As a new product of the Internet and big data era, migration data are of great significance for the revealing of the complex dynamic network patterns of urban agglomerations and for studying the relations between cities by using the “space of flows” model. Based on Baidu migration data of one week in 2021, this paper constructs a 30 × 30 rational data matrix for cities in Zhongyuan Urban Agglomeration and depicts the network pattern from static and dynamic perspectives by using social network analysis and dynamic network visualization. The results show that the network of Zhongyuan Urban Agglomeration is characterized by a circular structure with Zhengzhou as the center, a city belt around Zhengzhou as the connection, subcentral cities as the support and peripheral cities as the extension. Zhengzhou is the core city of the entire network, related to which the central and backbone networks divided in this paper account for nearly 40% of the total migration. Shangqiu, Luoyang, Zhoukou and Handan also play an important role in the structure of the migration network as subcentral cities. For a single city, the migration scale generally peaks on weekends and reaches its minimum during Tuesday to Thursday. Regarding the relations between cities, the migration variation can be divided into four types: peaking on Monday, peaking on weekends, bimodal and stable, and there are obvious phenomena of weekly commuting. In general, the links between cities outside Henan Province and other cities in the urban agglomeration are relatively weak, and the constraints of administrative regionalization on intercity migration are presumed to still exist. According to the results, the location advantage for multi-layer development and construction of Zhongyuan Urban Agglomeration should be made use of. In addition, the status as the core city and the radiation range should be strengthened, and the connections between the peripheral cities and the other cities should be improved, so as to promote the integrated and efficient development of the whole urban agglomeration.

Fast and accurate semantic scene understanding is essential for mobile robots to operate in complex environments. An emerging research topic, panoptic segmentation, serves such a purpose by performing the tasks of semantic segmentation and instance segmentation in a unified framework. To improve the performance of LiDAR-based real-time panoptic segmentation, this study proposes a spatiotemporal sequential data fusion strategy that fused points in “thing classes” based on accurate data statistics. The data fusion strategy could increase the proportion of valuable data in unbalanced datasets, and thus managed to mitigate the adverse impact of class imbalance in the limited training data. Subsequently, by improving the codec network, the multiscale features shared by semantic and instance branches were efficiently aggregated to achieve accurate panoptic segmentation for each LiDAR scan. Experiments on the publicly available dataset SemanticKITTI showed that our approach could achieve an effective balance between accuracy and efficiency, and it was also applicable to other point cloud segmentation tasks.