Learning-based point cloud completion tasks have shown potential in various critical tasks, such as object detection, assignment, and registration. However, accurately and efficiently quantifying the shape error between the predicted point clouds generated by networks and the ground truth remains challenging. While EMD-based loss functions excel in shape detail and perceived density distribution, their approach can only yield results with significant discrepancies from the actual EMD within a tolerable training time. To address these challenges, we first propose the initial price based on the auction algorithm, reducing the number of iterations required for the algorithm while ensuring the correctness of the assignment results. We then introduce an algorithm to compute the initial price through a successive shortest path and the Euclidean information between its nodes. Finally, we adopt a series of optimization strategies to speed up the algorithm and offer an EMD approximation scheme for point cloud problems that balances time loss and computational accuracy based on point cloud data characteristics. Our experimental results confirm that our algorithm achieves the smallest gap with the real EMD within an acceptable time range and yields the best results in end-to-end training.

The use of social media platforms has grown dramatically in recent times. Combined with the rise of mobile computing, users are now more connected and spend more of their time online. Social media has been used during emergency events where the public and authorities have used it as a form of communication and to receive information. Due to this, emergency managers and first responders can use this information to increase their awareness about an on-going crisis and aid decision making. The challenge here lies in processing this deluge of information and filtering it for insights that are useful for this purpose. This paper presents the Slandail Monitor, a system for harvesting and filtering a social media stream for emergency related social media data. Spatial and temporal data attached to each message are used with the analysed content of each message to summarise on-going emergency events as reported on social media. This information is combined with a visualisation component to allow a user to quickly assess an event by location, time, and by topic. Issues about ethical data harvesting and privacy are also addressed by the system in a computational way by logging potentially sensitive information in the intrusion index.