Yinghai Ke

A review of methods for automatic individual tree-crown detection and delineation from passive remote sensing

Efficient forest management demands detailed, timely information. As high spatial resolution remotely sensed imagery becomes more available, there is a great potential for conducting high accuracy forest inventory and analysis automatically and cost-efficiently. Recent research aimed at providing tree-based forest inventory measurements has generated numerous algorithms for automatic individual tree-crown detection and delineation. This article reviews this research with a focus on algorithms applied to passive remote-sensing imagery. The article categorizes and evaluates methods for automatic tree-crown detection and delineation. It considers the types of imagery and the characteristics of the study areas these algorithms are applied to and evaluates the influence of these factors on the methods. The article also reviews and evaluates quantitative accuracy assessment methods for tree-crown delineation and detection. Finally, the article summarizes the commonalities of current algorithms, and the new development that can be expected in the future.

A comparison of three methods for automatic tree crown detection and delineation from high spatial resolution imagery

This article compares the performance of three algorithms representative of published methods for tree crown detection and delineation from high spatial resolution imagery, and demonstrates a standardized accuracy assessment framework. The algorithms – watershed segmentation, region growing and valley-following – were tested on softwood and hardwood sites using Emerge natural colour vertical aerial imagery with 60 cm ground sampled distance and QuickBird panchromatic imagery with an 11˚ look angle. The evaluation considered both plot-level and individual tree crown detection and delineation results. The study shows that while all three methods reasonably delineate crowns in the softwood stand on the Emerge image, region growing provided the highest accuracies, with producers and users accuracy for tree detection reaching 70% and root mean square error for crown diameter estimation of 15%. Crown detection accuracies were lower on the QuickBird image. No algorithm proved accurate for the hardwood stand on either image set (both producers and users accuracies < 30%).

Active Contour and Hill Climbing for Tree Crown Detection and Delineation

This paper presents a new approach for individual tree crown detection and delineation that is applicable under various imaging conditions. The approach extracts crown area using a region-based active contour model and then detects tree tops within the crown area by considering both spectral and shape characteristics of the crown. The detected tree tops allow subsequent clustering of crown pixels using a new hill-climbing algorithm. We tested the approach on a Norway spruce stand using three types of high spatial resolution imagery: an Emerge natural color vertical aerial image, an off nadir QuickBird panchromatic image, and a natural color digital orthoimage. In comparison to the published region growing algorithm, our approach improved tree crown detection by over 10 percent for all three types of imagery, and provided accurate tree crown diameter estimation, which has utility in tree volume estimation, species composition, and forest health analysis.

Downscaling of MODIS One kilometer evapotranspiration using Landsat-8 data and machine learning approaches

This study presented a MODIS 8-day 1 km evapotranspiration (ET) downscaling method based on Landsat 8 data (30 m) and machine learning approaches. Eleven indicators including albedo, land surface temperature (LST), and vegetation indices (VIs) derived from Landsat 8 data were first upscaled to 1 km resolution. Machine learning algorithms including Support Vector Regression (SVR), Cubist, and Random Forest (RF) were used to model the relationship between the Landsat indicators and MODIS 8-day 1 km ET. The models were then used to predict 30 m ET based on Landsat 8 indicators. A total of thirty-two pairs of Landsat 8 images/MODIS ET data were evaluated at four study sites including two in United States and two in South Korea. Among the three models, RF produced the lowest error, with relative Root Mean Square Error (rRMSE) less than 20%. Vegetation greenness related indicators such as Normalized Difference Vegetation Index (NDVI), Enhanced Vegetation Index (EVI), Soil Adjusted Vegetation Index (SAVI), and vegetation moisture related indicators such as Normalized Difference Infrared Index—Landsat 8 OLI band 7 (NDIIb7) and Normalized Difference Water Index (NDWI) were the five most important features used in RF model. Temperature-based indicators were less important than vegetation greenness and moisture-related indicators because LST could have considerable variation during each 8-day period. The predicted Landsat downscaled ET had good overall agreement with MODIS ET (average rRMSE = 22%) and showed a similar temporal trend as MODIS ET. Compared to the MODIS ET product, the downscaled product demonstrated more spatial details, and had better agreement with in situ ET observations (R2 = 0.56). However, we found that the accuracy of MODIS ET was the main control factor of the accuracy of the downscaled product. Improved coarse-resolution ET estimation would result in better finer-resolution estimation. This study proved the potential of using machine learning approaches for ET downscaling considering their effectiveness and ease of implementation. Future research includes development of the spatial-temporal fusion models of Landsat data and MODIS ET in order to increase temporal resolution of downscaled ET.