Improving vegetation segmentation with shadow effects based on double input networks using polarization images

Yang, Lan; Chen, Wei; Bi, Pengshuai; Tang, Hongzhao; Zhang, Fengjiao; Wang, Zhe

doi:10.1016/j.compag.2022.107123

Cited by 16 publications

(5 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, when the polarized camera (model TRIO5OS-QC) was The unique relative light-intensity distribution in the directions of 0 • , 45 • , 90 • and 135 • may be observed for each airborne disease spore, as depicted in Figures 7-9. This phenomenon occurs due to the obstruction of certain light source information by polarized pictures at varying angles due to the polarizer's influence [17][18][19]. Furthermore, the relative light-intensity distribution values of the diffraction-polarization fingerprint images for three types of airborne disease spores deviate significantly from those documented in existing literature [16].…”

Section: Results For Feature Extractionmentioning

confidence: 89%

“…One additional characteristic of light is its polarization, which possesses a distinct benefit not found in regular image and reflection spectra. It can convey some information that is challenging to characterize using intensity images and spectra [17]. Extracting the feature information of objects in different polarization directions and fusing it can improve the recognition rate of objects [18,19].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Detection Method of Fungal Spores Based on Fingerprint Characteristics of Diffraction–Polarization Images

Wang,

Zhang,

Taha

et al. 2023

JoF

View full text Add to dashboard Cite

The most significant aspect of promoting greenhouse productivity is the timely monitoring of disease spores and applying proactive control measures. This paper introduces a method to classify spores of airborne disease in greenhouse crops by using fingerprint characteristics of diffraction–polarized images and machine learning. Initially, a diffraction–polarization imaging system was established, and the diffraction fingerprint images of disease spores were taken in polarization directions of 0°, 45°, 90° and 135°. Subsequently, the diffraction–polarization images were processed, wherein the fingerprint features of the spore diffraction–polarization images were extracted. Finally, a support vector machine (SVM) classification algorithm was used to classify the disease spores. The study’s results indicate that the diffraction–polarization imaging system can capture images of disease spores. Different spores all have their own unique diffraction–polarization fingerprint characteristics. The identification rates of tomato gray mold spores, cucumber downy mold spores and cucumber powdery mildew spores were 96.02%, 94.94% and 96.57%, respectively. The average identification rate of spores was 95.85%. This study can provide a research basis for the identification and classification of disease spores.

show abstract

Section: Results For Feature Extractionmentioning

confidence: 89%

Section: Introductionmentioning

confidence: 99%

Detection Method of Fungal Spores Based on Fingerprint Characteristics of Diffraction–Polarization Images

Wang,

Zhang,

Taha

et al. 2023

JoF

View full text Add to dashboard Cite

show abstract

“…You Only Look Once version 3 (YOLOv3) [57] and the faster region-based convolutional neural network (Faster R-CNN) [58,59] focus on the rapid detection and extraction of vegetation, which has great advantages in speed and comprehensive performance. Moreover, the double input residual DeepLabv3plus network (DIR DeepLabv3plus) [60] is proposed to reduce the impact of shading on vegetation segmentation, which can effectively improve the accuracy of vegetation extraction under shadowy conditions. Due to the powerful feature extraction and feature representation ability, deep-learning-based methods are often more effective than other vegetation segmentation methods based only on pixels or vegetation categories.…”

Section: Land Cover Segmentation Of Remote Sensing Imagesmentioning

confidence: 99%

SERNet: Squeeze and Excitation Residual Network for Semantic Segmentation of High-Resolution Remote Sensing Images

Zhang

et al. 2022

Remote Sensing

View full text Add to dashboard Cite

The semantic segmentation of high-resolution remote sensing images (HRRSIs) is a basic task for remote sensing image processing and has a wide range of applications. However, the abundant texture information and wide imaging range of HRRSIs lead to the complex distribution of ground objects and unclear boundaries, which bring huge challenges to the segmentation of HRRSIs. To solve this problem, in this paper we propose an improved squeeze and excitation residual network (SERNet), which integrates several squeeze and excitation residual modules (SERMs) and a refine attention module (RAM). The SERM can recalibrate feature responses adaptively by modeling the long-range dependencies in the channel and spatial dimensions, which enables effective information to be transmitted between the shallow and deep layers. The RAM pays attention to global features that are beneficial to segmentation results. Furthermore, the ISPRS datasets were processed to focus on the segmentation of vegetation categories and introduce Digital Surface Model (DSM) images to learn and integrate features to improve the segmentation accuracy of surface vegetation, which has certain prospects in the field of forestry applications. We conduct a set of comparative experiments on ISPRS Vaihingen and Potsdam datasets. The results verify the superior performance of the proposed SERNet.

show abstract

“…In the field of remote sensing, Andrade et al [4] employs radar time series for semantic segmentation studies related to mangrove detection. In agriculture, Yang et al [5] introduces a two-input residual network based on a fusion strategy involving cascade and addition. This effectively enhances vegetation segmentation accuracy by extracting features at various spatial scales from RGB and DOLP images through a deep residual network and ASPP structure.…”

Section: Introductionmentioning

confidence: 99%

Material semantic segmentation algorithm based on polarization information

Chen,

Wan

2024

Third International Conference on Electronic Information Engineering, Big Data, and Computer Technology (EIBDCT 2024)

View full text Add to dashboard Cite

Due to the variety of materials' forms and shapes as well as the dearth of material annotation data, the work of semantic segmentation presents considerable difficulties with material segmentation. Additionally, traditional RGB images are insufficient for obtaining adequate segmentation results. A polarization-driven material semantic segmentation method combined with a self-attention mechanism is proposed as a solution to these problems. The backborn network ResNet50, the decoding head DeepLabV3+, and the auxiliary decoding head FCN make up a unique network architecture. For the decoder and encoder in the decoding, and auxiliary decoding head, the polarization self-attention modules are introduced in order to preserve high-quality internal resolution in both the spatial and channel dimensions. Rich texture and edge information are provided by the polarization information, which is used as auxiliary information. Furthermore, there is a problem with the class imbalance in the application dataset. On the MCubeS dataset, comparative and ablation experiments are carried out. The outcomes show that the suggested method outperforms baseline methods by 7.92 percentage points. Furthermore, the proposed strategy improves by 1.15 percentage points in comparison to the network without a polarization self-attention mechanism.

show abstract

Improving vegetation segmentation with shadow effects based on double input networks using polarization images

Cited by 16 publications

References 32 publications

Detection Method of Fungal Spores Based on Fingerprint Characteristics of Diffraction–Polarization Images

Detection Method of Fungal Spores Based on Fingerprint Characteristics of Diffraction–Polarization Images

SERNet: Squeeze and Excitation Residual Network for Semantic Segmentation of High-Resolution Remote Sensing Images

Material semantic segmentation algorithm based on polarization information

Contact Info

Product

Resources

About