Unmanned Aerial vehicle’s runway landing system with efficient target detection by using morphological fusion for military surveillance system

Nagarani, N.; Venkatakrishnan, P.; Balaji, N.

doi:10.1016/j.comcom.2019.12.039

Cited by 23 publications

(16 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Des travaux définissent des métriques pour la mesure des performances des télépilotes [94] ou évaluent la charge mentale de travail pour les contrôleurs gérant du trafic impliquant des drones [12]. L'amélioration des aides au pilotage et à la préparation de missions est aussi étudiée pour mieux identifier les pistes d'atterrissage par mauvaise visibilité [83], changer le point de vue du pilote pour faciliter les opérations dans les environnements complexes en 3D [106], utiliser plusieurs drones lors de mission de sauvetage [2], planifier des trajectoires en réalité virtuelle [85] ou communiquer, vérifier et valider les objectifs de mission de drones autonomes [95]. Les interfaces adaptatives pour le pilotage sont l'objet des travaux de [19,64,71,72].…”

Section: Approches Principales (Rq2 -Rq3)unclassified

“…Par exemple, la surimpression pour montrer la géométrie d'un conflit possible [67], voir la mission en 3D et ses différentes zones [15] ou repérer la piste d'atterrissage par mauvais temps [83]. Paterson et al [85] proposent d'utiliser une vue immersive, en réalité virtuelle, qui améliore la perception de la profondeur et permet de régler le point de vue offert afin de déterminer plus rapidement un chemin adapté pour le drone.…”

Section: Recommandations Pour La Conceptionunclassified

“…Nous pensons que cette séparation est préjudiciable à la sécurité car cela ne permet pas une transition fluide entre les différentes étapes et fait courir un risque de manque d'information contextuelle sur la géographie du lieu envisagé pour la mission. Étendre l'usage de la réalité augmentée et réalité virtuelle La réalité augmentée ou virtuelle est étudiée par cinq articles[15,67,83,85,106]. Les informations supplémentaires augmentent la conscience de la situation des télépilotes et peuvent constituer une aide effective au pilotage.…”

unclassified

See 2 more Smart Citations

Revue Systématique de la Littérature sur le Soutien à la Sécurité des Opérations de Drones

Rakotonarivo

Conversy

Drougard

et al. 2021

32e Conférence Francophone Sur l'Interaction Homme-Machine

View full text Add to dashboard Cite

Dans cet article, nous nous intéressons au soutien à la sécurité des opérations de drones. Il s'agit d'un enjeu primordial pour les exploitants qui doivent se conformer au cadre légal. Nous présentons tout d'abord les systèmes de drones et la réglementation européenne. Ensuite nous décrivons une revue systématique de la littérature sur cette thématique. L'identification des approches principales en résulte : "Voir & Éviter", Interactions Humain-Machine et Facteurs Humains (IHM/FH), intégrité de l'aéronef, analyses de sécurité, planification de trajectoires, géorepérage, cyber-sécurité et gestion du trafic de drones. Nous analysons plus en détail les contributions liées à l'IHM en identifiant les tâches utilisateurs, les recommandations pour la conception d'interactions améliorant la sécurité des opérations de drones et les perspectives de recherche. Enfin, nous discutons des aspects peu couverts dans les articles examinés.

show abstract

Section: Approches Principales (Rq2 -Rq3)unclassified

Section: Recommandations Pour La Conceptionunclassified

unclassified

See 1 more Smart Citation

Revue Systématique de la Littérature sur le Soutien à la Sécurité des Opérations de Drones

Rakotonarivo

Conversy

Drougard

et al. 2021

32e Conférence Francophone Sur l'Interaction Homme-Machine

View full text Add to dashboard Cite

show abstract

“…VTOL UAVs have the capability of vertical taking-off and landing, but the shortcomings of a short range and slow speed limit the application in surface reconnaissance and combat [ 4 ]. Although fixed-wing UAVs have advantages in terms of payload and endurance, they still face the following challenges to achieve autonomous landing [ 5 ]: Since the mass of fixed-wing UAVs is generally much larger than that of VTOL UAVs, traditional recovery approaches such as net recovery and parachute recovery are not applicable, so the landing of fixed-wing UAVs requires the help of a runway; The landing speed of fixed-wing UAVs is so high that there is little room for correction in the event of mistakes, so the fault tolerance of the landing of fixed-wing UAVs is much lower than that of manned aircraft; Fixed-wing UAVs usually land on the deck by means of impact. Such a landing method not only has higher requirements on the strength of the airframe and landing gear, but also puts forward more reliable and accurate requirements for the landing guidance system, which plays a key role in safety.…”

Section: Introductionmentioning

confidence: 99%

Monocular-Vision-Based Precise Runway Detection Applied to State Estimation for Carrier-Based UAV Landing

Weng

Cao

et al. 2022

Sensors

View full text Add to dashboard Cite

Improving the level of autonomy during the landing phase helps promote the full-envelope autonomous flight capability of unmanned aerial vehicles (UAVs). Aiming at the identification of potential landing sites, an end-to-end state estimation method for the autonomous landing of carrier-based UAVs based on monocular vision is proposed in this paper, which allows them to discover landing sites in flight by using equipped optical sensors and avoid a crash or damage during normal and emergency landings. This scheme aims to solve two problems: the requirement of accuracy for runway detection and the requirement of precision for UAV state estimation. First, we design a robust runway detection framework on the basis of YOLOv5 (you only look once, ver. 5) with four modules: a data augmentation layer, a feature extraction layer, a feature aggregation layer and a target prediction layer. Then, the corner prediction method based on geometric features is introduced into the prediction model of the detection framework, which enables the landing field prediction to more precisely fit the runway appearance. In simulation experiments, we developed datasets applied to carrier-based UAV landing simulations based on monocular vision. In addition, our method was implemented with help of the PyTorch deep learning tool, which supports the dynamic and efficient construction of a detection network. Results showed that the proposed method achieved a higher precision and better performance on state estimation during carrier-based UAV landings.

show abstract

“…In the past decades, multi-sensor information fusion technology has received great attention and has been widely used in various fields, including military [ 1 , 2 ], medical [ 3 , 4 ], and financial [ 5 ] fields and so on [ 6 , 7 ]. In order to efficiently integrate information from different sources, it is crucial to choose an appropriate strategy.…”

Section: Introductionmentioning

confidence: 99%

A Novel Method to Determine Basic Probability Assignment Based on Adaboost and Its Application in Classification

Wang

2021

Entropy

View full text Add to dashboard Cite

In the framework of evidence theory, one of the open and crucial issues is how to determine the basic probability assignment (BPA), which is directly related to whether the decision result is correct. This paper proposes a novel method for obtaining BPA based on Adaboost. The method uses training data to generate multiple strong classifiers for each attribute model, which is used to determine the BPA of the singleton proposition since the weights of classification provide necessary information for fundamental hypotheses. The BPA of the composite proposition is quantified by calculating the area ratio of the singleton proposition’s intersection region. The recursive formula of the area ratio of the intersection region is proposed, which is very useful for computer calculation. Finally, BPAs are combined by Dempster’s rule of combination. Using the proposed method to classify the Iris dataset, the experiment concludes that the total recognition rate is 96.53% and the classification accuracy is 90% when the training percentage is 10%. For the other datasets, the experiment results also show that the proposed method is reasonable and effective, and the proposed method performs well in the case of insufficient samples.

show abstract

Unmanned Aerial vehicle’s runway landing system with efficient target detection by using morphological fusion for military surveillance system

Cited by 23 publications

References 12 publications

Revue Systématique de la Littérature sur le Soutien à la Sécurité des Opérations de Drones

Revue Systématique de la Littérature sur le Soutien à la Sécurité des Opérations de Drones

Monocular-Vision-Based Precise Runway Detection Applied to State Estimation for Carrier-Based UAV Landing

A Novel Method to Determine Basic Probability Assignment Based on Adaboost and Its Application in Classification

Contact Info

Product

Resources

About