Search for: All records

Reconstructing 4D vehicular activity (3D space and time) from cameras is useful for autonomous vehicles, commuters and local authorities to plan for smarter and safer cities. Traffic is inherently repetitious over long periods, yet current deep learning-based 3D reconstruction methods have not considered such repetitions and have difficulty generalizing to new intersection-installed cameras. We present a novel approach exploiting longitudinal (long-term) repetitious motion as self-supervision to reconstruct 3D vehicular activity from a video captured by a single fixed camera. Starting from off-the-shelf 2D keypoint detections, our algorithm optimizes 3D vehicle shapes and poses, and then clusters their trajectories in 3D space. The 2D keypoints and trajectory clusters accumulated over long-term are later used to improve the 2D and 3D keypoints via self-supervision without any human annotation. Our method improves reconstruction accuracy over state of the art on scenes with a significant visual difference from the keypoint detector’s training data, and has many applications including velocity estimation, anomaly detection and vehicle counting. We demonstrate results on traffic videos captured at multiple city intersections, collected using our smartphones, YouTube, and other public datasets. 

In this paper, a novel hierarchical signal processing methodology is proposed for generator condition monitoring and fault diagnosis based on raw electrical waveform data in power networks, which can often be measured by strategically located waveform sensors. The impact of generator short circuit faults on strategically located electrical waveform sensors in power networks are firstly investigated and validated in Matlab Simulink. Based on the large set of electrical waveform data produced by Matlab Simulink, a hierarchical algorithm is then designed to locate fault site location and monitor the condition of generators in power networks. Finally, the proposed methodology is validated in 14-bus IEEE standard power network under different scenarios (e.g, one generator fault, two-generator-fault, various aging levels, etc). Our results show that we can locate fault site location and monitor the aging condition of generators in power networks. Compared to traditional condition monitoring and fault diagnosis based on generator sensors, our proposed methodology can monitor a large number of generators based on a limited number of waveform sensors, which promises to reduce the cost of the maintenance and improve the reliability of the power grid.