Search Results (6)

Following European directives, asbestos–cement corrugated roofing tiles must be eliminated by 2025. Therefore, identifying asbestos–cement rooftops is the first necessary step to proceed with their removal. Unfortunately, asbestos detection is a challenging task. Current procedures for identifying asbestos require human exploration, which is costly and slow. This has motivated the interest of governments and companies in developing automatic tools that can help to detect and classify these types of materials that are dangerous to the population. This paper explores multiple computer vision techniques based on Deep Learning to advance the automatic detection of asbestos in aerial images. On the one hand, we trained and tested two classification architectures, obtaining high accuracy levels. On the other, we implemented an explainable AI method to discern what information in an RGB image is relevant for a successful classification, ensuring that our classifiers’ learning process is guided by the right variables—color, surface patterns, texture, etc.—observable on asbestos rooftops. Full article

In Africa, the distribution of color steel tile roof (CSTR) can reflect the living standard of residents, and the analysis of its temporal and spatial changes can reflect the local changes in local living conditions. It is helpful to analyze the change of the local economic level. By using the satellite remote sensing image processing method to obtain the temporal and spatial change characteristics of CSTR and to analyze the changes in residents’ living conditions in Munyaka, Eldoret, Kenya, Africa, the model of multifeature decision tree method (DTM) extraction was established. The Normalized Difference Vegetation Index (NDVI) and Normalized Difference Building Index (NDBI) were used to remove farmland from the difference of the CSTR. The Normalized Difference Surface Index (NCSI) was constructed, and the texture features were analyzed to eliminate wasteland and bare land, respectively. The research results show that the Kappa coefficient is 0.9223, and the user precision and mapping precision are 97.79% and 91.10%, respectively. At the same time, combined with the Erdoret municipal road project, the changes of CSTR before and after the project in 2016–2020 are studied. Compared the area change of CSTR in 2016–2018 with that in 2018–2020, the annual growth rate before the construction of the municipal road project is about 3.47%. After the completion of the project, the annual growth rate is 7.29%, more than twice the rate before the construction. This method can realize the dynamic monitoring of CSTR, reflect the changes of the residents’ living environment in the region, help analyze the improvement of poverty in Africa, and help understand the changes of African economic conditions. Full article

Convolutional neural network (CNN)-based remote sensing (RS) image segmentation has become a widely used method for building footprint mapping. Recently, DeeplabV3+, an advanced CNN architecture, has shown satisfactory performance for building extraction in different urban landscapes. However, it faces challenges due to the large amount of labeled data required for model training and the extremely high costs associated with the annotation of unlabelled data. These challenges encouraged us to design a framework for building footprint mapping with fewer labeled data. In this context, the published studies on RS image segmentation are reviewed first, with a particular emphasis on the use of active learning (AL), incremental learning (IL), transfer learning (TL), and their integration for reducing the cost of data annotation. Based on the literature review, we defined three candidate frameworks by integrating AL strategies (i.e., margin sampling, entropy, and vote entropy), IL, TL, and DeeplabV3+. They examine the efficacy of AL, the efficacy of IL in accelerating AL performance, and the efficacy of both IL and TL in accelerating AL performance, respectively. Additionally, these frameworks enable the iterative selection of image tiles to be annotated, training and evaluation of DeeplabV3+, and quantification of the landscape features of selected image tiles. Then, all candidate frameworks were examined using WHU aerial building dataset as it has sufficient (i.e., 8188) labeled image tiles with representative buildings (i.e., various densities, areas, roof colors, and shapes of the building). The results support our theoretical analysis: (1) all three AL strategies reduced the number of image tiles by selecting the most informative image tiles, and no significant differences were observed in their performance; (2) image tiles with more buildings and larger building area were proven to be informative for the three AL strategies, which were prioritized during the data selection process; (3) IL can expedite model training by accumulating knowledge from chosen labeled tiles; (4) TL provides a better initial learner by incorporating knowledge from a pre-trained model; (5) DeeplabV3+ incorporated with IL, TL, and AL has the best performance in reducing the cost of data annotation. It achieved good performance (i.e., mIoU of 0.90) using only 10–15% of the sample dataset; DeeplabV3+ needs 50% of the sample dataset to realize the equivalent performance. The proposed frameworks concerning DeeplabV3+ and the results imply that integrating TL, AL, and IL in human-in-the-loop building extraction could be considered in real-world applications, especially for building footprint mapping. Full article

The high rate of heat transfer through the residential roof assembly aggravates the condition of indoor thermal discomfort. Bulk insulation can be installed in the assembly to improve thermal performance. However, although it can efficiently reduce diurnal heat transfer from the outdoor environment into the indoor space through the roof assembly, it can also suppress nocturnal heat transfer in the opposite direction. Alternatively, high-albedo roof tiles employ cool colors to reflect heat at the roof surface, whereas bulk insulation hinders the conduction of heat through the roof assembly. In light of the potential of high-albedo roof tiles and bulk insulation in reducing heat transfer, thermal-energy performance of an urban pitched residential roof assembly, which adopted varying configurations of high-albedo roof tiles and bulk insulation under a hot, humid climate, was evaluated. Energy savings were generated, which were 15.13% when the change from a conventional to a high-albedo roof surface was performed, and 17.00% when the installation of bulk insulation was performed on the high-albedo roof assembly. Full article

The increase in gated communities is the most important recent urban phenomenon in Latin America. This article proposes a methodology to identify the morphological features and spatial characteristics of gated communities to map them based on the land cover map and the quality of life index. The importance of this proposal is related to the fact that there are no official statistics on gated communities in most Latin American countries. The proposal was tested in Marília, a medium-sized city in southeastern Brazil. Geographic object-based image analysis with high-resolution satellite images and 2010 demographic census variables were used to support the research procedures. The accuracy of the output was 83.3%. It was found that there is a positive correlation between the quality of life index and the occurrence of high-standard gated communities (golden ghettos). They were mainly identified by the following land cover classes: white painted concrete slabs/light-colored roof tiles, and the existence of pavement, pools, and herbaceous vegetation. In addition to mapping the gated communities, it was possible to classify them according to the categories proposed in the literature (golden ghettos and lifestyle gated communities). Full article

Automated building extraction from high-resolution satellite imagery is a challenging research problem, and several issues remain with respect to the variety of variables to be accounted for. In this paper we present an approach for building detection using multiple cues. We use the shadow, shape, and color features of buildings to propose our approach, known as Building Detection with Shadow Verification (BDSV). BDSV has three main pillars, which are: (1) tile building detection (TBD) to detect roof tile buildings; (2) flat building detection (FBD) to detect non-tile flat buildings according to shape features; and (3) results fusion used to fuse and aggregate results from previous blocks. Analyses performed over different study areas reveal high quality percentage and precision metrics, exceeding 95%. Performance analysis over the SztaKi–Inria and Istanbul datasets shows that BDSV outperforms benchmark algorithms. Full article