Volunteered remote sensing data generation with air passengers as sensors

Wang, Chisheng; Wang, Yongquan; Wang, Leyang; Hu, Zhongwen; Zhang, Shaobiao; Wang, Shuanglong; Xiu, Wenqun; Cui, Hongxing; Wang, Dan; Li, Qingquan

doi:10.1080/17538947.2020.1808721

Cited by 7 publications

(5 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nevertheless, the average number of daily flights for the whole year was still about 10,000. According to the study by Wang et al (2020), assuming an average speed of 900 km/h and a strip width of 34 km, with 8,000 aircraft flying over our heads every moment, the area covered per day is 5.8750 x 10 9 km 2 , which is close to the size of the Earth's surface [26]. In fact, there are many areas that cannot be covered by flights, which can be complemented by satellite imagery, and to a certain extent, the two observation methods can complement each other very well.…”

Section: Discussionmentioning

confidence: 93%

“…Second, a low incident is required to ensure that more ground details are captured in one picture, as well as to improve dense point matching. Side-look imaging geometry can be obtained when pictures are taken by passengers from both sides of the plane; however, the varying scales of the images are a defect in the oblique images [26,37]. To obtain high-quality images, the incidence angle should be controlled within a small range.…”

Section: A Passenger Aircraft Data Acquisitionmentioning

confidence: 99%

“…It is worth noting that by setting the interpolation value to the initial value of the camera position, the positioning error of the ground control points (GCPs) would be reduced in a further step. Our previous research has shown that the measurement accuracy of the GPS was roughly set to be about 10 times greater than that of the ground control points (GCPs), with a general ground sampling resolution of less than 6m [26].…”

Section: ) Camera Position Initializationmentioning

confidence: 99%

“…The inherent limitations are difficult to overcome by any cloud removal algorithms as they all require certain assumptions on the missing information. Recently, using passenger aircraft as the remote sensing platform has been proposed due to the large coverage area, short visitation frequency, and low cost [25][26][27]. Another merit from passenger aircraft is that it can overcome cloud interference due to their flight altitude and multi-viewing angles comparing with satellite.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Framework to Create Cloud-Free Remote Sensing Data Using Passenger Aircraft as the Platform

Wang

Cui

et al. 2021

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

Self Cite

View full text Add to dashboard Cite

Cloud removal in optical remote sensing imagery is essential for many Earth observation applications. To recover the cloud obscured information, some preconditions must be satisfied. For example, the cloud must be semi-transparent or relationships between contaminated and cloud-free pixels must be assumed. Due to the inherent imaging geometry features in satellite remote sensing, it is impossible to observe the ground under the clouds directly; therefore, cloud removal algorithms are always not perfect owing to the loss of ground truth. Recently, the use of passenger aircraft as a platform for remote sensing has been proposed by some researchers and institutes, including Airbus and the Japan Aerospace Exploration Agency. Passenger aircraft have the advantages of short visitation frequency and low cost. Additionally, because passenger aircraft fly at lower altitudes compared to satellites, they can observe the ground under the clouds at an oblique viewing angle. In this study, we examine the possibility of creating cloud-free remote sensing data by stacking multi-angle images captured by passenger aircraft. To accomplish this, a processing framework is proposed, which includes four main steps: 1) multi-angle image acquisition from passenger aircraft, 2) cloud detection based on deep learning semantic segmentation models, 3) cloud removal by image stacking, and 4) image quality enhancement via haze removal. This method is intended to remove cloud contamination without the requirements of reference images and pre-determination of cloud types. The proposed method was tested in multiple case studies, wherein the resultant cloud-and haze-free orthophotos were visualized and quantitatively analyzed in various land cover type scenes. The results of the case studies demonstrated that the proposed method could generate high quality, cloud-free orthophotos. Therefore, we conclude that this framework has great potential for creating cloud-free remote sensing images when the cloud removal of satellite imagery is difficult or inaccurate.

show abstract

Section: Discussionmentioning

confidence: 93%

Section: A Passenger Aircraft Data Acquisitionmentioning

confidence: 99%

Section: ) Camera Position Initializationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Framework to Create Cloud-Free Remote Sensing Data Using Passenger Aircraft as the Platform

Wang

Cui

et al. 2021

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

Self Cite

View full text Add to dashboard Cite

show abstract

“…A sufficient amount of data is the cornerstone for achieving high-performance deep learning algorithms, and large high-quality datasets can greatly improve the algorithm performance [5]. However, there are two constraints in the construction of existing remote sensing image datasets: on the one hand, compared with natural image datasets captured by groundbased equipment [6,7], the capture of remote sensing images requires high-cost imaging platforms such as aircraft or satellites, and the acquisition process is limited by aircraft routes and satellite orbits; on the other hand, the influence of factors such as light, rain, fog, and clouds [8] makes it difficult to collect effective high-quality images due to the high proportion of invalid data in each acquisition [9]. The above factors mean that existing datasets cannot meet the demand of artificial intelligence algorithm training in the field of remote sensing [10], which is mainly reflected in two aspects:…”

Section: Introductionmentioning

confidence: 99%

Gradient Structure Information-Guided Attention Generative Adversarial Networks for Remote Sensing Image Generation

Zhu

Yang

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

A rich and effective dataset is an important foundation for the development of AI algorithms, and the quantity and quality of the dataset determine the upper limit level of the algorithms. For aerospace remote sensing datasets, due to the high cost of data collection and susceptibility to meteorological and airway conditions, the existing datasets have two problems: firstly, the number of datasets is obviously insufficient, and, secondly, there is large unevenness between different categories in datasets. One of the effective solutions is to use neural networks to generate fake data by learning from real data, but existing methods still find difficulty in generating remote sensing sample images with good texture detail and geometric distortion. To address the shortcomings of existing image generation algorithms, this paper proposes a gradient structure information-guided attention generative adversarial network (SGA-GAN) for remote sensing image generation, which contains two innovative initiatives: on the one hand, a learnable gradient structure information extraction branch network can be added to the generator network to obtain complex structural information in the sample image, thus alleviating the distortion of the sample geometric structure in remote sensing image generation; on the other hand, a multidimensional self-attention feature selection module is proposed to further improve the quality of the generated remote sensing images by connecting cross-attentive modules as well as spatial and channel attention modules in series to guide the generator to better utilize global information. The algorithm proposed in this paper outperformed other methods, such as StyleGAN-XL and FastGAN, in both the qualitative and quantitative evaluation, whereby the FID on the DOTA dataset decreased by 23.927 and the IS was improved by 2.351. The comparison experiments show that the method proposed in this paper can generate more realistic sample images, and images generated by this method can improve object detection metrics by increasing the number of single-category datasets and the number of targets in fewer categories in multi-category datasets, which means it can be effectively used in the field of intelligent processing of remote sensing images.

show abstract

Recent advancements in low-cost portable sensors for urban and indoor air quality monitoring

Hernández-Gordillo

Ruíz-Correa

Robledo-Valero

et al. 2021

Air Qual Atmos Health

View full text Add to dashboard Cite

Volunteered remote sensing data generation with air passengers as sensors

Cited by 7 publications

References 41 publications

Framework to Create Cloud-Free Remote Sensing Data Using Passenger Aircraft as the Platform

Framework to Create Cloud-Free Remote Sensing Data Using Passenger Aircraft as the Platform

Gradient Structure Information-Guided Attention Generative Adversarial Networks for Remote Sensing Image Generation

Recent advancements in low-cost portable sensors for urban and indoor air quality monitoring

Contact Info

Product

Resources

About