Aerial cameras are one of the main devices for obtaining ground images in the air. Since the industrial community sets higher requirements of aerial cameras’ self-locating performance yearly using aerial cameras to locate ground targets has become a research hotspot in recent years. Based on the situation that no ground control point exists in target areas, the calculation principle of the aerial remote sensing image positioning algorithm has been analyzed by establishing different positioning models. Several error analysis models of the positioning algorithm based on the total differential method and the Monte Carlo method are established, and relevant factors that cause the positioning error are summarized. The last section proposes the optimization direction of aerial camera positioning algorithms in the future, which are verified by related simulation experiments. This paper provides a certain degree of guidelines in this area for researchers, who can quickly understand the current development and optimization direction of target geo-location algorithms of aerial remote sensing imagery.

Predicting traffic data on traffic networks is essential to transportation management. It is a challenging task due to the complicated spatial‐temporal dependency. The latest studies mainly focus on capturing temporal and spatial dependencies with spatially dense traffic data. However, when traffic data become spatially sparse, existing methods cannot capture sufficient spatial correlation information and thus fail to learn the temporal periodicity sufficiently. To address these issues, we propose a novel deep learning framework, Multi‐component Spatial‐Temporal Graph Attention Convolutional Networks (MSTGACN), for traffic prediction, and we successfully apply it to predicting traffic flow and speed with spatially sparse data. MSTGACN mainly consists of three independent components to model three types of periodic information. Each component in MSTGACN combines dilated causal convolution, graph convolution layer, and the weight‐shared graph attention layer. Experimental results on three real‐world traffic datasets, METR‐LA, PeMS‐BAY, and PeMSD7‐sparse, demonstrate the superior performance of our method in the case of spatially sparse data.