Multi-task fully convolutional network for tree species mapping in dense forests using small training hyperspectral data

Rosa, Laura Elena Cué La; Sothe, Camile; Feitosa, Raul Queiroz; Almeida, Cláudia Maria de; Schimalski, Marcos Benedito; Oliveira, Dário Augusto Borges

doi:10.1016/j.isprsjprs.2021.07.001

Cited by 38 publications

(27 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the case of a small sample size (e.g., only several training samples), using hyperspectral data or multiple combined data may be the preferred input image type because it can provide more features for model training. For example, La Rose et al reported that 23 individual tree crowns (maximum two individual tree crowns per species) could perform with reasonable accuracy for 14 tree species detections using the hyperspectral data with 25 spectral bands (OA: 72.55%) [24]. However, although the model training benefits from the increase in the image dimension, it increases the computational load and may cause a high correlation between bands.…”

Section: Input Imagementioning

confidence: 99%

“…However, although the model training benefits from the increase in the image dimension, it increases the computational load and may cause a high correlation between bands. Therefore, it may be necessary to design a special network, such as a 3D network [47], a partial loss function to train an FCN [24] to deal with this problem, which may outweigh the convenience mentioned above.…”

Section: Input Imagementioning

confidence: 99%

“…The object detection results are presented in the form of the rectangular bounding boxes but cannot explicitly define vegetation boundaries. Compared to object detection, semantic segmentation is capable of segmenting and classifying the target object in remote sensing data, such as fully convolutional networks (FCN) [23,24], DeepLabv3+ [25], and U-Net [19,26,27]. However, the main problem with semantic segmentation is that it is unable to segment continuous individuals from the same class.…”

Section: Introductionmentioning

confidence: 99%

“…Additionally, researchers recently combined hyperspectral data to reduce reliance on the size of the annotation samples. La Rosa et al [24] proposed a partial loss function to train an FCN, and achieved good accuracy (average user's accuracy: 88.63%, average producer's accuracy: 88.59%) for tree species classification using only 38 sparse and scarce trees as the training samples to detect 14 tree species. Zhang et al [47] employed a 3D-1D CNN model to classify tree species using airborne hyperspectral data, yielding a 93.14% classification accuracy.…”

Section: Introductionmentioning

confidence: 99%

“…Additionally, having numerous training samples can increase the time required for model training because of computational demand. Conversely, if the number of training samples is too small, it may not be sufficient to avoid overfitting during the model training and can yield poor performance [24], even when data augmentation is used. Therefore, it is an important part of the deep learning approach to determine suitable sample size.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

How Does Sample Labeling and Distribution Affect the Accuracy and Efficiency of a Deep Learning Model for Individual Tree-Crown Detection and Delineation

et al. 2022

View full text Add to dashboard Cite

Monitoring and assessing vegetation using deep learning approaches has shown promise in forestry applications. Sample labeling to represent forest complexity is the main limitation for deep learning approaches for remote sensing vegetation classification applications, and few studies have focused on the impact of sample labeling methods on model performance and model training efficiency. This study is the first-of-its-kind that uses Mask region-based convolutional neural networks (Mask R-CNN) to evaluate the influence of sample labeling methods (including sample size and sample distribution) on individual tree-crown detection and delineation. A flight was conducted over a plantation with Fokienia hodginsii as the main tree species using a Phantom4-Multispectral (P4M) to obtain UAV imagery, and a total of 2061 manually and accurately delineated tree crowns were used for training and validating (1689) and testing (372). First, the model performance of three pre-trained backbones (ResNet-34, ResNet-50, and ResNet-101) was evaluated. Second, random deleting and clumped deleting methods were used to repeatedly delete 10% from the original sample set to reduce the training and validation set, to simulate two different sample distributions (the random sample set and the clumped sample set). Both RGB image and Multi-band images derived from UAV flights were used to evaluate model performance. Each model’s average per-epoch training time was calculated to evaluate the model training efficiency. The results showed that ResNet-50 yielded a more robust network than ResNet-34 and ResNet-101 when the same parameters were used for Mask R-CNN. The sample size determined the influence of sample labeling methods on the model performance. Random sample labeling had lower requirements for sample size compared to clumped sample labeling, and unlabeled trees in random sample labeling had no impact on model training. Additionally, the model with clumped samples provides a shorter average per-epoch training time than the model with random samples. This study demonstrates that random sample labeling can greatly reduce the requirement of sample size, and it is not necessary to accurately label each sample in the image during the sample labeling process.

show abstract

Section: Input Imagementioning

confidence: 99%

Section: Input Imagementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

How Does Sample Labeling and Distribution Affect the Accuracy and Efficiency of a Deep Learning Model for Individual Tree-Crown Detection and Delineation

et al. 2022

View full text Add to dashboard Cite

show abstract

Tracking canopy gaps in mangroves remotely using deep learning

Lassalle

Filho

2022

Remote Sens Ecol Conserv

View full text Add to dashboard Cite

Mangroves are among the most ecologically valuable ecosystems of the globe. Reliable remote sensing solutions are required to assist their management and conservation at broad scale. Canopy gaps are part of forests' turnover and rejuvenation, but yet no method has been proposed to map their occurrence and recovery in mangroves. Here, were propose an approach based on a deep learning framework called Mask R-CNN to achieve automatic detection and delineation of gaps using very-high-resolution satellite imagery (<1 m). The Mask R-CNN combines a series of neural network architectures to identify and delineate gaps, determine their recovery stage, and estimate their morphological attributes. The approach was tested on four mangroves from different regions of the globe with high concentration of gaps of various origins (lightning strikes, oil spills, cutting, pests). The Mask R-CNN performed well to detect gaps, and accurately delineated gap contours (F1-score of segmentation ≥0.89). The model also succeeded in distinguishing among five recovery stages of gaps, from their onset to closure (Overall Accuracy = 91.4, Kappa = 0.89). Accurate retrieval of gap area, eccentricity, and compactnessthree relevant morphological attributeswere obtained (R 2 ≥ 0.83, NRMSE ≤10%). Several sources of confusion and misdelineation were identified. Our approach shows promising transferability to other mangrove sites and optical sensors and could help monitor canopy recovery in mangroves. It also opens promising perspectives for identifying the origin of gaps (natural or human-induced). It is intended to assist environmental managers and field experts in the management and conservation of these fragile ecosystems.

show abstract

An additive model system for heartwood, sapwood and bark diameter – A working example in Pinus koraiensis Siebold & Zucc. plantations

Sun,

Jia,

Saidahemaiti

2024

Computers and Electronics in Agriculture

View full text Add to dashboard Cite

Multi-task fully convolutional network for tree species mapping in dense forests using small training hyperspectral data

Cited by 38 publications

References 61 publications

How Does Sample Labeling and Distribution Affect the Accuracy and Efficiency of a Deep Learning Model for Individual Tree-Crown Detection and Delineation

How Does Sample Labeling and Distribution Affect the Accuracy and Efficiency of a Deep Learning Model for Individual Tree-Crown Detection and Delineation

Tracking canopy gaps in mangroves remotely using deep learning

An additive model system for heartwood, sapwood and bark diameter – A working example in Pinus koraiensis Siebold & Zucc. plantations

Contact Info

Product

Resources

About