Search

Achieving the accurate perception of occluded objects for autonomous vehicles is a challenging problem. Human vision can always quickly locate important object regions in complex external scenes, while other regions are only roughly analysed or ignored, defined as the visual attention mechanism. However, the perception system of autonomous vehicles cannot know which part of the point cloud is in the region of interest. Therefore, it is meaningful to explore how to use the visual attention mechanism in the perception system of autonomous driving. In this paper, we propose the model of the spatial attention frustum to solve object occlusion in 3D object detection. The spatial attention frustum can suppress unimportant features and allocate limited neural computing resources to critical parts of the scene, thereby providing greater relevance and easier processing for higher-level perceptual reasoning tasks. To ensure that our method maintains good reasoning ability when faced with occluded objects with only a partial structure, we propose a local feature aggregation module to capture more complex local features of the point cloud. Finally, we discuss the projection constraint relationship between the 3D bounding box and the 2D bounding box and propose a joint anchor box projection loss function, which will help to improve the overall performance of our method. The results of the KITTI dataset show that our proposed method can effectively improve the detection accuracy of occluded objects. Our method achieves 89.46%, 79.91% and 75.53% detection accuracy in the easy, moderate, and hard difficulty levels of the car category, and achieves a 6.97% performance improvement especially in the hard category with a high degree of occlusion. Our one-stage method does not need to rely on another refining stage, comparable to the accuracy of the two-stage method. [ABSTRACT FROM AUTHOR]

The vehicle HVAC (heating, ventilating, and air conditioning) system aims to keep passengers thermal comfort and reduce energy consumption. One effective measure is to use temperature prediction to optimize HVAC systems. This paper aimed to comprehensively investigate the potential of machine learning methods applied to cockpit temperature prediction and proposed a deep learning method considering the Spatio-temporal correlation of the temperature field. Specifically, this study constructs a topological description of the temperature field inspired by the spatial and temporal correlations revealed by the Navier-Stokes equations. The Graph Convolutional Network (GCN) is used to capture the topological structure to obtain spatial features, and the Gated Recurrent Unit (GRU) is used to capture the dynamic change of node attribute to obtain temporal features. Finally, the GCGRU model can extract Spatio-temporal features of the temperature field. The experimental results show that the prediction method using Spatio-temporal features for the temperature field is feasible. The prediction performance is better than all the baseline methods and has the robustness to the data noise. This work is enlightening and may have a further reference to the feasibility study of the vehicle cabin air temperature prediction model. [ABSTRACT FROM AUTHOR]