A method for UAV monitoring road conditions in dangerous environment

Wang, Xi; Ouyang, Cheng; Shao, Xiangling; Xu, Hui

doi:10.1088/1742-6596/1792/1/012050

Cited by 4 publications

(3 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, in [4,5,18], the authors propose to bypass dangerous areas in order to minimize the probability of loss of UAVs. Part of the work [8] is devoted to compare UAV control methods in dangerous area in order to increase the probability of successful flight. There is a…”

Section: Discussion and Comparisonmentioning

confidence: 99%

“…Crossing of dangerous area is very important when there is a need to deliver medical supplies, food and communication devices into the disaster area. In [8], a path-planning algorithm is proposed based on a threat probability map, which is built upon a priori observational data. This study analyzes the case when communication with the operator is lost, and the UAV has to map out a flight plan to perform the area survey by itself.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

New algorithm for calculating the required number of unmanned aerial vehicles and the duration of their stay in dangerous area

et al. 2022

View full text Add to dashboard Cite

This paper proposes a new approach to calculate the time spent by unmanned aerial vehicle (UAV) in dangerous area with the consideration of the maximum allowed probability of losing UAV and the increasing rate of this probability in a given area. Unlike the known approaches, which are based on flying around the dangerous areas, it is proposed to cross the boundaries of the dangerous area for a defined time, which is calculated to allow the obtaining of the required data set about the interested area. Based on the UAV loss probabilities estimates, an approach to planning the number of UAVs in a group flight is substantiated, taking into account losing them. The formula for calculating the required number of UAVs, obtained by this approach, consists of three terms, which consider the requirements for pre-flight task accomplishment, high-quality in-flight service of new requests, as well as the necessary reserve in case of the decrease of UAV performance. To evaluate the quality of the proposed algorithm, various case with different initial conditions in determining the time of stay in dangerous zone are considered. The specified time minimizes the given indicator. In addition, the paper presents practical example where the algorithm is used to observe a territory by a group of UAVs. It is shown that the algorithm can determine the required number of UAVs to study an area with a given dimension, and it also can calculate the time of stay of each UAV in the dangerous area in order to reduce the loss probability of UAVs.

show abstract

Section: Discussion and Comparisonmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

New algorithm for calculating the required number of unmanned aerial vehicles and the duration of their stay in dangerous area

et al. 2022

View full text Add to dashboard Cite

show abstract

“…With the lightweight and dexterous design, unmanned aerial vehicles (UAVs) are widely applied to civil and military fields [1,2]. Meanwhile, convolutional neural network-based target detection technology has also made remarkable progress in recent years [3], which allows the UAV technology to be more closely integrated with target detection technology.…”

Section: Introductionmentioning

confidence: 99%

Lightweight-YOLOv5s for the camouflaged personnel detection in the woodland

Wang

Liu

et al. 2023

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

Unmanned aerial vehicles(UAVs) technology and target detection technology are increasingly integrated. However, the target detection networks are cumbersome and complex, and it is hard to directly deploy these networks on the UAVs. To address this problem, a Lightweight-YOLOv5s which can be applied to the UAVs is proposed to detect the camouflaged personnel in the woodland. Depthwise separable convolutions are added to the YOLOv5s for reducing the parameters and computational effort. Then a new channel pruning method based on Batch Normalization(BN) layer scaling factor with adaptive sparsity training is proposed for network compression, which can balance the compression ratio and accuracy of the detection. The pruned network is then fine-tuned to detect the camouflaged personnel. In addition, a special dataset is built for the camouflaged personnel detection in the woodland. The quantitative results on this dataset prove that the proposed Lightweight-YOLOv5s greatly improve the YOLOv5s. Parameters from 7.06M to 1.86M, floating point operations from 16.4G to 9.9G and inference time from 8.16ms to 7.06ms. Besides, mAP of the Lightweight-YOLOv5s is 0.83, which shows the excellent detection performance of the proposed method.

show abstract

Development of Unmanned Aerial Vehicle (UAV) Fixed-Wing for Monitoring, Mapping and Dropping applications on agricultural land

Hakim

Pratiwi

Nugraha

et al. 2021

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

UAV technology is used in various fields, namely the military, to strengthen defence, surveillance, dropping logistics. In addition, UAV applications are also used in agriculture. In this study, a fixed-wing UAV will be developed as a monitoring, mapping and dropping process. Several things were carried out in the development process, namely design, manufacturing, installing electronic components, and test flights. The results showed that the vehicle could carry out the mission well. The monitoring process is carried out to review land security. Besides that, it can monitor if there is a fire in agricultural land. In the mapping process, photo data processing taken in the context of the mapping is carried out into an orthophoto map. Meanwhile, in the dropping stage, the aircraft managed to drop a payload weighing 0.5 kg with a distance of 20m from a predetermined centre point. The dropped payload is also equipped with a parachute for increased safety and reduced speed when the payload is dropped.

show abstract

A method for UAV monitoring road conditions in dangerous environment

Cited by 4 publications

References 3 publications

New algorithm for calculating the required number of unmanned aerial vehicles and the duration of their stay in dangerous area

New algorithm for calculating the required number of unmanned aerial vehicles and the duration of their stay in dangerous area

Lightweight-YOLOv5s for the camouflaged personnel detection in the woodland

Development of Unmanned Aerial Vehicle (UAV) Fixed-Wing for Monitoring, Mapping and Dropping applications on agricultural land

Contact Info

Product

Resources

About