Computer Vision Techniques in Forest Inventory Assessment: Improving Accuracy of Tree Diameter Measurement Using Smartphone Camera and Photogrammetry

Woo, Heesung; Kim, Ikhyun; Choi, Bong-Su

doi:10.18494/sam.2021.3605

Cited by 6 publications

(4 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, the RMSE of the minimum ellipse circle showed the lowest volume estimation among four circular fitting algorithms. (9) Additionally, Bienert et al investigated tree DBH using integrated MLS and TLS LiDAR systems. The results of their research indicated that the least-squares cylinder-fitting algorithm was the most accurate with an RMSE of 3.7 cm.…”

Section: Results Of Individual Dbh Estimationmentioning

confidence: 99%

“…They found that the least-squares circle and minimum-enclosing circle algorithms were the most accurate for estimating tree diameter in Pinus densiflora and Pinus koraiensis forest stands. (9) Recently, unmanned aerial vehicles (UAVs) equipped with LiDAR systems for ALS have been widely adopted in large-scale forests. ALS allows scanning over a large area and is increasingly being used to determine forest canopy structures.…”

Section: Introductionmentioning

confidence: 99%

“…(11) Unfortunately, the application of LiDAR sensors remains limited in forestry, a small-scale industry, in South Korea, because of the high cost of sensors and lack of information on LiDAR applications in forestry. (9) Hence, we investigated the opportunities and limitations of using the LiDAR technology to estimate the DBH and height of individual trees in South Korean forests.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Forest Inventory Assessment Using Integrated Light Detection and Ranging (LiDAR) Systems: Merged Point Cloud of Airborne and Mobile Laser Scanning Systems

Lee¹,

Woo²,

Lee³

2022

Sensors and Materials

View full text Add to dashboard Cite

Precise assessment of forest inventory can help optimize timber value and industrial forestmanagement planning. Light detection and ranging (LiDAR) technology has been recently introduced in forestry to effectively and precisely estimate and monitor forest inventories. In this study, we investigated the opportunities and limitations of integrated mobile laser scanning (MLS) and airborne laser scanning (ALS) LiDAR applications for estimating individual tree diameter at breast height (DBH) and tree height. Three circular fitting algorithms (integrated RANSAC and circle fitting, minimum enclosing circle, and least-squares ellipse fitting) were used to estimate DBH. Height was calculated using the crown height model (CHM). DBH was most accurately estimated by the ellipse-fitting algorithm. Integrated MLS and ALS performed better than previous circular fitting applications in estimating DBH values. Lastly, the tree height estimated using the CHM was compared with the ground truth, and R 2 and the root mean square error (RMSE) of the height were 0.60 and 2.0 m, respectively. In addition, the trend of low accuracy for suppressed trees was identified from point cloud data (PCD) extraction because of overlapped PCD among the surrounding dominant trees. This result indicated that the segmentation of the top of suppressed trees was limited by overlap issues in high-density forests.

show abstract

Section: Results Of Individual Dbh Estimationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Forest Inventory Assessment Using Integrated Light Detection and Ranging (LiDAR) Systems: Merged Point Cloud of Airborne and Mobile Laser Scanning Systems

Lee¹,

Woo²,

Lee³

2022

Sensors and Materials

View full text Add to dashboard Cite

show abstract

“…Vastaranta et al (2015) studied basal area and height mensurations with Tres-tima and obtained excellent results, but the set-up in their study was also different to our study. Other smartphone studies have mainly focused on measuring DBH (Fan et al 2018, Wu et al 2019, Woo et al 2021.…”

Section: Discussionmentioning

confidence: 99%

Estimating the accuracy of smartphone app-based removal estimates against actual wood-harvesting data from clear cuttings

Vähä-Konka,

Korhonen,

Kärhä

et al. 2024

iForest

View full text Add to dashboard Cite

is a computer vision-based smartphone application that utilises relascope theory to obtain estimates of forest attributes from smartphone photographs. The aim of this study was to investigate the accuracy of Trestima estimation and evaluate whether it is sufficiently accurate for operational use in forestry. Our data consisted of 37 forest stands, encompassing 73.5 ha in southeastern Finland, where Trestima estimates were obtained by forestry professionals during their work. The results were compared with harvester data obtained from clear-cut stands. The number of photographs taken per stand ranged between 1-29 (average: 7.3; standard deviation: 5.0). The total amount of industrial roundwood harvested from the stands was 21,531 m 3 and the average harvest removal per hectare was 282 m 3 . The accuracy of Trestima estimation was relatively good when ≥ 10 photographs per stand were taken. In this case, the root mean square error percent (RMSE%) value associated with roundwood volume was 17.7%. When the number of photographs per stand was < 10, the accuracy of Trestima was much weaker (RMSE% 22.7-55.3%). On average, Trestima underestimated harvested volumes in Scots pine (Pinus sylvestris L.) stands (Bias% 11.4-89.2), although the bias was smaller (Bias% -12.7-12.4) with Norway spruce (Picea abies [L.] Karst.) stands. The Trestima smartphone application is a possible option for traditional field measurements in operational forestry, provided that its usage instructions are strictly followed, which is not always the case in practice.

show abstract

Augmented reality for measuring diameter at breast height using the iPhone measure app: outcomes on tree- and stand-level estimates of basal area in a Carpathian mixed forest

Apăfăian,

Avasiloaie,

Vasilescu

2024

Eur J Forest Res

View full text Add to dashboard Cite

Computer Vision Techniques in Forest Inventory Assessment: Improving Accuracy of Tree Diameter Measurement Using Smartphone Camera and Photogrammetry

Cited by 6 publications

References 28 publications

Forest Inventory Assessment Using Integrated Light Detection and Ranging (LiDAR) Systems: Merged Point Cloud of Airborne and Mobile Laser Scanning Systems

Forest Inventory Assessment Using Integrated Light Detection and Ranging (LiDAR) Systems: Merged Point Cloud of Airborne and Mobile Laser Scanning Systems

Estimating the accuracy of smartphone app-based removal estimates against actual wood-harvesting data from clear cuttings

Augmented reality for measuring diameter at breast height using the iPhone measure app: outcomes on tree- and stand-level estimates of basal area in a Carpathian mixed forest

Contact Info

Product

Resources

About