Imbalanced learning of remotely sensed data for bioenergy source identification in a forest in the Wallacea region of Indonesia

Review Chemistry, Inorganic & Nuclear

Surveying coconut trees using high-resolution satellite imagery in remote atolls of the Pacific Ocean

Juepeng Zheng et al.

Summary: Coconut is an economically important tree species and its plantations dominate many islands and tropical coastlines. However, the expansion of plantations threatens biodiversity. This study presents a method called COCODET, which uses satellite imagery to accurately detect coconut trees, and achieves better performance than other object detection algorithms.

COORDINATION CHEMISTRY REVIEWS (2023)

添加到收藏夹

Review Computer Science, Artificial Intelligence

Imbalance Problems in Object Detection: A Review

Kemal Oksuz et al.

Summary: This paper provides a comprehensive review of imbalance problems in object detection, presenting a problem-based taxonomy to systematically analyze and discuss solutions. Major open issues regarding existing and new imbalance problems are identified, with a webpage cataloging relevant papers for researchers to access.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2021)

添加到收藏夹

Article Geography, Physical

Growing status observation for oil palm trees using Unmanned Aerial Vehicle (UAV) images

Juepeng Zheng et al.

Summary: The rapid expansion of oil palm plantations in tropical developing countries has both positive economic benefit and negative ecological impact. Accurate detection of oil palm trees is crucial for improving plantation planning, yield, and reducing manpower and fertilizer consumption. The use of Unmanned Aerial Vehicles (UAVs) shows promise for monitoring individual oil palms, but challenges remain in achieving accuracy due to class imbalance and similarity. The Multi-class Oil Palm Detection approach (MOPAD) proposed in this paper utilizes advanced features and loss modules to achieve accurate detection and monitoring of individual oil palms, demonstrating excellent potential for efficient management.

ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING (2021)

添加到收藏夹

Article Environmental Sciences

Machine Learning Classification of Endangered Tree Species in a Tropical Submontane Forest Using WorldView-2 Multispectral Satellite Imagery and Imbalanced Dataset

Colbert M. Jackson et al.

Summary: This study assessed the effects of imbalanced data in identifying and mapping tree species in a tropical forest. The combined oversampling and undersampling technique produced the best results, showing improved classification accuracy compared to the original imbalanced dataset.

REMOTE SENSING (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Cascade R-CNN: High Quality Object Detection and Instance Segmentation

Zhaowei Cai et al.

Summary: In object detection, the commonly used IoU threshold of 0.5 can lead to noisy detections, and performance may degrade for larger thresholds. The Cascade R-CNN architecture addresses this issue by training detectors sequentially with increasing IoU thresholds and eliminating quality mismatches at inference, resulting in state-of-the-art performance and significant improvement in high-quality detection across various datasets. The model is also generalized to instance segmentation, achieving nontrivial improvements over existing methods.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2021)

添加到收藏夹

Article Remote Sensing