Comparative Analysis of Generalized Intersection over Union and Error Matrix for Vegetation Cover Classification Assessment

Choi, Hyun Kyung; Lee, Hyun-Jik; You, Ho Jin; Rhee, Sang-Yong; Jeon, Wang-Su

doi:10.18494/sam.2019.2584

Cited by 10 publications

(6 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The key bone developmental grades and locations were the categories we sorted the results into following the KBS. We assessed location accuracy using the Intersection over Union (IOU) ( 33 ). After plotting the confusion matrix, we calculated the key bone developmental grade classification data’s accuracy and precision (weighted average).…”

Section: Methodsmentioning

confidence: 99%

“…In the first part, Both the PP-PicoDet and NanoDet models are anchor-free models, while the YOLOv5 model employed the Kmeans method to obtain anchors such as [[23,24, 27,28, 26,34], [32,33,31,41,37,38], [38,48,54,58,66,69]]. The images were preprocessed before model training, including resizing the images to correspond to the size required by the model (640x640 for YOLOv5, 416x416 for PP-PicoDet, and 416x416 for NanoDet) and normalizing the images to a range of pixel values of (0, 1).…”

Section: Training Modelmentioning

confidence: 99%

See 1 more Smart Citation

A real-time automated bone age assessment system based on the RUS-CHN method

Yang

Dai²,

Qin³

et al. 2023

Front. Endocrinol.

View full text Add to dashboard Cite

BackgroundBone age is the age of skeletal development and is a direct indicator of physical growth and development in children. Most bone age assessment (BAA) systems use direct regression with the entire hand bone map or first segmenting the region of interest (ROI) using the clinical a priori method and then deriving the bone age based on the characteristics of the ROI, which takes more time and requires more computation.Materials and methodsKey bone grades and locations were determined using three real-time target detection models and Key Bone Search (KBS) post-processing using the RUS-CHN approach, and then the age of the bones was predicted using a Lightgbm regression model. Intersection over Union (IOU) was used to evaluate the precision of the key bone locations, while the mean absolute error (MAE), the root mean square error (RMSE), and the root mean squared percentage error (RMSPE) were used to evaluate the discrepancy between predicted and true bone age. The model was finally transformed into an Open Neural Network Exchange (ONNX) model and tested for inference speed on the GPU (RTX 3060).ResultsThe three real-time models achieved good results with an average (IOU) of no less than 0.9 in all key bones. The most accurate outcomes for the inference results utilizing KBS were a MAE of 0.35 years, a RMSE of 0.46 years, and a RMSPE of 0.11. Using the GPU RTX3060 for inference, the critical bone level and position inference time was 26 ms. The bone age inference time was 2 ms.ConclusionsWe developed an automated end-to-end BAA system that is based on real-time target detection, obtaining key bone developmental grade and location in a single pass with the aid of KBS, and using Lightgbm to obtain bone age, capable of outputting results in real-time with good accuracy and stability, and able to be used without hand-shaped segmentation. The BAA system automatically implements the entire process of the RUS-CHN method and outputs information on the location and developmental grade of the 13 key bones of the RUS-CHN method along with the bone age to assist the physician in making judgments, making full use of clinical a priori knowledge.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Training Modelmentioning

confidence: 99%

A real-time automated bone age assessment system based on the RUS-CHN method

Yang

Dai²,

Qin³

et al. 2023

Front. Endocrinol.

View full text Add to dashboard Cite

show abstract

“…Correlation is also highly sensitive to non-linear relationship, noise, subgroups and outliers [51,52] making incorrect evaluation. According to [53,54], the dice score and the mean intersection over union (mIoU) are more adapted to evaluate the segmentation mask. Defined by:…”

Section: Performance Evaluationmentioning

confidence: 99%

DeepIndices: Remote Sensing Indices Based on Approximation of Functions through Deep-Learning, Application to Uncalibrated Vegetation Images

et al. 2021

View full text Add to dashboard Cite

The form of a remote sensing index is generally empirically defined, whether by choosing specific reflectance bands, equation forms or its coefficients. These spectral indices are used as preprocessing stage before object detection/classification. But no study seems to search for the best form through function approximation in order to optimize the classification and/or segmentation. The objective of this study is to develop a method to find the optimal index, using a statistical approach by gradient descent on different forms of generic equations. From six wavebands images, five equations have been tested, namely: linear, linear ratio, polynomial, universal function approximator and dense morphological. Few techniques in signal processing and image analysis are also deployed within a deep-learning framework. Performances of standard indices and DeepIndices were evaluated using two metrics, the dice (similar to f1-score) and the mean intersection over union (mIoU) scores. The study focuses on a specific multispectral camera used in near-field acquisition of soil and vegetation surfaces. These DeepIndices are built and compared to 89 common vegetation indices using the same vegetation dataset and metrics. As an illustration the most used index for vegetation, NDVI (Normalized Difference Vegetation Indices) offers a mIoU score of 63.98% whereas our best models gives an analytic solution to reconstruct an index with a mIoU of 82.19%. This difference is significant enough to improve the segmentation and robustness of the index from various external factors, as well as the shape of detected elements.

show abstract

“…The higher OA value, the more correctly classified samples among the entire samples among the dataset. IoU (Equation (2)) was a parameter calculated by the number of samples intersection divided by that of union [64], or the ratio between the number of true positive and the sum of the number of true positives, false positives, false negatives [65]. The higher IoU of ith class (IoU i ), the fewer samples with wrong predictions or misclassified of ith class.…”

Section: Semantic Segmentation Performance Evaluationmentioning

confidence: 99%

Early Detection of Encroaching Woody Juniperus virginiana and Its Classification in Multi-Species Forest Using UAS Imagery and Semantic Segmentation Algorithms

et al. 2021

View full text Add to dashboard Cite

Woody plant encroachment into grasslands ecosystems causes significantly ecological destruction and economic losses. Effective and efficient management largely benefits from accurate and timely detection of encroaching species at an early development stage. Recent advances in unmanned aircraft systems (UAS) enabled easier access to ultra-high spatial resolution images at a centimeter level, together with the latest machine learning based image segmentation algorithms, making it possible to detect small-sized individuals of target species at early development stage and identify them when mixed with other species. However, few studies have investigated the optimal practical spatial resolution of early encroaching species detection. Hence, we investigated the performance of four popular semantic segmentation algorithms (decision tree, DT; random forest, RF; AlexNet; and ResNet) on a multi-species forest classification case with UAS-collected RGB images in original and down-sampled coarser spatial resolutions. The objective of this study was to explore the optimal segmentation algorithm and spatial resolution for eastern redcedar (Juniperus virginiana, ERC) early detection and its classification within a multi-species forest context. To be specific, firstly, we implemented and compared the performance of the four semantic segmentation algorithms with images in the original spatial resolution (0.694 cm). The highest overall accuracy was 0.918 achieved by ResNet with a mean interaction over union at 85.0%. Secondly, we evaluated the performance of ResNet algorithm with images in down-sampled spatial resolutions (1 cm to 5 cm with 0.5 cm interval). When applied on the down-sampled images, ERC segmentation performance decreased with decreasing spatial resolution, especially for those images coarser than 3 cm spatial resolution. The UAS together with the state-of-the-art semantic segmentation algorithms provides a promising tool for early-stage detection and localization of ERC and the development of effective management strategies for mixed-species forest management.

show abstract

Comparative Analysis of Generalized Intersection over Union and Error Matrix for Vegetation Cover Classification Assessment

Cited by 10 publications

References 13 publications

A real-time automated bone age assessment system based on the RUS-CHN method

A real-time automated bone age assessment system based on the RUS-CHN method

DeepIndices: Remote Sensing Indices Based on Approximation of Functions through Deep-Learning, Application to Uncalibrated Vegetation Images

Early Detection of Encroaching Woody Juniperus virginiana and Its Classification in Multi-Species Forest Using UAS Imagery and Semantic Segmentation Algorithms

Contact Info

Product

Resources

About