Wei Yao

Li Fang, Tianyu Li, Yanghong Lin et al.

Point clouds are vital in computer vision tasks such as 3D reconstruction, autonomous driving, and robotics. However, TLS-acquired point clouds often contain virtual points from reflective surfaces, causing disruptions. This study presents a reflection noise elimination algorithm for TLS point clouds. Our innovative reflection plane detection algorithm, based on geometry-optical models and physical properties, identifies and categorizes reflection points per optical reflection theory. We've adapted the LSFH feature descriptor to retain reflection features, mitigating interference from symmetrical architectural structures. By incorporating the Hausdorff feature distance, the algorithm enhances resilience to ghosting and deformation, improving virtual point detection accuracy. Extensive experiments on the 3DRN benchmark dataset, featuring diverse urban environments with virtual TLS reflection noise, show our algorithm improves precision and recall rates for 3D points in reflective regions by 57.03\% and 31.80\%, respectively. Our method achieves a 9.17\% better outlier detection rate and 5.65\% higher accuracy than leading methods. Access the 3DRN dataset at (https://github.com/Tsuiky/3DRN).

Puzuo Wang, Wei Yao, Jie Shao

Reliance on vast annotations to achieve leading performance severely restricts the practicality of large-scale point cloud semantic segmentation. For the purpose of reducing data annotation costs, effective labeling schemes are developed and contribute to attaining competitive results under weak supervision strategy. Revisiting current weak label forms, we introduce One Class One Click (OCOC), a low cost yet informative quasi scene-level label, which encapsulates point-level and scene-level annotations. An active weakly supervised framework is proposed to leverage scarce labels by involving weak supervision from global and local perspectives. Contextual constraints are imposed by an auxiliary scene classification task, respectively based on global feature embedding and point-wise prediction aggregation, which restricts the model prediction merely to OCOC labels. Furthermore, we design a context-aware pseudo labeling strategy, which effectively supplement point-level supervisory signals. Finally, an active learning scheme with a uncertainty measure - temporal output discrepancy is integrated to examine informative samples and provides guidance on sub-clouds query, which is conducive to quickly attaining desirable OCOC annotations and reduces the labeling cost to an extremely low extent. Extensive experimental analysis using three LiDAR benchmarks collected from airborne, mobile and ground platforms demonstrates that our proposed method achieves very promising results though subject to scarce labels. It considerably outperforms genuine scene-level weakly supervised methods by up to 25\% in terms of average F1 score and achieves competitive results against full supervision schemes. On terrestrial LiDAR dataset - Semantics3D, using approximately 2\textpertenthousand{} of labels, our method achieves an average F1 score of 85.2\%, which increases by 11.58\% compared to the baseline model.

Rong Huang, Wei Yao, Zhong Xu et al.

Forest land plays a vital role in global climate, ecosystems, farming and human living environments. Therefore, forest biomass estimation methods are necessary to monitor changes in the forest structure and function, which are key data in natural resources research. Although accurate forest biomass measurements are important in forest inventory and assessments, high-density measurements that involve airborne light detection and ranging (LiDAR) at a low flight height in large mountainous areas are highly expensive. The objective of this study was to quantify the aboveground biomass (AGB) of a plateau mountainous forest reserve using a system that synergistically combines an unmanned aircraft system (UAS)-based digital aerial camera and LiDAR to leverage their complementary advantages. In this study, we utilized digital aerial photogrammetry (DAP), which has the unique advantages of speed, high spatial resolution, and low cost, to compensate for the deficiency of forestry inventory using UAS-based LiDAR that requires terrain-following flight for high-resolution data acquisition. Combined with the sparse LiDAR points acquired by using a high-altitude and high-speed UAS for terrain extraction, dense normalized DAP point clouds can be obtained to produce an accurate and high-resolution canopy height model (CHM). Based on the CHM and spectral attributes obtained from multispectral images, we estimated and mapped the AGB of the region of interest with considerable cost efficiency. Our study supports the development of predictive models for large-scale wall-to-wall AGB mapping by leveraging the complementarity between DAP and LiDAR measurements. This work also reveals the potential of utilizing a UAS-based digital camera and LiDAR synergistically in a plateau mountainous forest area.

Jie Shao, Wei Yao, Puzuo Wang et al.

Developments in three-dimensional real worlds promote the integration of geoinformation and building information models (BIM) known as GeoBIM in urban construction. Light detection and ranging (LiDAR) integrated with global navigation satellite systems can provide geo-referenced spatial information. However, constructing detailed urban GeoBIM poses challenges in terms of LiDAR data quality. BIM models designed from software are rich in geometrical information but often lack accurate geo-referenced locations. In this paper, we propose a complementary strategy that integrates LiDAR point clouds with as-designed BIM models for reconstructing urban scenes. A state-of-the-art deep learning framework and graph theory are first combined for LiDAR point cloud segmentation. A coarse-to-fine matching program is then developed to integrate object point clouds with corresponding BIM models. Results show the overall segmentation accuracy of LiDAR datasets reaches up to 90%, and average positioning accuracies of BIM models are 0.023 m for pole-like objects and 0.156 m for buildings, demonstrating the effectiveness of the method in segmentation and matching processes. This work offers a practical solution for rapid and accurate urban GeoBIM construction.

Jie Shao, Wei Yao, Peng Wan et al.

Registration of unmanned aerial vehicle laser scanning (ULS) and ground light detection and ranging (LiDAR) point clouds in forests is critical to create a detailed representation of a forest structure and an accurate inversion of forest parameters. However, forest occlusion poses challenges for marker-based registration methods, and some marker-free automated registration methods have low efficiency due to the process of object (e.g., tree, crown) segmentation. Therefore, we use a divide-and-conquer strategy and propose an automated and efficient method to register ULS and ground LiDAR point clouds in forests. Registration involves coarse alignment and fine registration, where the coarse alignment of point clouds is divided into vertical and horizontal alignment. The vertical alignment is achieved by ground alignment, which is achieved by the transformation relationship between normal vectors of the ground point cloud and the horizontal plane, and the horizontal alignment is achieved by canopy projection image matching. During image matching, vegetation points are first distinguished by the ground filtering algorithm, and then, vegetation points are projected onto the horizontal plane to obtain two binary images. To match the two images, a matching strategy is used based on canopy shape context features, which are described by a two-point congruent set and canopy overlap. Finally, we implement coarse alignment of ULS and ground LiDAR datasets by combining the results of ground alignment and image matching and finish fine registration. Also, the effectiveness, accuracy, and efficiency of the proposed method are demonstrated by field measurements of forest plots. Experimental results show that the ULS and ground LiDAR data in different plots are registered, of which the horizontal alignment errors are less than 0.02 m, and the average runtime of the proposed method is less than 1 second.

Puzuo Wang, Wei Yao

While there are novel point cloud semantic segmentation schemes that continuously surpass state-of-the-art results, the success of learning an effective model usually rely on the availability of abundant labeled data. However, data annotation is a time-consuming and labor-intensive task, particularly for large-scale airborne laser scanning (ALS) point clouds involving multiple classes in urban areas. Thus, how to attain promising results while largely reducing labeling works become an essential issue. In this study, we propose a deep-learning based weakly supervised framework for semantic segmentation of ALS point clouds, exploiting potential information from unlabeled data subject to incomplete and sparse labels. Entropy regularization is introduced to penalize the class overlap in predictive probability. Additionally, a consistency constraint by minimizing the discrepancy distance between instant and ensemble predictions is designed to improve the robustness of predictions. Finally, we propose an online soft pseudo-labeling strategy to create extra supervisory sources in an efficient and nonpaprametric way. Extensive experimental analysis using three benchmark datasets demonstrates that in case of sparse point annotations, our proposed method significantly boosts the classification performance without compromising the computational efficiency. It outperforms current weakly supervised methods and achieves a comparable result against full supervision competitors. For the ISPRS 3D Labeling Vaihingen data, by using only 0.1% of labels, our method achieves an overall accuracy of 83.0% and an average F1 score of 70.0%, which have increased by 6.9% and 12.8% respectively, compared to model trained by sparse label information only.

Jacquelyn Shelton, Przemyslaw Polewski, Wei Yao

Since the outbreak of COVID-19 policy makers have been relying upon non-pharmacological interventions to control the outbreak. With air pollution as a potential transmission vector there is need to include it in intervention strategies. We propose a U-net driven quantile regression model to predict $PM_{2.5}$ air pollution based on easily obtainable satellite imagery. We demonstrate that our approach can reconstruct $PM_{2.5}$ concentrations on ground-truth data and predict reasonable $PM_{2.5}$ values with their spatial distribution, even for locations where pollution data is unavailable. Such predictions of $PM_{2.5}$ characteristics could crucially advise public policy strategies geared to reduce the transmission of and lethality of COVID-19.

Rong Huang, Wei Yao, Yusheng Xu et al.

Registration is a fundamental but critical task in point cloud processing, which usually depends on finding element correspondence from two point clouds. However, the finding of reliable correspondence relies on establishing a robust and discriminative description of elements and the correct matching of corresponding elements. In this letter, we develop a coarse-to-fine registration strategy, which utilizes rotation-invariant features and a new weighted graph matching method for iteratively finding correspondence. In the graph matching method, the similarity of nodes and edges in Euclidean and feature space are formulated to construct the optimization function. The proposed strategy is evaluated using two benchmark datasets and compared with several state-of-the-art methods. Regarding the experimental results, our proposed method can achieve a fine registration with rotation errors of less than 0.2 degrees and translation errors of less than 0.1m.

Przemyslaw Polewski, Jacquelyn Shelton, Wei Yao et al.

In this paper, we introduce a framework for segmenting instances of a common object class by multiple active contour evolution over semantic segmentation maps of images obtained through fully convolutional networks. The contour evolution is cast as an energy minimization problem, where the aggregate energy functional incorporates a data fit term, an explicit shape model, and accounts for object overlap. Efficient solution neighborhood operators are proposed, enabling optimization through metaheuristics such as simulated annealing. We instantiate the proposed framework in the context of segmenting individual fallen stems from high-resolution aerial multispectral imagery. We validated our approach on 3 real-world scenes of varying complexity. The test plots were situated in regions of the Bavarian Forest National Park, Germany, which sustained a heavy bark beetle infestation. Evaluations were performed on both the polygon and line segment level, showing that the multi-contour segmentation can achieve up to 0.93 precision and 0.82 recall. An improvement of up to 7 percentage points (pp) in recall and 6 in precision compared to an iterative sample consensus line segment detection was achieved. Despite the simplicity of the applied shape parametrization, an explicit shape model incorporated into the energy function improved the results by up to 4 pp of recall. Finally, we show the importance of using a deep learning based semantic segmentation method as the basis for individual stem detection. Our method is a step towards increased accessibility of automatic fallen tree mapping, due to higher cost efficiency of aerial imagery acquisition compared to laser scanning. The precise fallen tree maps could be further used as a basis for plant and animal habitat modeling, studies on carbon sequestration as well as soil quality in forest ecosystems.

Puzuo Wang, Wei Yao

Competitive point cloud semantic segmentation results usually rely on a large amount of labeled data. However, data annotation is a time-consuming and labor-intensive task, particularly for three-dimensional point cloud data. Thus, obtaining accurate results with limited ground truth as training data is considerably important. As a simple and effective method, pseudo labels can use information from unlabeled data for training neural networks. In this study, we propose a pseudo-label-assisted point cloud segmentation method with very few sparsely sampled labels that are normally randomly selected for each class. An adaptive thresholding strategy was proposed to generate a pseudo-label based on the prediction probability. Pseudo-label learning is an iterative process, and pseudo labels were updated solely on ground-truth weak labels as the model converged to improve the training efficiency. Experiments using the ISPRS 3D sematic labeling benchmark dataset indicated that our proposed method achieved an equally competitive result compared to that using a full supervision scheme with only up to 2$\unicode{x2030}$ of labeled points from the original training set, with an overall accuracy of 83.7% and an average F1 score of 70.2%.

Dimitrios Marmanis, Wei Yao, Fathalrahman Adam et al.

Very High Spatial Resolution (VHSR) large-scale SAR image databases are still an unresolved issue in the Remote Sensing field. In this work, we propose such a dataset and use it to explore patch-based classification in urban and periurban areas, considering 7 distinct semantic classes. In this context, we investigate the accuracy of large CNN classification models and pre-trained networks for SAR imaging systems. Furthermore, we propose a Generative Adversarial Network (GAN) for SAR image generation and test, whether the synthetic data can actually improve classification accuracy.