Stereoscopic hyperspectral remote sensing of the atmospheric environment: Innovation and prospects

Cheng, Lijing; Xing, Chengzhi; Hu, Qihou; Wang, Shanshan; Zhao, Shaohua; Gao, Meng

doi:10.1016/j.earscirev.2022.103958

Cited by 40 publications

(18 citation statements)

References 139 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Alternatively, hyperspectral data may also be utilized in this context for spotting a forest fire in a larger region [14][15][16]. However, it has a low temporal and spatial resolution, thus narrowing down the surveillance area [17,18]. The most often employed method is to acquire visible or infrared images via exploration flights with planes or low-cost drones [19,20].…”

Section: Related Workmentioning

confidence: 99%

Assessing the Impact of the Loss Function and Encoder Architecture for Fire Aerial Images Segmentation Using Deeplabv3+

Harkat

Nascimento

Bernardino³

et al. 2022

Remote Sensing

View full text Add to dashboard Cite

Wildfire early detection and prevention had become a priority. Detection using Internet of Things (IoT) sensors, however, is expensive in practical situations. The majority of present wildfire detection research focuses on segmentation and detection. The developed machine learning models deploy appropriate image processing techniques to enhance the detection outputs. As a result, the time necessary for data processing is drastically reduced, as the time required rises exponentially with the size of the captured pictures. In a real-time fire emergency, it is critical to notice the fire pixels and warn the firemen as soon as possible to handle the problem more quickly. The present study addresses the challenge mentioned above by implementing an on-site detection system that detects fire pixels in real-time in the given scenario. The proposed approach is accomplished using Deeplabv3+, a deep learning architecture that is an enhanced version of an existing model. However, present work fine-tuned the Deeplabv3 model through various experimental trials that have resulted in improved performance. Two public aerial datasets, the Corsican dataset and FLAME, and one private dataset, Firefront Gestosa, were used for experimental trials in this work with different backbones. To conclude, the selected model trained with ResNet-50 and Dice loss attains a global accuracy of 98.70%, a mean accuracy of 89.54%, a mean IoU 86.38%, a weighted IoU of 97.51%, and a mean BF score of 93.86%.

show abstract

Section: Related Workmentioning

confidence: 99%

Assessing the Impact of the Loss Function and Encoder Architecture for Fire Aerial Images Segmentation Using Deeplabv3+

Harkat

Nascimento

Bernardino³

et al. 2022

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Hyperspectral imaging (HI) enables us to obtain both spatial and spectral information of a target object, offering numerous application prospects in agriculture [1][2][3][4] , remote sensing [5][6][7][8] , biomedical imaging [9][10][11][12] , environmental monitoring [13][14][15][16] , military reconnaissance [17][18][19][20] and other fields [21][22][23][24][25][26] . Traditional HI systems are based on physical spectroscopic elements, such as prisms, gratings, and filters, which need to be scanned along the spectrum or space to obtain hyperspectral images.…”

Section: Introductionmentioning

confidence: 99%

Compact hyperspectral imaging of extreme-depth-of-field diffractive lenses based on spatial–spectral sparse deep learning

Wei,

Niu,

et al. 2023

Preprint

View full text Add to dashboard Cite

Thin and flat diffractive optical elements (DOEs) are significant in the field of integrated optics and provide a novel and optimal solution for hyperspectral imaging (HI) which is expected to be compact, snapshot, with large depth of field (DoF) and resolution. The tradeoff between spectral and spatial resolutions caused by the restricted DoF, limits the application scenarios for HI. To address this, based on the prior of spatial and spectral sparse, we propose a spatial–spectral achromatic (SSA) neural network to end-to-end optimize a broad-bandwidth system with a DOE to provide the support for snapshotly achromatic extreme-DoF HI. We experimentally show that our system can snapshotly capture achromatic, high-fidelity hyperspectral images with 25 spectral channels ranging from 420 nm to 660 nm, covering distances from 0.5 m to 5 m. The proposed system enables precise and dynamic reconstruction of spectra within an extreme DoF, a capability previously unattainable with compact computational spectral cameras. The precise reconstruction of spectra demonstrates the potential of the developed system in various applications, such as precision agriculture, food quality inspection, and object detection.

show abstract

“…The acquisition methods of optical and synthetic aperture radar (SAR) images in remote sensing have been gradually diversified and improved in quality with the development of Earth observation technology. The interpretation of optical and SAR images can help relevant departments to effectively obtain valuable information, which can be beneficial for many tasks, including environmental monitoring [1,2], marine management [3,4], resource planning [5], and natural disaster damage analysis [6]. Therefore, research on optical and SAR image interpretation is of great practical importance.…”

Section: Introductionmentioning

confidence: 99%

Meta-Knowledge Guided Weakly Supervised Instance Segmentation for Optical and SAR Image Interpretation

et al. 2023

View full text Add to dashboard Cite

The interpretation of optical and synthetic aperture radar (SAR) images in remote sensing is general for many tasks, such as environmental monitoring, marine management, and resource planning. Instance segmentation of optical and SAR images, which can simultaneously provide instance-level localization and pixel-level classification of objects of interest, is a crucial and challenging task in image interpretation. Considering that most current methods for instance segmentation of optical and SAR images rely on expensive pixel-level annotation, we develop a weakly supervised instance segmentation (WSIS) method to balance the visual processing requirements with the annotation cost. First, we decompose the prior knowledge of the mask-aware task in WSIS into three meta-knowledge components: fundamental knowledge, apparent knowledge, and detailed knowledge inspired by human visual perception habits of “whole to part” and “coarse to detailed.” Then, a meta-knowledge-guided weakly supervised instance segmentation network (MGWI-Net) is proposed. In this network, the weakly supervised mask (WSM) head can instantiate both fundamental knowledge and apparent knowledge to perform mask awareness without any annotations at the pixel level. The network also includes a mask information awareness assist (MIAA) head, which can implicitly guide the network to learn detailed information about edges through the boundary-sensitive feature of the fully connected conditional random field (CRF), facilitating the instantiation of detailed knowledge. The experimental results show that the MGWI-Net can efficiently generate instance masks for optical and SAR images and achieve the approximate instance segmentation results of the fully supervised method with about one-eighth of the annotation production time. The model parameters and processing speed of our network are also competitive. This study can provide inexpensive and convenient technical support for applying and promoting instance segmentation methods for optical and SAR images.

show abstract

Stereoscopic hyperspectral remote sensing of the atmospheric environment: Innovation and prospects

Cited by 40 publications

References 139 publications

Assessing the Impact of the Loss Function and Encoder Architecture for Fire Aerial Images Segmentation Using Deeplabv3+

Assessing the Impact of the Loss Function and Encoder Architecture for Fire Aerial Images Segmentation Using Deeplabv3+

Compact hyperspectral imaging of extreme-depth-of-field diffractive lenses based on spatial–spectral sparse deep learning

Meta-Knowledge Guided Weakly Supervised Instance Segmentation for Optical and SAR Image Interpretation

Contact Info

Product

Resources

About