Cross-regional oil palm tree counting and detection via a multi-level attention domain adaptation network

Zheng, Juepeng; Fu, Haohuan; Li, Weijia; Wu, Wencheng; Zhao, Yi; Dong, Runmin; Yu, Le

doi:10.1016/j.isprsjprs.2020.07.002

Cited by 63 publications

(25 citation statements)

References 62 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zheng et al [13] designed a multi-stage attention domain adaptation network (MADAN) for counting palm trees for satellite images. MADAN consists of a batch-instance normalization network as a feature extractor, a multi-level attention mechanism, a minimum entropy regularization, a sliding-window-based prediction, and a post-processing step based on IoU (intersection over union metric).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep-Learning-Based Automated Palm Tree Counting and Geolocation in Large Farms from Aerial Geotagged Images

2021

View full text Add to dashboard Cite

In this paper, we propose an original deep learning framework for the automated counting and geolocation of palm trees from aerial images using convolutional neural networks. For this purpose, we collected aerial images from two different regions in Saudi Arabia, using two DJI drones, and we built a dataset of around 11,000 instances of palm trees. Then, we applied several recent convolutional neural network models (Faster R-CNN, YOLOv3, YOLOv4, and EfficientDet) to detect palms and other trees, and we conducted a complete comparative evaluation in terms of average precision and inference speed. YOLOv4 and EfficientDet-D5 yielded the best trade-off between accuracy and speed (up to 99% mean average precision and 7.4 FPS). Furthermore, using the geotagged metadata of aerial images, we used photogrammetry concepts and distance corrections to automatically detect the geographical location of detected palm trees. This geolocation technique was tested on two different types of drones (DJI Mavic Pro and Phantom 4 pro) and was assessed to provide an average geolocation accuracy that attains 1.6 m. This GPS tagging allows us to uniquely identify palm trees and count their number from a series of drone images, while correctly dealing with the issue of image overlapping. Moreover, this innovative combination between deep learning object detection and geolocalization can be generalized to any other objects in UAV images.

show abstract

Section: Introductionmentioning

confidence: 99%

“…Figure13. Original UAV image of palms on PSU campus (right) and 4 selected palms (left) used for assessing the accuracy of our geolocation method.…”

mentioning

confidence: 99%

Deep-Learning-Based Automated Palm Tree Counting and Geolocation in Large Farms from Aerial Geotagged Images

2021

View full text Add to dashboard Cite

show abstract

“…However, complex scenarios such as overlapping tree crowns may cause deterioration of detection outcomes since there is no requirement of labels in this technique. DL-based classifiers, which use multiscale computational methods, have gained widespread adoption in recent studies using remote sensing images [134]. Most advances studies utilize deep learning-based classifier combined with a sliding window-based method to detect tree crowns from satellite images [134].…”

Section: ) Selection Of Optimum Algorithm For Oil Palm Yield Predictionmentioning

confidence: 99%

“…DL-based classifiers, which use multiscale computational methods, have gained widespread adoption in recent studies using remote sensing images [134]. Most advances studies utilize deep learning-based classifier combined with a sliding window-based method to detect tree crowns from satellite images [134]. It is renowned for its notable capacity of feature extraction, which can be accomplished using DL.…”

Section: ) Selection Of Optimum Algorithm For Oil Palm Yield Predictionmentioning

confidence: 99%

See 1 more Smart Citation

A Comprehensive Review of Crop Yield Prediction Using Machine Learning Approaches With Special Emphasis on Palm Oil Yield Prediction

et al. 2021

View full text Add to dashboard Cite

Cross-region building counting in satellite imagery using counting consistency

Zakria

Rawal

Sultani

et al. 2023

Neural Comput & Applic

View full text Add to dashboard Cite

Cross-regional oil palm tree counting and detection via a multi-level attention domain adaptation network

Cited by 63 publications

References 62 publications

Deep-Learning-Based Automated Palm Tree Counting and Geolocation in Large Farms from Aerial Geotagged Images

Deep-Learning-Based Automated Palm Tree Counting and Geolocation in Large Farms from Aerial Geotagged Images

A Comprehensive Review of Crop Yield Prediction Using Machine Learning Approaches With Special Emphasis on Palm Oil Yield Prediction

Cross-region building counting in satellite imagery using counting consistency

Contact Info

Product

Resources

About