We propose MTC-BEV, a novel multi-modal 3D object detection framework for autonomous driving that achieves robust and efficient perception by combining spatial, temporal, and semantic cues. MTC-BEV integrates image and LiDAR features in the Bird’s-Eye View (BEV) space, where heterogeneous modalities are aligned and fused through the Bidirectional Cross-Modal Attention Fusion (BCAP) module with positional encodings. To model temporal consistency, the Temporal Fusion (TTFusion) module explicitly compensates for ego-motion and incorporates past BEV features. In addition, a segmentation-guided BEV enhancement projects 2D instance masks into BEV space, highlighting semantically informative regions. Experiments on the nuScenes dataset demonstrate that MTC-BEV achieves a nuScenes Detection Score (NDS) of 72.4% at 14.91 FPS, striking a favorable balance between accuracy and efficiency. These results confirm the effectiveness of the proposed design, highlighting the potential of semantic-guided cross-modal and temporal fusion for robust 3D object detection in autonomous driving.

This paper proposed an intelligent temperature-controlled load energy-saving technology based on multi-modal target detection, recognition and tracking, aiming to study the integration of traditional power energy-saving technology and high-tech multi-modal target detection, recognition and tracking technology. The method proposed in this paper was to use the energy management model of temperature-controlled load based on multi-modal target detection, identification and tracking and aggregate response algorithm to carry out energy-saving management of user's temperature-controlled load. The two algorithms jointly carried out energy-saving and optimal management of electrical appliances. Through the analysis of the electrical load optimization management experiment, after the energy saving optimization of the air conditioner, its 24-hour total power has dropped by 61kW, and the temperature has dropped by 3 degrees Celsius. After the energy saving optimization of the electric water heater, its 24-hour total power has dropped by 37kW and the temperature has dropped by 5 degrees Celsius. This shows that the power load (PL) temperature control and energy-saving technology can effectively save energy and control the temperature of electrical appliances. The experimental results can effectively demonstrate that the research on the optimal control method of the temperature-controlled load energy-saving technology based on multi-modal target detection, identification and tracking is feasible. The results of this study clearly show that the multi-modal target detection, recognition and tracking technology can be well applied to the current PL temperature control and energy saving, which provides a possible development direction for the future PL energy saving processing technology.