaissance Missions using a UAV

Santos, Nuno Pessanha; Rodrigues, Vítor Manuel Costa Pereira; Pinto, André F.; Damas, Bruno

doi:10.1109/icarsc58346.2023.10129575

Cited by 8 publications

(3 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To guide the learning of robustness scores based on their influences on making predictions for each sub-model, an additional MLP layer is attached after the separation stage and input into γ + and γ − . Specifically, we formulate the guidance process with a loss function L 1 as (9).…”

Section: Sub-model Robustness Enhancementmentioning

confidence: 99%

“…State-of-the-art performances of various tasks in the field of remote sensing have been achieved by advanced DNN models. Concurrently, an increasing number of modern unmanned aerial vehicles (UAVs) with DNN-based visual navigation and recognition systems are able now to support on-device inference for real-time RSIs and quickly provide useful analysis of the images for both military (e.g., target recognition [5][6][7], battlefield surveillance [8][9][10], communication [11]) and civilian (e.g., land planning [12], medical rescue [13], parcel delivery [14]) use.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Adversarial Robust Aerial Image Recognition Based on Reactive-Proactive Defense Framework with Deep Ensembles

Lu,

Sun,

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

As a safety-related application, visual systems based on deep neural networks (DNNs) in modern unmanned aerial vehicles (UAVs) show adversarial vulnerability when performing real-time inference. Recently, deep ensembles with various defensive strategies against adversarial samples have drawn much attention due to the increased diversity and reduced variance for their members. Aimed at the recognition task of remote sensing images (RSIs), this paper proposes to use a reactive-proactive ensemble defense framework to solve the security problem. In reactive defense, we fuse scoring functions of several classical detection algorithms with the hidden features and average output confidences from sub-models as a second fusion. In terms of proactive defense, we attempt two strategies, including enhancing the robustness of each sub-model and limiting the transferability among sub-models. In practical applications, the real-time RSIs are first input to the reactive defense part, which can detect and reject the adversarial RSIs. The accepted ones are then passed to robust recognition with a proactive defense. We conduct extensive experiments on three benchmark RSI datasets (i.e., UCM, AID, and FGSC-23). The experimental results show that the deep ensemble method of reactive and proactive defense performs very well in gradient-based attacks. The analysis of the applicable attack scenarios for each proactive ensemble defense is also helpful for this field. We also perform a case study with the whole framework in the black-box scenario, and the highest detection rate reaches 93.25%. Most of the adversarial RSIs can be rejected in advance or correctly recognized by the enhanced deep ensemble. This article is the first one to combine reactive and proactive defenses with a deep ensemble against adversarial attacks in the context of RSI recognition for DNN-based UAVs.

show abstract

Section: Sub-model Robustness Enhancementmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Adversarial Robust Aerial Image Recognition Based on Reactive-Proactive Defense Framework with Deep Ensembles

Lu,

Sun,

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…It is obvious that advanced vision systems and flights at a hundred meters above the ground significantly increase the range of visual observation. This can be proven by drone usage in modern wars, where identifying enemy positions is crucial in a successful strike [2]. Drones and their vision systems are excellent tools for monitoring national borders [3] or forests to protect against fires [4].…”

Section: Introductionmentioning

confidence: 99%

Development and Evaluation of a Tethered Class C3 Hexacopter in Maritime Conditions on the Helipad of a Ferry

Kownacki,

Ambroziak,

Ciężkowski

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

Various unmanned aerial vechicle (UAV) applications, especially those based on reconnaissance and observation missions, often require an unlimited time of flight. This is possible only when a UAV is continuously supplied with power from a ground-based power source, which is why tethered UAV systems were developed. Tethered UAV systems are based on multicopters, which can hover above a landing pad or track its position if it is movable. The presented research concerned the development of a large C3 class hexacopter with a maximal payload of about 1 kg and a takeoff mass of 16 kg, which was tested in maritime conditions during a ferry’s cruise. The main purpose of the hexacopter was to continuously observe the area ahead of the vessel to detect and localize obstacles in the water. During the experimental tests, critical phases of flight were identified, the AC/DC power supply unit and power cord unwinder were tested, and the power required by six brushless direct current (BLDC) motors was registered. The obtained results could be useful in future work on tethered UAV systems applied in windy maritime conditions.

show abstract

Prescribed-time unknown input observer-based UAV attitude tracking control with uncertainties

Wang,

Shao,

Zhao

2024

2024 36th Chinese Control and Decision Conference (CCDC)

View full text Add to dashboard Cite

Automatic Detection of Civilian and Military Personnel in Reconnaissance Missions using a UAV

Cited by 8 publications

References 21 publications

Adversarial Robust Aerial Image Recognition Based on Reactive-Proactive Defense Framework with Deep Ensembles

Adversarial Robust Aerial Image Recognition Based on Reactive-Proactive Defense Framework with Deep Ensembles

Development and Evaluation of a Tethered Class C3 Hexacopter in Maritime Conditions on the Helipad of a Ferry

Prescribed-time unknown input observer-based UAV attitude tracking control with uncertainties

Contact Info

Product

Resources

About