Indoor scene segmentation based on 3-D laser point cloud is important for rebuilding and classification, especially for permanent building structure. However, the existing segmentation methods mainly focus on the large-scale planar structures but ignore the other sharp structures and details, which would cause accuracy degradation in scene reconstruction. To handle this issue, an iterative Gaussian mapping-based segmentation strategy has been proposed in this article, which goes from rough segmentation to refined one iteratively to decompose the indoor scene into detectable point cloud clusters layer by layer. An improved model fitting algorithm based on the maximum likelihood estimation sampling consensus (MLESAC) algorithm is proposed for refined segmentation, which is called the Prior-MLESAC algorithm, to deal with the extraction of both vertical and nonvertical planar and cylindrical structures. The experimental results demonstrate that planar and cylindrical structures are segmented more completely by the proposed strategy, and more details of the indoor structure are restored than other existing methods.

Concrete wall surfaces are prone to cracking for a long time, which affects the stability of concrete structures and may even lead to collapse accidents. In view of this, it is necessary to recognize and distinguish the concrete cracks. Then, the stability of concrete will be known. In this paper, we propose a novel approach by fusing fractal dimension and UHK-Net deep learning network to conduct the semantic recognition of concrete cracks. We first use the local fractal dimensions to study the concrete cracking and roughly determine the location of concrete crack. Then, we use the U-Net Haar-like (UHK-Net) network to construct the crack segmentation network. Ultimately, the different types of concrete crack images are used to verify the advantage of the proposed method by comparing with FCN, U-Net, YOLO v5 network. Results show that the proposed method can not only characterize the dark crack images, but also distinguish small and fine crack images. The pixel accuracy (PA), mean pixel accuracy (MPA), and mean intersection over union (MIoU) of crack segmentation determined by the proposed method are all greater than 90%.

Accurate fire identification can help to control fires. Traditional fire detection methods are mainly based on temperature or smoke detectors. These detectors are susceptible to damage or interference from the outside environment. Meanwhile, most of the current deep learning methods are less discriminative with respect to dynamic fire and have lower detection precision when a fire changes. Therefore, we propose a dynamic convolution YOLOv5 fire detection method using a video sequence. Our method first uses the K-mean++ algorithm to optimize anchor box clustering; this significantly reduces the rate of classification error. Then, the dynamic convolution is introduced into the convolution layer of YOLOv5. Finally, pruning of the network heads of YOLOv5’s neck and head is carried out to improve the detection speed. Experimental results verify that the proposed dynamic convolution YOLOv5 fire detection method demonstrates better performance than the YOLOv5 method in recall, precision and F1-score. In particular, compared with three other deep learning methods, the precision of the proposed algorithm is improved by 13.7%, 10.8% and 6.1%, respectively, while the F1-score is improved by 15.8%, 12% and 3.8%, respectively. The method described in this paper is applicable not only to short-range indoor fire identification but also to long-range outdoor fire detection.

In order to improve the accuracy of fire identification based on video in the Internet-of-Things environment, this article proposes a new fire identification algorithm by merging fire segmentation and multifeature fusion of fire. First, according to the relationship between R and Y channels, the improved YCbCr models are established for initial fire segmentation under reflection and nonreflection conditions, respectively. Simultaneously, the reflection and nonreflection conditions are judged by comparing the areas obtained by the two improved YCbCr models. Second, an improved region growing algorithm is proposed for fine fire segmentation by making use of the relationship between the seed point and its adjacent points. The seed points are determined using the weighted average of centroid coordinates of each segmented image. Finally, the quantitative indicators of fire identification are given according to the variation coefficient of fire area, the dispersion of centroid, and the circularity. Extensive experiments were conducted, and the experimental results demonstrate that the proposed fire detection method considerably outperforms the traditional methods on average in terms of three performance indexes: precision, recall, and $F1$ -score. Specifically, compared with the deep learning method, the precision of the proposed method is slightly higher. Although the recall of the proposed method is slightly lower than the deep learning method, its computation complexity is low.

Terrestrial laser scanning (TLS) is a widely used remote sensing technique which can produce very dense point cloud data very promptly and is particularly suited for surface deformation monitoring. Deformation magnitude is typically estimated by comparing TLS scans over the same area but at different time epochs of interest. However, there is an issue related to such a method, which is not clear that whether the difference between two successive surveys results from the surface deformation. Hence, it is vital to determine the minimum detectable deformation (MDD) by a TLS device with a given registration and point cloud error level. In this paper, the MDD is determined based on the computation of the point cloud error entropy. The performance of the proposed method is extensively evaluated numerically using simulated plane board deformation point clouds under a range of distances and incidence angles. This proposed method was also successfully applied to deformation monitoring of one landslide test site located in the Wuhan University of Technology. The experimental results demonstrate that the theoretical MDD has a good match with the actual deformation, and the deformation greater than MDD can be accurately detected by the TLS device.

In the last decades, 3-D object recognition has received significant attention. Particularly, in the presence of clutter and occlusion, 3-D object recognition is a challenging task. In this article, we present an object recognition pipeline to identify the objects from cluttered scenes. A highly descriptive, robust, and computationally efficient local shape descriptor (LSD) is first designed to establish the correspondences between a model point cloud and a scene point cloud. Then, a clustering method, which utilizes the local reference frames (LRFs) of the keypoints, is proposed to select the correct correspondences. Finally, an index is developed to verify the transformation hypotheses. The experiments are conducted to validate the proposed object recognition method. The experimental results demonstrate that the proposed LSD holds high descriptor matching performance and the clustering method can well group the correct correspondences. The index is also very effective to filter the false transformation hypotheses. All these enhance the recognition performance of our method.