UAV route planning for active disease classification

Vivaldini, Kelen Cristiane Teixeira; Martinelli, Thiago H.; Guizilini, Vitor; Souza, Jefferson R.; Oliveira, Matheus Della Croce; Ramos, Fábio; Wolf, Denis F.

doi:10.1007/s10514-018-9790-x

Cited by 29 publications

(14 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…With it, the UAVs can carry out the trajectory in less time without stop. The environments tested are unstructured, similar to forests [3] and hilly areas [6], where can be made missions of monitoring or rescue.…”

Section: Simulationmentioning

confidence: 99%

See 1 more Smart Citation

Comparison between Meta-Heuristic Algorithms for Path Planning

Rocha

Vivaldini

2020

Anais Estendidos Do XII Simpósio Brasileiro De Robótica E XVII Simpósio Latino Americano De Robótica (SBR/LARS Estendido 2020)

View full text Add to dashboard Cite

Unmanned Aerial Vehicle (UAV) has been increasingly employed in several missions with a pre-defined path. Over the years, UAV has become necessary in complex environments, where it demands high computational cost and execution time for traditional algorithms. To solve this problem meta-heuristic algorithms are used. Meta-heuristics are generic algorithms to solve problems without having to describe each step until the result and search for the best possible answer in an acceptable computational time. The simulations are made in Python, with it, a statistical analyses was realized based on execution time and path length between algorithms Particle Swarm Optimization (PSO), Grey Wolf Optimization (GWO) and Glowworm Swarm Optimization (GSO). Despite the GWO returns the paths in a shorter time, the PSO showed better performance with similar execution time and shorter path length. However, the reliability of the algorithms will depend on the size of the environment. PSO is less reliable in large environments, while the GWO maintains the same reliability.

show abstract

Section: Simulationmentioning

confidence: 99%

“…UAVs are being adopted as an important choice for application in several areas, surveillance [1], construction [2], environment monitoring [3], and others. Initially, the paths were defined by the pilots and the UAVs followed the points [4] .…”

Section: Introductionmentioning

confidence: 99%

Comparison between Meta-Heuristic Algorithms for Path Planning

Rocha

Vivaldini

2020

Anais Estendidos Do XII Simpósio Brasileiro De Robótica E XVII Simpósio Latino Americano De Robótica (SBR/LARS Estendido 2020)

View full text Add to dashboard Cite

show abstract

“…Now the fitness function is computed by calculating Euclidean distance between the pixels and their respective cluster by using the following Eqns. (17) and (18).…”

Section: Image Processing and Disease Detectionmentioning

confidence: 99%

“…For specific disease detection, the SVM classifier is used to compare the extracted properties of the image by cooccurrence method with a stored data set values. SVM classifier uses minimum distance criterion for disease classification [2,17]. Classification success is calculated by equation (23…”

Section: Image Processing and Disease Detectionmentioning

confidence: 99%

Diseased Area Recognition and Pesticide Spraying in Farming Lands by Multicopters and Image Processing System

Pittu¹,

Gorantla²

2020

JESA

View full text Add to dashboard Cite

United Nations indexes that the world's population will increase drastically, it may increase by 20% and it will be around 970 crores by 2050. However this scenario requires 20% more food to serve this much population, but farming land is decreasing due to pollution, industrialization, and globalization. Cultivation these days is more difficult and increasing the labor cost and pesticides. Enough labor is not available, so labor charges are also increasing which reflects in expenditure for cultivation. In regular spraying system pesticides are sprayed in the whole field. This will increase pesticide costs and pollution. In this proposed system image acquiring Multicopter will move in a pre-defined path in the field is given in a Mission planner firmware. UAV while moving along the pre-defined path captures high-quality RGB pictures in the field and those captured images are tagged with a Global Positioning System (GPS). These pictures are processed by the image processing system using MATLAB software at the ground station and actual disease recognition from the database frame is done. Disease recognition is done along with the tag of the specific diseased area in the field. These tags can help the crew to identify the diseased area spot. This diseased area or plant GPS tag information is used for the creation of a path for pesticide spraying Multicopters and will spray the pesticide in a diseased area or a plant in the field. This will lead to the optimal usage of pesticides.

show abstract

“…Many publications exist that examine route planning for UAVs in various applications. Vivaldini et al [12] propose a framework for efficient visual data acquisition using UAVs; this combines perception, environment representation, and route planning in the task of disease classification. Liu et al [13] present a UAV route planning problem for aerial photography under interval uncertainties.…”

Section: Literature Reviewmentioning

confidence: 99%

Trajectory Optimization in a Cooperative Aerial Reconnaissance Model

Stodola

Drozd

Nohel

et al. 2019

Sensors

View full text Add to dashboard Cite

In recent years, the use of modern technology in military operations has become standard practice. Unmanned systems play an important role in operations such as reconnaissance and surveillance. This article examines a model for planning aerial reconnaissance using a fleet of mutually cooperating unmanned aerial vehicles to increase the effectiveness of the task. The model deploys a number of waypoints such that, when every waypoint is visited by any vehicle in the fleet, the area of interest is fully explored. The deployment of waypoints must meet the conditions arising from the technical parameters of the sensory systems used and tactical requirements of the task at hand. This paper proposes an improvement of the model by optimizing the number and position of waypoints deployed in the area of interest, the effect of which is to improve the trajectories of individual unmanned systems, and thus increase the efficiency of the operation. To achieve this optimization, a modified simulated annealing algorithm is proposed. The improvement of the model is verified by several experiments. Two sets of benchmark problems were designed: (a) benchmark problems for verifying the proposed algorithm for optimizing waypoints, and (b) benchmark problems based on typical reconnaissance scenarios in the real environment to prove the increased effectiveness of the reconnaissance operation. Moreover, an experiment in the SteelBeast simulation system was also conducted.

show abstract

UAV route planning for active disease classification

Cited by 29 publications

References 37 publications

Comparison between Meta-Heuristic Algorithms for Path Planning

Comparison between Meta-Heuristic Algorithms for Path Planning

Diseased Area Recognition and Pesticide Spraying in Farming Lands by Multicopters and Image Processing System

Trajectory Optimization in a Cooperative Aerial Reconnaissance Model

Contact Info

Product

Resources

About