The comprehensive integration of wireless technology in intelligent connected vehicles (ICVs) demands rigorous and practical Over-the-air (OTA) performance testing. However, the large physical dimensions of vehicles render direct application of standardized mobile phone testing methods outlined by Cellular Telecommunications and Internet Association and 3rd Generation Partnership Project impractical. Employing compact antenna test range for vehicle testing faces significant challenges such as high costs and potential safety hazards during 3D rotation for a vehicle, while existing spherical near-field testing methods fail to accurately evaluate the Total Radiated Power (TRP) and Total Isotropic Sensitivity (TIS) for multi-antenna spatial diversity systems, a common configuration in modern ICVs to ensure robust coverage. This paper proposes a novel, efficient, and comprehensive measurement methodology specifically designed for TRP and TIS testing of multiple transceivers, addressing the gap in current approaches. The solution involves characterizing the passive radiation patterns of the vehicle’s multiple antennas and functionally isolating individual transceivers to determine their respective port radiated power and radiated sensitivity. These parameters are then used to calculate the effective isotropic radiated power and effective isotropic sensitivity, ultimately deriving the overall multi-antenna TRP and TIS. In addition to precision, a significant advantage of this method is its dramatically reduced test time; for instance, TIS measurement for a single frequency band can be completed within thirty minutes instead of the dozens of hours required by traditional methods. This approach represents the only viable and practical solution for wireless performance evaluation of ICVs.

Facial emotion recognition is an inherently difficult problem, not only due to individual facial feature diversity but also racial and cultural differences. Compound facial emotion recognition makes the problem even more difficult because the discrimination between the dominant emotion and the complementary emotion is usually weak. To mitigate this problem, we propose the two-stage recognition method. The first stage is a coarse recognition stage and the second stage is a fine recognition stage. By doing this the classification for symmetrical emotion labels is enhanced. Beyond this, we make good use of the context information existing in the same label to correct some false-classification so that the recognition can be more robust. In this contest, our method can achieve very promising results.

A narrative collage is an interesting image editing method for summarizing the main theme or storyline behind an image collection. We present a novel method to generate narrative images with plausible semantic scene structures. To achieve this goal, we introduce a layer graph and a scene graph to represent the relative depth order and semantic relationship between image objects, respectively. We first cluster the input image collection to select representative images, and then we extract a group of semantic salient objects from each representative image. Both layer graphs and scene graphs are constructed and combined according to our specific rules for reorganizing the extracted objects in every image. We design an energy model to appropriately locate every object on the final canvas. The experimental results show that our method can produce competitive narrative collage results and that it performs well on a wide range of image collections.