Land Use Change Detection Using Deep Siamese Neural Networks and Weakly Supervised Learning

Kalita, Indrajit; Karatsiolis, Savvas; Kamilaris, Andreas

doi:10.1007/978-3-030-89131-2_3

Cited by 7 publications

(2 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Tang et al developed a weakly supervised learning model for pavement crack detection and achieved better results than some fully supervised learning models ( 31 ). The works of ( 32 – 35 ) share a similar approach; they utilized image-level labels, trained a CNN that could roughly locate the change regions, and then applied a secondary method to refine the change map. However, their network architectures, segmentation refining methods, and some other details are different.…”

Section: Related Workmentioning

confidence: 99%

Railroad Crossing Surveillance and Foreground Extraction Network: Weakly Supervised Artificial-Intelligence Approach

Tang

Wang

Qian

2023

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

According to the report to Congress National Strategy to Prevent Trespassing on Railroad Property issued by the Federal Railroad Administration, trespassing is currently the number one cause of all railroad-related deaths. The number of fatalities resulting from trespassing, including both illegally entering and remaining in the railroad right-of-way, is even higher than the number of deaths caused by collisions between vehicles and trains. Accurately and effectively detecting objects at rail crossings is critical for improving railway safety. The convolutional neural network (CNN) is one of the most potent tools in image processing and video surveillance. However, the current CNNs under supervised learning rely on a substantial amount of manually labeled images, which is labor-intensive and time-consuming. This study proposes a weakly supervised learning technique for training foreground-segmentation networks and develops a tailored CNN network, RC-SAFE (railroad crossing surveillance and foreground extraction), to accurately and effectively detect and track both still and moving objects in the railroad crossing area. The weakly supervised learning significantly reduces the load for image labeling. The experimental results on the public CDnet 2014 dataset show that the weakly supervised network outperforms the supervised network and some other state-of-the-art foreground-segmentation methods. Railroad crossing monitoring videos are collected at different railroad crossings to validate the proposed RC-SAFE network. The results confirm the robustness of the proposed RC-SAFE network, and that RC-SAFE can detect any object that does not belong to the railroad crossing, which outperforms object-detection-based models, such as Mask RCNN (a region-based CNN).

show abstract

Section: Related Workmentioning

confidence: 99%

Railroad Crossing Surveillance and Foreground Extraction Network: Weakly Supervised Artificial-Intelligence Approach

Tang

Wang

Qian

2023

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

show abstract

“…An- In the field of weakly supervised CD, current methods for propagating initial change areas across the entire image pair to generate pixel-level pseudo-labels predominantly rely on relatively traditional post-processing techniques such as PCA [138], K-Means [139], and conditional random fields (CRF) [140]. For instance, Kalita et al [141] trained a Siamese CNN classification network using image-level labels to obtain deep features of image pairs and generate change localization maps. They then applied PCA and K-Means methods to segment these maps for pixel-level CD results.…”

mentioning

confidence: 99%

Advances and Challenges in Deep Learning-Based Change Detection for Remote Sensing Images: A Review through Various Learning Paradigms

Wang,

Zhang,

Gao

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

Change detection (CD) in remote sensing (RS) imagery is a pivotal method for detecting changes in the Earth’s surface, finding wide applications in urban planning, disaster management, and national security. Recently, deep learning (DL) has experienced explosive growth and, with its superior capabilities in feature learning and pattern recognition, it has introduced innovative approaches to CD. This review explores the latest techniques, applications, and challenges in DL-based CD, examining them through the lens of various learning paradigms, including fully supervised, semi-supervised, weakly supervised, and unsupervised. Initially, the review introduces the basic network architectures for CD methods using DL. Then, it provides a comprehensive analysis of CD methods under different learning paradigms, summarizing commonly used frameworks. Additionally, an overview of publicly available datasets for CD is offered. Finally, the review addresses the opportunities and challenges in the field, including: (a) incomplete supervised CD, encompassing semi-supervised and weakly supervised methods, which is still in its infancy and requires further in-depth investigation; (b) the potential of self-supervised learning, offering significant opportunities for Few-shot and One-shot Learning of CD; (c) the development of Foundation Models, with their multi-task adaptability, providing new perspectives and tools for CD; and (d) the expansion of data sources, presenting both opportunities and challenges for multimodal CD. These areas suggest promising directions for future research in CD. In conclusion, this review aims to assist researchers in gaining a comprehensive understanding of the CD field.

show abstract

Cnns in land cover mapping with remote sensing imagery: a review and meta-analysis

Kotaridis,

Lazaridou

2023

International Journal of Remote Sensing

View full text Add to dashboard Cite

Land Use Change Detection Using Deep Siamese Neural Networks and Weakly Supervised Learning

Cited by 7 publications

References 21 publications

Railroad Crossing Surveillance and Foreground Extraction Network: Weakly Supervised Artificial-Intelligence Approach

Railroad Crossing Surveillance and Foreground Extraction Network: Weakly Supervised Artificial-Intelligence Approach

Advances and Challenges in Deep Learning-Based Change Detection for Remote Sensing Images: A Review through Various Learning Paradigms

Cnns in land cover mapping with remote sensing imagery: a review and meta-analysis

Contact Info

Product

Resources

About