Early detection of occluded moving vehicles at intersections can prevent collisions, but most of the existing sensors only detect objects in sight. Sound propagates around obstacles by means such as reflection and diffraction, allowing passive acoustic sensing of the occluded vehicle. We propose a deep learning-based acoustic non-line-of-sight (NLOS) vehicle detection method. With the direction-of-arrival feature and time-frequency feature calculated from the microphone array data as inputs in image form, we designed and trained the parallel neural network to perceive the direction of the occluded moving vehicle at intersections. Since intelligent vehicles react differently to the approaching and leaving occluded moving vehicle, we further distinguished the occluded moving vehicle’s approaching/leaving status. To evaluate the proposed method, we collected data from different locations in the urban environment. The experimental results show that the classification for 6-class intersection traffic conditions reached 96.71%, and the occluded approaching vehicle was detected 1 second before it entered the line of sight, providing additional reaction time for intelligent vehicles. The direction of the occluded moving vehicle is accurately predicted, and the approaching/leaving status is further inferred, providing detailed traffic information for the intelligent vehicles’ response decisions. Furthermore, experiments show that the predictions of our method outperform the state-of-the-art acoustic NLOS approach vehicle detection baseline on real-world traffic datasets. Our code and dataset: https://github.com/RST2detection/Acoustic-Occluded-Vehicle-Detection.

In this paper, we investigate how to complete human body shape models by combining shape and flow estimation given two consecutive depth images. Shape completion is a challenging task in computer vision that is highly under-constrained when considering partial depth observations. Besides model based strategies that exploit strong priors, and consequently struggle to preserve fine geometric details, learning based approaches build on weaker assumptions and can benefit from efficient implicit representations. We adopt such a representation and explore how the motion flow between two consecutive frames can contribute to the shape completion task. In order to effectively exploit the flow information, our architecture combines both estimations and implements two features for robustness: First, an all-to-all attention module that encodes the correlation between points in the same frame and between corresponding points in different frames; Second, a coarse-dense to fine-sparse strategy that balances the representation ability and the computational cost. Our experiments demonstrate that the flow actually benefits human body model completion. They also show that our method outperforms the state-of-the-art approaches for shape completion on 2 benchmarks, considering different human shapes, poses, and clothing.

OBJECTIVE: To develop an information model for automating evaluation of concordance between patient preferences and end-of-life care. METHODS: We modeled and validated 15 end-of-life care preference option domains, to which we mapped preferences recorded in standardized advance care planning documents and 232 end-of-life care events defined by procedure and medication codes. Patient preferences and end-of-life care events were available in electronic health records. Data from Kaiser Permanente Southern California modeling and testing populations were evaluated for concordance between patients' preferences and the end-of-life care events they experienced. RESULTS: The information model successfully assessed concordance between patient preferences and end-of-life care events. Among 388 expired patients in the modeling population, 4164 care events occurred, 4100 (98%) of which were preference-concordant, and 64 (2%) of which were preference-discordant. Including end-of-life care events that did not occur increased the number of observations to 6029; 99% were preference-concordant. At the level of individuals, 72% (278) of patients experienced only preference-concordant care events, 13% (50) experienced at least one preference-discordant care event, and 15% (60) experienced no preference-related care events. DISCUSSION: Model limitations pertain to assumptions that are required to match advance care planning documents with patient preference options and exclusion of preferred care that did not occur. Further research is required to apply the model to larger populations and to investigate the need for additional preference options. CONCLUSION: An information model for automating the assessment of the concordance between patients' advance care planning preferences and the end-of-life care they received was effective in a small population and has the potential to assess population-level preference-concordance on an ongoing basis.