LiDAR Point Cloud Recognition and Visualization with Deep Learning for Overhead Contact Inspection

Construction of a Semantic Segmentation Network for the Overhead Catenary System Point Cloud Based on Multi-Scale Feature Fusion

Accurate semantic segmentation results of the overhead catenary system (OCS) are significant for OCS component extraction and geometric parameter detection. Actually, the scenes of OCS are complex, and the density of point cloud data obtained through Light Detection and Ranging (LiDAR) scanning is uneven due to the character difference of OCS components. However, due to the inconsistent component points, it is challenging to complete better semantic segmentation of the OCS point cloud with the existing deep learning methods. Therefore, this paper proposes a point cloud multi-scale feature fusion refinement structure neural network (PMFR-Net) for semantic segmentation of the OCS point cloud. The PMFR-Net includes a prediction module and a refinement module. The innovations of the prediction module include the double efficient channel attention module (DECA) and the serial hybrid domain attention (SHDA) structure. The point cloud refinement module (PCRM) is used as the refinement module of the network. DECA focuses on detail features; SHDA strengthens the connection of contextual semantic information; PCRM further refines the segmentation results of the prediction module. In addition, this paper created and released a new dataset of the OCS point cloud. Based on this dataset, the overall accuracy (OA), F1-score, and mean intersection over union (MIoU) of PMFR-Net reached 95.77%, 93.24%, and 87.62%, respectively. Compared with four state-of-the-art (SOTA) point cloud deep learning methods, the comparative experimental results showed that PMFR-Net achieved the highest accuracy and the shortest training time. At the same time, PMFR-Net segmentation performance on S3DIS public dataset is better than the other four SOTA segmentation methods. In addition, the effectiveness of DECA, SHDA structure, and PCRM was verified in the ablation experiment. The experimental results show that this network could be applied to practical applications.

Deep Learning Using Multiple Degrees of Maximum-Intensity Projection for PET/CT Image Classification in Breast Cancer

Deep learning (DL) has become a remarkably powerful tool for image processing recently. However, the usefulness of DL in positron emission tomography (PET)/computed tomography (CT) for breast cancer (BC) has been insufficiently studied. This study investigated whether a DL model using images with multiple degrees of PET maximum-intensity projection (MIP) images contributes to increase diagnostic accuracy for PET/CT image classification in BC. We retrospectively gathered 400 images of 200 BC and 200 non-BC patients for training data. For each image, we obtained PET MIP images with four different degrees (0°, 30°, 60°, 90°) and made two DL models using Xception. One DL model diagnosed BC with only 0-degree MIP and the other used four different degrees. After training phases, our DL models analyzed test data including 50 BC and 50 non-BC patients. Five radiologists interpreted these test data. Sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) were calculated. Our 4-degree model, 0-degree model, and radiologists had a sensitivity of 96%, 82%, and 80–98% and a specificity of 80%, 88%, and 76–92%, respectively. Our 4-degree model had equal or better diagnostic performance compared with that of the radiologists (AUC = 0.936 and 0.872–0.967, p = 0.036–0.405). A DL model similar to our 4-degree model may lead to help radiologists in their diagnostic work in the future.

Novel CE-CBCE feature extraction method for object classification using a low-density LiDAR point cloud

Low-end LiDAR sensor provides an alternative for depth measurement and object recognition for lightweight devices. However due to low computing capacity, complicated algorithms are incompatible to be performed on the device, with sparse information further limits the feature available for extraction. Therefore, a classification method which could receive sparse input, while providing ample leverage for the classification process to accurately differentiate objects within limited computing capability is required. To achieve reliable feature extraction from a sparse LiDAR point cloud, this paper proposes a novel Clustered Extraction and Centroid Based Clustered Extraction Method (CE-CBCE) method for feature extraction followed by a convolutional neural network (CNN) object classifier. The integration of the CE-CBCE and CNN methods enable us to utilize lightweight actuated LiDAR input and provides low computing means of classification while maintaining accurate detection. Based on genuine LiDAR data, the final result shows reliable accuracy of 97% through the method proposed.

Towards an Optimal Footprint Based Area Coverage Strategy for a False-Ceiling Inspection Robot

False-ceiling inspection is a critical factor in pest-control management within a built infrastructure. Conventionally, the false-ceiling inspection is done manually, which is time-consuming and unsafe. A lightweight robot is considered a good solution for automated false-ceiling inspection. However, due to the constraints imposed by less load carrying capacity and brittleness of false ceilings, the inspection robots cannot rely upon heavy batteries, sensors, and computation payloads for enhancing task performance. Hence, the strategy for inspection has to ensure efficiency and best performance. This work presents an optimal functional footprint approach for the robot to maximize the efficiency of an inspection task. With a conventional footprint approach in path planning, complete coverage inspection may become inefficient. In this work, the camera installation parameters are considered as the footprint defining parameters for the false ceiling inspection. An evolutionary algorithm-based multi-objective optimization framework is utilized to derive the optimal robot footprint by minimizing the area missed and path-length taken for the inspection task. The effectiveness of the proposed approach is analyzed using numerical simulations. The results are validated on an in-house developed false-ceiling inspection robot-Raptor-by experiment trials on a false-ceiling test-bed.

Railway Overhead Contact System Point Cloud Classification

As the railway overhead contact system (OCS) is the key component along the high-speed railway, it is crucial to detect the quality of the OCS. Compared with conventional manual OCS detection, the vehicle-mounted Light Detection and Ranging (LiDAR) technology has advantages such as high efficiency and precision, which can solve the problems of OCS detection difficulty, low efficiency, and high risk. Aiming at the contact cables, return current cables, and catenary cables in the railway vehicle-mounted LiDAR OCS point cloud, this paper used a scale adaptive feature classification algorithm and the DBSCAN (density-based spatial clustering of applications with noise) algorithm considering OCS characteristics to classify the OCS point cloud. Finally, the return current cables, catenary cables, and contact cables in the OCS were accurately classified and extracted. To verify the accuracy of the method presented in this paper, we compared the experimental results of this article with the classification results of TerraSolid, and the classification results were evaluated in terms of four accuracy indicators. According to statistics, the average accuracy of using this method to extract two sets of OCS point clouds is 99.83% and 99.89%, respectively; the average precision is 100% and 99.97%, respectively; the average recall is 99.16% and 99.42%, respectively; and the average overall accuracy is 99.58% and 99.69% respectively, which is overall better than TerraSolid. The experimental results showed that this approach could accurately and quickly extract the complete OCS from the point cloud. It provides a new method for processing railway OCS point clouds and has high engineering application value in railway component detection.

Two-Dimensional LiDAR Sensor-Based Three-Dimensional Point Cloud Modeling Method for Identification of Anomalies inside Tube Structures for Future Hypersonic Transportation

The hyperloop transportation system has emerged as an innovative next-generation transportation system. In this system, a capsule-type vehicle inside a sealed near-vacuum tube moves at 1000 km/h or more. Not only must this transport tube span over long distances, but it must be clear of potential hazards to vehicles traveling at high speeds inside the tube. Therefore, an automated infrastructure anomaly detection system is essential. This study sought to confirm the applicability of advanced sensing technology such as Light Detection and Ranging (LiDAR) in the automatic anomaly detection of next-generation transportation infrastructure such as hyperloops. To this end, a prototype two-dimensional LiDAR sensor was constructed and used to generate three-dimensional (3D) point cloud models of a tube facility. A technique for detecting abnormal conditions or obstacles in the facility was used, which involved comparing the models and determining the changes. The design and development process of the 3D safety monitoring system using 3D point cloud models and the analytical results of experimental data using this system are presented. The tests on the developed system demonstrated that anomalies such as a 25 mm change in position were accurately detected. Thus, we confirm the applicability of the developed system in next-generation transportation infrastructure.