Automated annotation of coral reef survey images

Beijbom, Oscar; Edmunds, Peter J.; Kline, David I.; Mitchell, B. Greg; Kriegman, David

doi:10.1109/cvpr.2012.6247798

Cited by 235 publications

(258 citation statements)

References 98 publications

Supporting

Mentioning

258

Contrasting

Order By: Relevance

“…Recent studies have also shown the value of image features for remote sensing and ecological applications. Beijborn et al [79] used image features to automatically classify coral communities. Image features have been used for automatic detection and classification of leaves and flowers [80,81].…”

Section: Computer Vision Image Features: the New Pixelmentioning

confidence: 99%

Optimal Altitude, Overlap, and Weather Conditions for Computer Vision UAV Estimates of Forest Structure

2015

View full text Add to dashboard Cite

Ecological remote sensing is being transformed by three-dimensional (3D), multispectral measurements of forest canopies by unmanned aerial vehicles (UAV) and computer vision structure from motion (SFM) algorithms. Yet applications of this technology have out-paced understanding of the relationship between collection method and data quality. Here, UAV-SFM remote sensing was used to produce 3D multispectral point clouds of Temperate Deciduous forests at different levels of UAV altitude, image overlap, weather, and image processing. Error in canopy height estimates was explained by the alignment of the canopy height model to the digital terrain model (R 2 = 0.81) due to differences in lighting and image overlap. Accounting for this, no significant differences were observed in height error at different levels of lighting, altitude, and side overlap. Overall, accurate estimates of canopy height compared to field measurements (R 2 = 0.86, RMSE = 3.6 m) and LIDAR (R 2 = 0.99, RMSE = 3.0 m) were obtained under optimal conditions of clear lighting and high image overlap (>80%). Variation in point cloud quality appeared related to the behavior of SFM 'image features'. Future research should consider the role of image features as the fundamental unit of SFM remote sensing, akin to the pixel of optical imaging and the laser pulse of LIDAR.

show abstract

Section: Computer Vision Image Features: the New Pixelmentioning

confidence: 99%

Optimal Altitude, Overlap, and Weather Conditions for Computer Vision UAV Estimates of Forest Structure

2015

View full text Add to dashboard Cite

show abstract

“…The average precision (AP) summarizes the precision-recall curve by measuring the area under the curve. To compare the proposed framework, four underwater image algorithms (Pizarro [8], Beijbom [4], Marcos [9] and Stokes and Deane [10]) and two state-of-the-art texture classification methods (Caputo [19] and Zhang [20]) are used. Each algorithm is implemented as closely as possible to the original papers (the parameters are tuned with exhaustive search).…”

Section: Criteria For Evaluation and Comparison With Other Methodsmentioning

confidence: 99%

“…Most of the other methods, however, perform significantly worse against texture-only datasets. The failure of the methods by Marcos [9], Stokes & Deane [10], Pizarro [8] and Beijbom [4] on standard texture datasets indicates that these methods rely heavily on color information. Heavy reliance on color information may limit the robustness of classification algorithms, since color can be inconsistent or absent in underwater datasets.…”

Section: Montipora Pavona Pocilloporamentioning

confidence: 99%

“…Without comparison on standard datasets, it is impossible to assess the relative effectiveness and efficiency of these methods: Pizarro [8], Beijbom [4], Marcos [9] and Stokes and Deane [10]. All the previous algorithms used fixed classification schemes for all types of underwater optical image datasets.…”

Section: Introductionmentioning

confidence: 99%

“…Efforts to automate classification have been made for well over a decade [3], but no single algorithm is yet widely accepted as robust. A few of the most challenging obstacles to classification accuracy in coral reef environments include: significant intra-class and inter-site variability in the morphology of benthic organisms [4], complex spatial borders between classes on the seabed, subjective annotation of training data by different analysts, variation in viewpoints, distances and image quality, limits to spatial and spectral resolution when trying to classify to a free taxonomic scale, partial occlusion of objects due to the three-dimensional structure of the seabed, lighting artifacts due to wave focusing [5][6][7] and variable optical properties of the water column.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Image-Based Coral Reef Classification and Thematic Mapping

et al. 2013

View full text Add to dashboard Cite

This paper presents a novel image classification scheme for benthic coral reef images that can be applied to both single image and composite mosaic datasets. The proposed method can be configured to the characteristics (e.g., the size of the dataset, number of classes, resolution of the samples, color information availability, class types, etc.) of individual datasets. The proposed method uses completed local binary pattern (CLBP), grey level co-occurrence matrix (GLCM), Gabor filter response, and opponent angle and hue channel color histograms as feature descriptors. For classification, either knearest neighbor (KNN), neural network (NN), support vector machine (SVM) or probability density weighted mean distance (PDWMD) is used. The combination of features and classifiers that attains the best results is presented together with the guidelines for selection. The accuracy and efficiency of our proposed method are compared with other state-of-the-art techniques using three benthic and three texture datasets. The proposed method achieves the highest overall classification accuracy of any of the tested methods and has moderate execution time. Finally, the proposed classification scheme is applied to a large-scale image mosaic of the Red Sea to create a completely classified thematic map of the reef benthos.

show abstract

Application Challenges from a Bird's‐Eye View

Scaramuzza

López²,

Imiya³

et al. 2017

Computer Vision in Vehicle Technology

View full text Add to dashboard Cite

Computer Vision in Vehicle Technology focuses on computer vision as on-board technology, bringing together fields of research where computer vision is progressively penetrating: the automotive sector, unmanned aerial and underwater vehicles. It also serves as a reference for researchers of current developments and challenges in areas of the application of computer vision, involving vehicles such as advanced driver assistance (pedestrian detection, lane departure warning, traffic sign recognition), autonomous driving and robot navigation (with visual simultaneous localization and mapping) or unmanned aerial vehicles (obstacle avoidance, landscape classification and mapping, fire risk assessment).

show abstract

Automated annotation of coral reef survey images

Cited by 235 publications

References 98 publications

Optimal Altitude, Overlap, and Weather Conditions for Computer Vision UAV Estimates of Forest Structure

Optimal Altitude, Overlap, and Weather Conditions for Computer Vision UAV Estimates of Forest Structure

Image-Based Coral Reef Classification and Thematic Mapping

Application Challenges from a Bird's‐Eye View

Contact Info

Product

Resources

About