LiDAR-based pedestrian detection and tracking (PDT) with high-resolution sensing capability plays an important role in real-world applications such as security monitoring, human behavior analysis, and intelligent transportation. The problem of LiDAR-based PDT suffers from the complex gathering movements and the phenomenon of self- and inter-object occlusions. In this paper, the detection and tracking of dense pedestrians using three-dimensional (3D) real-measured LiDAR point clouds in surveillance applications is studied. To deal with the problem of undersegmentation of dense pedestrian point clouds, the kernel density estimation (KDE) is used for pedestrians center estimation which further leads to a pedestrian segmentation method. Three novel features are defined and used for further PDT performance improvements, which takes advantage of the pedestrians’ posture and body proportion. Finally, a new track management strategy for dense pedestrians is presented to deal with the tracking instability caused by dense pedestrians occlusion. The performance of the proposed method is validated with experiments on the KITTI dataset. The experiment shows that the proposed method can significantly increase F1 score from 0.5122 to 0.7829 compared with the STM-KDE. In addition, compared with AB3DMOT and EagerMOT, the tracking trajectories from the proposed method have the longest average survival time of 36.17 frames.

This paper presents a novel online learning-based fault detection designed for underwater robotic thruster health monitoring. In the fault detection algorithm, we build a mathematical model between the control variable and the propeller speed by fitting collected online work status data to the model. To improve the accuracy of online modeling, a multi-center PSO algorithm with memory ability is utilized to optimize the modeling parameters. Additionally, a model online update mechanism is designed to accommodate the model to the change of thruster work status and sea environment. During the operation, propeller speed of the underwater robot is predicted through the online learning-based model, and the model residuals are used for thruster health monitoring. To avoid false alarm, an adaptive fault detection strategy is established based on model online update mechanism. The proposed method has been extensively evaluated using different underwater robotics, through a sea trial data simulation, a pool test fault detection experiment and a sea trial fault detection experiment. Compared with fixed model-based method, speed prediction MAE of the online learning model is at least 37.9% lower than that of the fixed model. The online learning-based method show no misdiagnosis in experiments, while the fixed model-based method is misdiagnosed. Experimental results show that the proposed method is competitive in terms of accuracy, adaptability, and robustness.

No abstract